{"name":"Macrostack AI API price index","url":"https://www.macrostack.net/compute/ai-api-prices","license":"CC-BY-4.0","licenseUrl":"https://creativecommons.org/licenses/by/4.0/","citeAs":"Macrostack (2026). AI API price index, read 16 Oct 2026. CC BY 4.0. https://www.macrostack.net/compute/ai-api-prices","observed":"2026-10-16","basis":"Published list prices in US dollars: per million tokens for text and embeddings (input, cached input, output), per audio hour for speech-to-text (per-minute prices × 60), per million characters for text-to-speech (per-thousand prices × 1,000). Standard or pay-as-you-go tier, standard prompt-length band. Where a page prints a promotional and a regular price, the regular one is ranked. Batch, priority, regional and committed prices are described, not ranked.","disclaimer":"Published list prices read on each provider's own pricing page on the date in each row. Macrostack measures nothing and is paid by none of these providers. Different models are different products: compare like with like (see sameOpenModel).","providers":[{"slug":"openai","name":"OpenAI","group":"model maker","pricingUrl":"https://developers.openai.com/api/docs/pricing","readOn":"2026-10-16","freeTier":"none stated for text models. The page lists only omni-moderation-latest as \"Free\" (Moderation), plus tool allowances: File search storage \"$0.10 / GB per day (1 GB free)\" and ChatKit upload storage \"$0.10 / GB-day after 1 GB free per account per month\".","discounts":["Batch: the page prints Batch prices at half of Standard, e.g. gpt-6-astra $5.00 input / $0.50 cached input / $25.00 output per 1M tokens (short context), vs $10.00 / $1.00 / $50.00 Standard","Flex: the page prints the same prices as Batch for the models it lists, e.g. gpt-6-astra $5.00 / $0.50 / $25.00; gpt-6-luna $0.05 / $0.005 / $0.25","Fast (premium, not a discount): \"Priority processing was renamed Fast mode on July 30, 2026.\" Fast prices are double Standard for the gpt-6 family, e.g. gpt-6-astra $20.00 / $2.00 / $100.00","Ultrafast (premium, not a discount): gpt-6-astra $60.00 input / $6.00 cached / $300.00 output; gpt-6.1-sol $12.00 / $0.60 / $60.00 (short context)"]},{"slug":"anthropic","name":"Anthropic","group":"model maker","pricingUrl":"https://platform.claude.com/docs/en/about-claude/pricing","readOn":"2026-10-16","freeTier":"No free tier in the price table. FAQ \"Are there free tiers or trials?\": \"New users receive a small amount of free credits to test the API.\" Extended trials for enterprise evaluation via sales.","discounts":["Batch API: \"a 50% discount on both input and output tokens\" (page prints batch prices, e.g. Claude Fable 5.1 $5 / $25 per MTok; Claude Opus 5.5 $2 / $10; Claude Sonnet 5.5 $1 / $5; Claude Haiku 5.5 $0.05 / $0.25 for prompts up to 100,000 tokens and $0.25 / $1.25 over 100,000)","Prompt caching: 5-minute cache write 1.25x base input price; 1-hour cache write 2x base input price; cache read (hit) 0.1x base input price (0.025x on Claude Fable 5.1 and Claude Mythos 5.1; 0.05x on Claude Opus 5.5 and Claude Sonnet 5.5). These multipliers stack with the Batch API discount and data residency","Volume discounts: \"may be available for high-volume users. These are negotiated on a case-by-case basis.\""]},{"slug":"google-gemini","name":"Google Gemini","group":"model maker","pricingUrl":"https://ai.google.dev/gemini-api/docs/pricing","readOn":"2026-10-16","freeTier":"Free tier: \"For developers and small projects getting started with the Gemini API\" — \"Limited access to certain models\", \"Free input & output tokens\", \"Google AI Studio access\", \"Content used to improve our products\". Per model, input and output are \"Free of charge\" on Gemini 3.8 Flash, 3.6 Flash, 3.5 Flash-Lite, 3.1 Flash-Lite, 3 Flash Preview, 2.5 Pro, 2.5 Flash, 2.5 Flash-Lite and Gemini Embedding 2; Gemini 3.1 Pro Preview is \"Not available\" on the free tier. Re-read 16 Oct: \"Gemini 4 Argon is not available on the Free tier or on the Google AI Pro plan.\" Context caching is free on the free tier for 3.8 Flash, 3.6 Flash and 3 Flash Preview, and \"Not available\" for the others. \"Google AI Studio usage is free of charge in all available regions.\"","discounts":["Batch API (50% cost reduction) — Paid tier; e.g. Gemini 3.8 Flash Batch $0.375 input / $1.875 output per 1M tokens through December 31, 2026 (vs $0.75 / $3.75 Standard); Gemini 2.5 Pro Batch $0.625 / $5.00 for prompts <= 200k tokens","Flex: on Gemini 3.8 Flash the page lists the same prices as Batch ($0.375 input / $1.875 output through December 31, 2026)","Priority (premium, not a discount): Gemini 3.8 Flash $1.35 input / $6.75 output through December 31, 2026; $2.70 / $13.50 starting January 1, 2027","Enterprise (Gemini Enterprise Agent Platform): \"Volume-based discounts (based on usage)\""]},{"slug":"mistral","name":"Mistral AI","group":"model maker","pricingUrl":"https://docs.mistral.ai/inference/pricing","readOn":"2026-10-16","freeTier":"No free API tier with a dollar amount is stated. mistral.ai/pricing: 'Mistral's Free plan provides limited access to Vibe ... On the Free plan, you also get access to Mistral Studio.' mistral.ai/cloud/inference FAQ: 'Yes, in Studio, you can test-prompt general models in the agent playground, or try documents and speech in the dedicated OCR and audio playgrounds.' (Paid consumer plans on mistral.ai/pricing list monthly API credits, e.g. '$15 /mo in API credits'; the page layout did not make the plan-to-credit mapping unambiguous, so no figure is assigned here.)","discounts":["Batch: 'High-volume processing, at half price' / 'Batch processing, for high-volume work, cuts the price by 50%' (the docs pricing page also has a Batch toggle).","Cached input: 'cutting input costs by 90%' — cached-input prices are printed per model in the rows.","Mistral Large 4 is on a 'Temporary sale price. The struck-through amount is the original price.' (tooltip on the docs pricing page; no end date given)."]},{"slug":"cohere","name":"Cohere","group":"model maker","pricingUrl":"https://cohere.com/pricing","readOn":"2026-10-16","freeTier":"Trial API key: 'API calls made from a Trial API key are free. However, trial keys are rate limited and are not permitted to be used for production or commercial purposes.' Production keys are 'charged on a pay-as-you-go basis'. Command A+ and North Mini Code are printed as 'API key $0 / Free' and 'Model download $0 / Free'.","discounts":[]},{"slug":"groq","name":"Groq","group":"open-model host","pricingUrl":"https://console.groq.com/docs/models","readOn":"2026-10-16","freeTier":"A Free plan exists: the rate-limits page has a 'Free Plan Limits' tab (e.g. openai/gpt-oss-120b 30 RPM, 1K RPD, 8K TPM, 200K TPD; whisper-large-v3 20 RPM, 7.2K ASH). Upgrading to the pay-as-you-go Developer tier needs a payment method; 'there's no immediate charge'. Billing FAQ: 'We occasionally offer promotional credits, such as during hackathons and special events.' No free dollar credit is stated.","discounts":["Batch API: 'Pricing is at a 50% cost discount compared to synchronous API pricing.' Batch models listed: openai/gpt-oss-20b, openai/gpt-oss-120b, llama-3.3-70b-versatile, llama-3.1-8b-instant, meta-llama/llama-guard-4-12b, whisper-large-v3, whisper-large-v3-turbo. 24-hour to 7-day processing window.","Prompt caching: 'There is a 50% discount for cached input tokens.' Supported only on openai/gpt-oss-20b, openai/gpt-oss-120b, openai/gpt-oss-safeguard-20b. 'The batch discount does not stack with prompt caching discounts.'","Flex service tier: 'Pricing matches the on-demand tier' (10x higher rate limits, paid customers only, may fail with 498 capacity_exceeded).","Performance tier (enterprise only): provisioned throughput bundles, not per-token; 'Reach out to inquire about pricing.'"]},{"slug":"together","name":"Together AI","group":"open-model host","pricingUrl":"https://www.together.ai/pricing","readOn":"2026-10-16","freeTier":"Pricing page only says 'Start for free, scale on demand' (page meta description); no credit amount. The official Credits doc says: 'Together AI does not currently offer free trials. Access to the Together platform requires a minimum $15 credit purchase.' Two chat models are priced at zero on the pricing page: Ternary Bonsai 27B ($0.00 / $0.00) and Tev1 4B Experimental (output 'Free').","discounts":["Batch API: docs say 'up to 50% off serverless rates', but 'Selected serverless models run at 50% off batch rates' and the only model listed is openai/whisper-large-v3; 'Models not listed run at standard rates.' The pricing page has a 'Batch API price' toggle but shows no separate batch figures for chat models.","Kimi K3's promotion ('Promotion valid until 10/11/2026' — $2.70 input / $13.50 output instead of $3.00 / $15.00) has ended: re-read 16 Oct, the page prints $3.00 / $0.30 cached / $15.00 with no PROMO tag.","GPU Clusters: reserved per-GPU-hour rates for 3-30, 31-90, 91-180 days (e.g. HGX H100 $3.69 / $3.45 / $3.19) and preemptible compute (HGX H100 $1.99)."]},{"slug":"fireworks","name":"Fireworks AI","group":"open-model host","pricingUrl":"https://docs.fireworks.ai/serverless/pricing","readOn":"2026-10-16","freeTier":"The pricing page states no free tier or credit amount ('Pay per token with pre-paid, usage-based billing. Simply add a payment method to buy credits'). The official billing FAQ is titled 'What happens when I finish my $1 credit?' and says that without a payment method the account is suspended once that $1 credit is used — i.e. a $1 starting credit is implied, not stated as an offer.","discounts":["Batch inference is billed at 50% of serverless pricing on both input and output (docs serverless pricing page).","Prompt-cached input tokens priced lower (per-model cached-input column).","Bulk / pre-paid discounts by contacting sales: 'We offer discounts for bulk or pre-paid purchases.'"]},{"slug":"replicate","name":"Replicate","group":"open-model host","pricingUrl":"https://replicate.com/pricing","readOn":"2026-10-16","freeTier":"The pricing page states no free tier or credit amount (only a 'Try for free' button). The official billing docs ('Free limits') say: 'You can run select models on Replicate for free, but after a bit you'll be asked to set up billing.'","discounts":["Volume discounts: 'We've also got volume discounts for large amounts of spend.' (enterprise)","Site banner on the pricing page: 'Wan 3.0 is 30% off this week' (no Wan 3.0 price printed on the pricing page)"]},{"slug":"deepgram","name":"Deepgram","group":"voice","pricingUrl":"https://deepgram.com/pricing","readOn":"2026-10-16","freeTier":"Pay As You Go: \"Free $200 Credit then pay-as-you-go\"; \"No minimums. No expiration. No credit card required.\" FAQ: \"Every new account receives $200 in free credit, which is equivalent to approximately 43,000 minutes (over 700 hours) of transcription using our Nova model\"; the credit does not expire (\"available until you use it up\").","discounts":["Growth plan: \"Save up to 20%\" with pre-paid annual credits, \"$4K+ / year\"; overages billed at the Growth rate \"plus a 10% premium (plus tax)\" (FAQ)","\"Limited-time promotional rates on streaming\" (Flux English, Nova-3 Monolingual, Nova-3 Multilingual show a current price and a struck regular price); no end date printed","Flux TTS: \"For every $1 you spend on Flux TTS, we'll add $1 in credits — up to $500. Available on Pay As You Go and Growth plans. Offer ends December 31, 2026.\"","Enterprise: \"significant volume discounts\" for millions of minutes per month (FAQ), contact sales"]},{"slug":"elevenlabs","name":"ElevenLabs","group":"voice","pricingUrl":"https://elevenlabs.io/pricing/api","readOn":"2026-10-16","freeTier":"Free plan: \"$0 per month\", \"10k credits per month\" (\"Build for free\"). On the API page the \"Free / Pay as you go\" column includes e.g. 10,000 v4 characters (~10 min), 20,000 Flash / Turbo characters, 4 hours 30 minutes of Scribe v2, 2 hours 30 minutes of Scribe v2 Realtime and 15 min of Speech Engine; pay-as-you-go is \"Start for free\". Separate Startup Grants Program: \"12 months free\", \"33,000,000 characters\" (apply).","discounts":["v4 and v4 Turbo: the \"72% off until Oct 12\" launch promotion ($0.022 and $0.011 per 1K characters) has ended — re-read 16 Oct, the page prints only the regular $0.08 and $0.04","Banner on 10 Oct: \"3x credits included on Creator+ until October 12\" (that end date has passed)","Starter: \"$6 First month 83% off\" — $1 first month, \"Until Oct 18\"","Creator: \"$22 First month 50% off\" — $11 first month","Annual billing: \"two months free — you pay for 10 months\"; monthly equivalents $5 Starter, $18.33 Creator, $82.50 Pro, $249.17 Scale, $825 Business (FAQ)","\"Try v4 with 2x credits for two weeks\" on Creator plans and above, web and mobile apps only (not API)","Enterprise: \"Significant discounts at scale\" (contact sales)","Business plan: \"Low-latency TTS as low as 5c/minute\""]}],"sameOpenModel":[{"model":"Whisper Large v3","modality":"speech-to-text","hosts":[{"provider":"Together AI","model":"Whisper Large v3","input":null,"cachedInput":null,"output":null,"usdPerAudioHour":0.09},{"provider":"Groq","model":"Whisper (whisper-large-v3)","input":null,"cachedInput":null,"output":null,"usdPerAudioHour":0.111}]},{"model":"DeepSeek V4.1 Flash","modality":"text","hosts":[{"provider":"Fireworks AI","model":"DeepSeek V4.1 Flash","input":0.3,"cachedInput":0.006,"output":1.2,"usdPerAudioHour":null},{"provider":"Together AI","model":"DeepSeek V4.1 Flash","input":0.3,"cachedInput":0.006,"output":1.2,"usdPerAudioHour":null}]},{"model":"GLM 5.3","modality":"text","hosts":[{"provider":"Fireworks AI","model":"GLM 5.3","input":1.4,"cachedInput":0.26,"output":4.4,"usdPerAudioHour":null},{"provider":"Mistral AI","model":"Z.ai GLM 5.3","input":1.4,"cachedInput":0.14,"output":4.4,"usdPerAudioHour":null},{"provider":"Together AI","model":"GLM-5.3","input":1.4,"cachedInput":0.26,"output":4.4,"usdPerAudioHour":null}]},{"model":"GLM 5.3 Flash","modality":"text","hosts":[{"provider":"Fireworks AI","model":"GLM 5.3 Flash","input":0.15,"cachedInput":0.03,"output":0.5,"usdPerAudioHour":null},{"provider":"Together AI","model":"GLM-5.3-Flash","input":0.15,"cachedInput":0.03,"output":0.5,"usdPerAudioHour":null}]},{"model":"gpt-oss-120b","modality":"text","hosts":[{"provider":"Fireworks AI","model":"OpenAI GPT OSS 120B","input":0.15,"cachedInput":0.015,"output":0.6,"usdPerAudioHour":null},{"provider":"Groq","model":"GPT OSS 120B (openai/gpt-oss-120b)","input":0.15,"cachedInput":0.075,"output":0.6,"usdPerAudioHour":null},{"provider":"Together AI","model":"gpt-oss-120B","input":0.15,"cachedInput":null,"output":0.6,"usdPerAudioHour":null}]},{"model":"Kimi K3","modality":"text","hosts":[{"provider":"Fireworks AI","model":"Kimi K3","input":3,"cachedInput":0.3,"output":15,"usdPerAudioHour":null},{"provider":"Together AI","model":"Kimi K3","input":3,"cachedInput":0.3,"output":15,"usdPerAudioHour":null}]},{"model":"MiniMax M3","modality":"text","hosts":[{"provider":"Fireworks AI","model":"MiniMax M3","input":0.3,"cachedInput":0.06,"output":1.2,"usdPerAudioHour":null},{"provider":"Together AI","model":"MiniMax M3","input":0.3,"cachedInput":0.06,"output":1.2,"usdPerAudioHour":null}]}],"rows":[{"provider":"openai","model":"gpt-6-astra","modality":"text","unit":"1M tokens","input":10,"cachedInput":1,"output":50,"price":null,"tier":"standard","condition":"Short context (≤272K input tokens)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-6-astra","modality":"text","unit":"1M tokens","input":20,"cachedInput":2,"output":75,"price":null,"tier":"standard","condition":"Long context (>272K input tokens)","inIndex":false,"whyNot":"long-prompt band; the index ranks the standard band","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-6.1-sol","modality":"text","unit":"1M tokens","input":2,"cachedInput":0.1,"output":10,"price":null,"tier":"standard","condition":"Short context (≤272K input tokens)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-6.1-sol","modality":"text","unit":"1M tokens","input":4,"cachedInput":0.2,"output":15,"price":null,"tier":"standard","condition":"Long context (>272K input tokens)","inIndex":false,"whyNot":"long-prompt band; the index ranks the standard band","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-6-sol","modality":"text","unit":"1M tokens","input":2,"cachedInput":0.2,"output":10,"price":null,"tier":"standard","condition":"Short context (≤272K input tokens)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-6-sol","modality":"text","unit":"1M tokens","input":4,"cachedInput":0.4,"output":15,"price":null,"tier":"standard","condition":"Long context (>272K input tokens)","inIndex":false,"whyNot":"long-prompt band; the index ranks the standard band","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-6-luna","modality":"text","unit":"1M tokens","input":0.1,"cachedInput":0.01,"output":0.5,"price":null,"tier":"standard","condition":"Short context (≤272K input tokens)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-6-luna","modality":"text","unit":"1M tokens","input":0.2,"cachedInput":0.02,"output":0.75,"price":null,"tier":"standard","condition":"Long context (>272K input tokens)","inIndex":false,"whyNot":"long-prompt band; the index ranks the standard band","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-5.6-sol","modality":"text","unit":"1M tokens","input":4,"cachedInput":0.4,"output":20,"price":null,"tier":"standard","condition":"Short context (≤272K input tokens); promotional pricing 'available at least through November 21, 2026'","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-5.6-sol","modality":"text","unit":"1M tokens","input":8,"cachedInput":0.8,"output":30,"price":null,"tier":"standard","condition":"Long context (>272K input tokens); promotional pricing 'available at least through November 21, 2026'","inIndex":false,"whyNot":"long-prompt band; the index ranks the standard band","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-5.6-terra","modality":"text","unit":"1M tokens","input":2,"cachedInput":0.2,"output":12,"price":null,"tier":"standard","condition":"Short context (≤272K input tokens)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-5.6-terra","modality":"text","unit":"1M tokens","input":4,"cachedInput":0.4,"output":18,"price":null,"tier":"standard","condition":"Long context (>272K input tokens)","inIndex":false,"whyNot":"long-prompt band; the index ranks the standard band","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-5.6-luna","modality":"text","unit":"1M tokens","input":0.2,"cachedInput":0.02,"output":1.2,"price":null,"tier":"standard","condition":"Short context (≤272K input tokens)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-5.6-luna","modality":"text","unit":"1M tokens","input":0.4,"cachedInput":0.04,"output":1.8,"price":null,"tier":"standard","condition":"Long context (>272K input tokens)","inIndex":false,"whyNot":"long-prompt band; the index ranks the standard band","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-5.5","modality":"text","unit":"1M tokens","input":5,"cachedInput":0.5,"output":30,"price":null,"tier":"standard","condition":"Short context (≤272K input tokens)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-5.5","modality":"text","unit":"1M tokens","input":10,"cachedInput":1,"output":45,"price":null,"tier":"standard","condition":"Long context (>272K input tokens)","inIndex":false,"whyNot":"long-prompt band; the index ranks the standard band","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-5.4","modality":"text","unit":"1M tokens","input":2.5,"cachedInput":0.25,"output":15,"price":null,"tier":"standard","condition":"Short context (≤272K input tokens)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-5.4","modality":"text","unit":"1M tokens","input":5,"cachedInput":0.5,"output":22.5,"price":null,"tier":"standard","condition":"Long context (>272K input tokens)","inIndex":false,"whyNot":"long-prompt band; the index ranks the standard band","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-5.4-mini","modality":"text","unit":"1M tokens","input":0.75,"cachedInput":0.075,"output":4.5,"price":null,"tier":"standard","condition":"Short context only (no long-context price listed)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"gpt-5.4-nano","modality":"text","unit":"1M tokens","input":0.2,"cachedInput":0.02,"output":1.25,"price":null,"tier":"standard","condition":"Short context only (no long-context price listed)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"text-embedding-3-small","modality":"embeddings","unit":"1M tokens","input":0.02,"cachedInput":null,"output":null,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"openai","model":"text-embedding-3-large","modality":"embeddings","unit":"1M tokens","input":0.13,"cachedInput":null,"output":null,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://developers.openai.com/api/docs/pricing"},{"provider":"anthropic","model":"Claude Fable 5.1","modality":"text","unit":"1M tokens","input":10,"cachedInput":0.25,"output":50,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing"},{"provider":"anthropic","model":"Claude Mythos 5.1","modality":"text","unit":"1M tokens","input":10,"cachedInput":0.25,"output":50,"price":null,"tier":"standard","condition":"limited availability (verified organisations only)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing"},{"provider":"anthropic","model":"Claude Fable 5","modality":"text","unit":"1M tokens","input":10,"cachedInput":1,"output":50,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing"},{"provider":"anthropic","model":"Claude Mythos 5","modality":"text","unit":"1M tokens","input":10,"cachedInput":1,"output":50,"price":null,"tier":"standard","condition":"limited availability (verified organisations only)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing"},{"provider":"anthropic","model":"Claude Opus 5.5","modality":"text","unit":"1M tokens","input":4,"cachedInput":0.2,"output":20,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing"},{"provider":"anthropic","model":"Claude Opus 5","modality":"text","unit":"1M tokens","input":5,"cachedInput":0.5,"output":25,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing"},{"provider":"anthropic","model":"Claude Opus 4.8","modality":"text","unit":"1M tokens","input":5,"cachedInput":0.5,"output":25,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing"},{"provider":"anthropic","model":"Claude Sonnet 5.5","modality":"text","unit":"1M tokens","input":2,"cachedInput":0.1,"output":10,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing"},{"provider":"anthropic","model":"Claude Sonnet 5","modality":"text","unit":"1M tokens","input":2,"cachedInput":0.2,"output":10,"price":null,"tier":"standard","condition":"introductory $2/$10 price is now the standard price","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing"},{"provider":"anthropic","model":"Claude Sonnet 4.6","modality":"text","unit":"1M tokens","input":3,"cachedInput":0.3,"output":15,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing"},{"provider":"anthropic","model":"Claude Haiku 5.5","modality":"text","unit":"1M tokens","input":0.1,"cachedInput":0.01,"output":0.5,"price":null,"tier":"standard","condition":"for prompts up to 100,000 tokens","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing"},{"provider":"anthropic","model":"Claude Haiku 5.5","modality":"text","unit":"1M tokens","input":0.5,"cachedInput":0.05,"output":2.5,"price":null,"tier":"standard","condition":"for prompts over 100,000 tokens","inIndex":false,"whyNot":"long-prompt band; the index ranks the standard band","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing"},{"provider":"anthropic","model":"Claude Haiku 4.5","modality":"text","unit":"1M tokens","input":1,"cachedInput":0.1,"output":5,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing"},{"provider":"google-gemini","model":"Gemini 4 Argon","modality":"text","unit":"1M tokens","input":2,"cachedInput":0.1,"output":10,"price":null,"tier":"standard","condition":"through November 30, 2026; added to the page 15 Oct (read 16 Oct); not on the free tier","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini 4 Argon","modality":"text","unit":"1M tokens","input":4,"cachedInput":0.2,"output":20,"price":null,"tier":"standard","condition":"starting December 1, 2026","inIndex":false,"whyNot":"scheduled price from 1 December 2026","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini 3.8 Flash","modality":"text","unit":"1M tokens","input":0.75,"cachedInput":0.075,"output":3.75,"price":null,"tier":"standard","condition":"through December 31, 2026","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini 3.8 Flash","modality":"text","unit":"1M tokens","input":1.5,"cachedInput":0.15,"output":7.5,"price":null,"tier":"standard","condition":"starting January 1, 2027","inIndex":false,"whyNot":"scheduled price from 1 January 2027","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini 3.6 Flash","modality":"text","unit":"1M tokens","input":0.75,"cachedInput":0.075,"output":3.75,"price":null,"tier":"standard","condition":"through December 31, 2026","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini 3.6 Flash","modality":"text","unit":"1M tokens","input":1.5,"cachedInput":0.15,"output":7.5,"price":null,"tier":"standard","condition":"starting January 1, 2027","inIndex":false,"whyNot":"scheduled price from 1 January 2027","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini 3.5 Flash-Lite","modality":"text","unit":"1M tokens","input":0.3,"cachedInput":0.03,"output":2.5,"price":null,"tier":"standard","condition":"one input price for text / image / video / audio","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini 3.1 Flash-Lite","modality":"text","unit":"1M tokens","input":0.25,"cachedInput":0.025,"output":1.5,"price":null,"tier":"standard","condition":"text / image / video input; audio input $0.50, audio caching $0.05","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini 3.1 Pro Preview","modality":"text","unit":"1M tokens","input":2,"cachedInput":0.2,"output":12,"price":null,"tier":"standard","condition":"prompts <= 200k tokens; not available on the free tier","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini 3.1 Pro Preview","modality":"text","unit":"1M tokens","input":4,"cachedInput":0.4,"output":18,"price":null,"tier":"standard","condition":"prompts > 200k tokens; not available on the free tier","inIndex":false,"whyNot":"long-prompt band; the index ranks the standard band","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini 3 Flash Preview","modality":"text","unit":"1M tokens","input":0.5,"cachedInput":0.05,"output":3,"price":null,"tier":"standard","condition":"text / image / video input; audio input $1.00, audio caching $0.10","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini 2.5 Pro","modality":"text","unit":"1M tokens","input":1.25,"cachedInput":0.125,"output":10,"price":null,"tier":"standard","condition":"prompts <= 200k tokens","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini 2.5 Pro","modality":"text","unit":"1M tokens","input":2.5,"cachedInput":0.25,"output":15,"price":null,"tier":"standard","condition":"prompts > 200k tokens","inIndex":false,"whyNot":"long-prompt band; the index ranks the standard band","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini 2.5 Flash","modality":"text","unit":"1M tokens","input":0.3,"cachedInput":0.03,"output":2.5,"price":null,"tier":"standard","condition":"text / image / video input; audio input $1.00, audio caching $0.1","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini 2.5 Flash-Lite","modality":"text","unit":"1M tokens","input":0.1,"cachedInput":0.01,"output":0.4,"price":null,"tier":"standard","condition":"text / image / video input; audio input $0.30, audio caching $0.03","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"google-gemini","model":"Gemini Embedding 2","modality":"embeddings","unit":"1M tokens","input":0.2,"cachedInput":null,"output":null,"price":null,"tier":"standard","condition":"text input; free of charge on the free tier","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"provider":"mistral","model":"Mistral Large 4","modality":"text","unit":"1M tokens","input":0.68,"cachedInput":0.07,"output":2.09,"price":null,"tier":"standard","condition":"Temporary sale price (no end date); original $1.36 in / $0.14 cached / $4.18 out. Public Preview.","inIndex":false,"whyNot":"temporary sale price; the index ranks the list price","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Mistral Large 3","modality":"text","unit":"1M tokens","input":0.5,"cachedInput":0.05,"output":1.5,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Mistral Medium 3.5","modality":"text","unit":"1M tokens","input":1.5,"cachedInput":0.15,"output":7.5,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Mistral Small 4","modality":"text","unit":"1M tokens","input":0.15,"cachedInput":0.015,"output":0.6,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Ministral 3 14B","modality":"text","unit":"1M tokens","input":0.2,"cachedInput":0.02,"output":0.2,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Ministral 3 8B","modality":"text","unit":"1M tokens","input":0.15,"cachedInput":0.015,"output":0.15,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Ministral 3 3B","modality":"text","unit":"1M tokens","input":0.1,"cachedInput":0.01,"output":0.1,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Z.ai GLM 5.3","modality":"text","unit":"1M tokens","input":1.4,"cachedInput":0.14,"output":4.4,"price":null,"tier":"standard","condition":"Third-party model hosted by Mistral","inIndex":true,"whyNot":null,"openModel":"glm-5.3","readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Codestral","modality":"text","unit":"1M tokens","input":0.3,"cachedInput":0.03,"output":0.9,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Codestral Embed","modality":"embeddings","unit":"1M tokens","input":0.15,"cachedInput":0.015,"output":null,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Mistral Embed","modality":"embeddings","unit":"1M tokens","input":0.1,"cachedInput":null,"output":null,"price":null,"tier":"standard","condition":"Price from the GA model card (not on the pricing page)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Mistral Moderation 2","modality":"text","unit":"1M tokens","input":0,"cachedInput":0,"output":0,"price":null,"tier":"standard","condition":"Printed as Free","inIndex":false,"whyNot":"a safety classifier, not a general model","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"OCR 4.1","modality":"image","unit":"1K pages","input":null,"cachedInput":0.4,"output":null,"price":4,"tier":"standard","condition":"Per 1,000 pages; cached $0.4 /1000 Pages. mistral.ai/cloud/inference also prints 'Document AI $5 / 1000 pages'","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Voxtral Mini Transcribe 2","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":0.0003,"output":null,"price":0.003,"usdPerAudioHour":0.18,"tier":"standard","condition":"Per minute of audio input; cached $0.0003 /Min","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Voxtral Mini Transcribe Realtime","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.006,"usdPerAudioHour":0.36,"tier":"standard","condition":"Price from the GA model card (not on the pricing page)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Voxtral TTS","modality":"text-to-speech","unit":"1M characters","input":0,"cachedInput":0,"output":16,"price":16,"usdPerMillionChars":16,"tier":"standard","condition":"Printed as input $0 /M Chars, output $16 /M Chars (= $0.016 per 1K characters)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"mistral","model":"Mistral Large 4","modality":"text","unit":"1M tokens","input":1.36,"cachedInput":0.14,"output":4.18,"price":null,"tier":"standard","condition":"List price — struck through on the page during the temporary sale","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.mistral.ai/inference/pricing"},{"provider":"cohere","model":"Command A+","modality":"text","unit":"1M tokens","input":null,"cachedInput":null,"output":null,"price":0,"tier":"standard","condition":"Printed as 'API key $0 / Free' and 'Model download $0 / Free'; open-source (Apache 2.0); no per-token rate shown","inIndex":false,"whyNot":"printed as free — no per-token price to rank","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Command R","modality":"text","unit":"1M tokens","input":0.15,"cachedInput":null,"output":0.6,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Command R7B","modality":"text","unit":"1M tokens","input":0.0375,"cachedInput":null,"output":0.15,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Transcribe","modality":"speech-to-text","unit":"hour","input":null,"cachedInput":null,"output":null,"price":3.75,"usdPerAudioHour":3.75,"tier":"Model Vault (dedicated instance)","condition":"'From' price, per instance-hour via Model Vault — NOT per audio hour","inIndex":false,"whyNot":"dedicated instance priced per hour, not per unit of use","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Embed 5 Pro","modality":"embeddings","unit":"1M tokens","input":0.12,"cachedInput":null,"output":null,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Embed 5 Fast","modality":"embeddings","unit":"1M tokens","input":0.08,"cachedInput":null,"output":null,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Rerank 4 Fast","modality":"rerank","unit":"1K searches","input":null,"cachedInput":null,"output":null,"price":2,"tier":"standard","condition":"Search = one query with up to 100 documents","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Rerank 4 Pro","modality":"rerank","unit":"1K searches","input":null,"cachedInput":null,"output":null,"price":2.5,"tier":"standard","condition":"Search = one query with up to 100 documents","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Parse 5","modality":"image","unit":"1K pages","input":null,"cachedInput":null,"output":null,"price":1.5,"tier":"standard","condition":"Document parsing, per 1,000 pages","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"North Mini Code","modality":"text","unit":"1M tokens","input":null,"cachedInput":null,"output":null,"price":0,"tier":"standard","condition":"Printed as 'API key $0 / Free' and 'Model download $0 / Free'; open-source (Apache 2.0); no per-token rate shown","inIndex":false,"whyNot":"printed as free — no per-token price to rank","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Aya Expanse (8B and 32B)","modality":"text","unit":"1M tokens","input":0.5,"cachedInput":null,"output":1.5,"price":null,"tier":"standard","condition":"Research models via the API","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Command","modality":"text","unit":"1M tokens","input":1,"cachedInput":null,"output":2,"price":null,"tier":"legacy","condition":"Legacy model, existing customers only","inIndex":false,"whyNot":"legacy model, existing customers only","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Command-light","modality":"text","unit":"1M tokens","input":0.3,"cachedInput":null,"output":0.6,"price":null,"tier":"legacy","condition":"Legacy model, existing customers only","inIndex":false,"whyNot":"legacy model, existing customers only","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Command R 03-2024","modality":"text","unit":"1M tokens","input":0.5,"cachedInput":null,"output":1.5,"price":null,"tier":"legacy","condition":"Legacy model, existing customers only","inIndex":false,"whyNot":"legacy model, existing customers only","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Command R+ 04-2024","modality":"text","unit":"1M tokens","input":3,"cachedInput":null,"output":15,"price":null,"tier":"legacy","condition":"Legacy model, existing customers only","inIndex":false,"whyNot":"legacy model, existing customers only","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Command R+ 08-2024","modality":"text","unit":"1M tokens","input":2.5,"cachedInput":null,"output":10,"price":null,"tier":"legacy","condition":"Legacy model, existing customers only","inIndex":false,"whyNot":"legacy model, existing customers only","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Embed 5 Fast — Model Vault Small","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":3,"tier":"Model Vault (dedicated instance)","condition":"Per instance; monthly rate $2,000","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Embed 5 Fast — Model Vault Medium","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":5,"tier":"Model Vault (dedicated instance)","condition":"Per instance; monthly rate $3,250","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Embed 5 Pro — Model Vault Small","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":3,"tier":"Model Vault (dedicated instance)","condition":"Per instance; monthly rate $2,000","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Embed 5 Pro — Model Vault Medium","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":5,"tier":"Model Vault (dedicated instance)","condition":"Per instance; monthly rate $3,250","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Rerank 4 Fast — Model Vault Medium","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":5,"tier":"Model Vault (dedicated instance)","condition":"Per instance; monthly rate $3,250","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Rerank 4 Pro — Model Vault Medium","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":5,"tier":"Model Vault (dedicated instance)","condition":"Per instance; monthly rate $3,250","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Rerank 4 Pro — Model Vault Large","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":10,"tier":"Model Vault (dedicated instance)","condition":"Per instance; monthly rate $6,500","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Rerank 3.5 — Model Vault Medium","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":5,"tier":"Model Vault (dedicated instance)","condition":"Per instance; monthly rate $3,250","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Parse 5 — Model Vault Medium","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":4,"tier":"Model Vault (dedicated instance)","condition":"Per instance; monthly rate $2,500","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"cohere","model":"Parse 5 — Model Vault XL","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":7,"tier":"Model Vault (dedicated instance)","condition":"Per instance; monthly rate $4,300","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://cohere.com/pricing"},{"provider":"groq","model":"GPT OSS 120B (openai/gpt-oss-120b)","modality":"text","unit":"1M tokens","input":0.15,"cachedInput":0.075,"output":0.6,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":"gpt-oss-120b","readOn":"2026-10-16","sourceUrl":"https://console.groq.com/docs/models"},{"provider":"groq","model":"GPT OSS 20B (openai/gpt-oss-20b)","modality":"text","unit":"1M tokens","input":0.075,"cachedInput":0.037,"output":0.3,"price":null,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://console.groq.com/docs/models"},{"provider":"groq","model":"Safety GPT OSS 20B (openai/gpt-oss-safeguard-20b)","modality":"text","unit":"1M tokens","input":0.075,"cachedInput":0.037,"output":0.3,"price":null,"tier":"standard","condition":"Preview model (evaluation only)","inIndex":false,"whyNot":"a safety classifier, not a general model","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://console.groq.com/docs/models"},{"provider":"groq","model":"Qwen/Qwen3.8-27B (qwen/qwen3.8-27b)","modality":"text","unit":"1M tokens","input":0.8,"cachedInput":null,"output":4,"price":null,"tier":"standard","condition":"Preview model (evaluation only); text + image input, each image counts as 2048 input tokens","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://console.groq.com/docs/models"},{"provider":"groq","model":"Llama Prompt Guard 2 22M (meta-llama/llama-prompt-guard-2-22m)","modality":"text","unit":"1M tokens","input":0.03,"cachedInput":null,"output":0.03,"price":null,"tier":"standard","condition":"Preview model (evaluation only)","inIndex":false,"whyNot":"a safety classifier, not a general model","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://console.groq.com/docs/models"},{"provider":"groq","model":"Prompt Guard 2 86M (meta-llama/llama-prompt-guard-2-86m)","modality":"text","unit":"1M tokens","input":0.04,"cachedInput":null,"output":0.04,"price":null,"tier":"standard","condition":"Preview model (evaluation only)","inIndex":false,"whyNot":"a safety classifier, not a general model","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://console.groq.com/docs/models"},{"provider":"groq","model":"Llama 3.1 8B (llama-3.1-8b-instant)","modality":"text","unit":"1M tokens","input":null,"cachedInput":null,"output":null,"price":null,"tier":"enterprise","condition":"No public price: tagged Enterprise, price column reads Contact Sales","inIndex":false,"whyNot":"no public price — Contact Sales","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://console.groq.com/docs/models"},{"provider":"groq","model":"Llama 3.3 70B (llama-3.3-70b-versatile)","modality":"text","unit":"1M tokens","input":null,"cachedInput":null,"output":null,"price":null,"tier":"enterprise","condition":"No public price: tagged Enterprise, price column reads Contact Sales","inIndex":false,"whyNot":"no public price — Contact Sales","openModel":"llama-3.3-70b","readOn":"2026-10-16","sourceUrl":"https://console.groq.com/docs/models"},{"provider":"groq","model":"MiniMax M2.7 (minimaxai/minimax-m2.7)","modality":"text","unit":"1M tokens","input":null,"cachedInput":null,"output":null,"price":null,"tier":"enterprise","condition":"Preview model; no public price: tagged Enterprise, Contact Sales","inIndex":false,"whyNot":"no public price — Contact Sales","openModel":"minimax-m2.7","readOn":"2026-10-16","sourceUrl":"https://console.groq.com/docs/models"},{"provider":"groq","model":"Whisper (whisper-large-v3)","modality":"speech-to-text","unit":"hour","input":null,"cachedInput":null,"output":null,"price":0.111,"usdPerAudioHour":0.111,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":"whisper-large-v3","readOn":"2026-10-16","sourceUrl":"https://console.groq.com/docs/models"},{"provider":"groq","model":"Whisper Large V3 Turbo (whisper-large-v3-turbo)","modality":"speech-to-text","unit":"hour","input":null,"cachedInput":null,"output":null,"price":0.04,"usdPerAudioHour":0.04,"tier":"standard","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://console.groq.com/docs/models"},{"provider":"groq","model":"Canopy Labs Orpheus V1 English (canopylabs/orpheus-v1-english)","modality":"text-to-speech","unit":"1M characters","input":null,"cachedInput":null,"output":null,"price":22,"usdPerMillionChars":22,"tier":"standard","condition":"Preview model; unit is per 1M characters as printed (= $0.022 per 1K characters)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://console.groq.com/docs/models"},{"provider":"groq","model":"Canopy Labs Orpheus Arabic Saudi (canopylabs/orpheus-arabic-saudi)","modality":"text-to-speech","unit":"1M characters","input":null,"cachedInput":null,"output":null,"price":40,"usdPerMillionChars":40,"tier":"standard","condition":"Preview model; unit is per 1M characters as printed (= $0.04 per 1K characters)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://console.groq.com/docs/models"},{"provider":"together","model":"MiniMax M3","modality":"text","unit":"1M tokens","input":0.3,"cachedInput":0.06,"output":1.2,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":"minimax-m3","readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Kimi K3","modality":"text","unit":"1M tokens","input":3,"cachedInput":0.3,"output":15,"price":null,"tier":"serverless","condition":"List price. Re-read 16 Oct: the promotion the 10 Oct page printed ('Promotion valid until 10/11/2026', $2.70 / $0.27 cached / $13.50) has ended; the page and the docs model table both print $3.00 / $0.30 cached / $15.00.","inIndex":true,"whyNot":null,"openModel":"kimi-k3","readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Qwen3.8-2.4T-A95B","modality":"text","unit":"1M tokens","input":2,"cachedInput":0.25,"output":6,"price":null,"tier":"serverless","condition":"Docs model table prints cached input $0.50","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Muse Glimmer 30B","modality":"text","unit":"1M tokens","input":0.35,"cachedInput":0.04,"output":1.5,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"DeepSeek V4 Pro 0813","modality":"text","unit":"1M tokens","input":1.32,"cachedInput":0.13,"output":3.96,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"DeepSeek V4.1 Flash","modality":"text","unit":"1M tokens","input":0.3,"cachedInput":0.006,"output":1.2,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":"deepseek-v4.1-flash","readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"DeepSeek V4 Flash 0731","modality":"text","unit":"1M tokens","input":0.14,"cachedInput":0.03,"output":0.28,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"GLM-5.3","modality":"text","unit":"1M tokens","input":1.4,"cachedInput":0.26,"output":4.4,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":"glm-5.3","readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"GLM-5.3-Flash","modality":"text","unit":"1M tokens","input":0.15,"cachedInput":0.03,"output":0.5,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":"glm-5.3-flash","readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"GLM-5.2","modality":"text","unit":"1M tokens","input":1.4,"cachedInput":0.26,"output":4.4,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"gpt-oss-120B","modality":"text","unit":"1M tokens","input":0.15,"cachedInput":null,"output":0.6,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":"gpt-oss-120b","readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Llama 3.3 70B","modality":"text","unit":"1M tokens","input":1.04,"cachedInput":null,"output":1.04,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":"llama-3.3-70b","readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Llama 3 8B Instruct Lite","modality":"text","unit":"1M tokens","input":0.14,"cachedInput":null,"output":0.14,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Qwen3 235B A22B Instruct 2507 FP8 Throughput","modality":"text","unit":"1M tokens","input":0.2,"cachedInput":null,"output":0.6,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Qwen3.5-397B-A17B","modality":"text","unit":"1M tokens","input":0.6,"cachedInput":0.35,"output":3.6,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Qwen3.5 9B","modality":"text","unit":"1M tokens","input":0.17,"cachedInput":null,"output":0.25,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Qwen3.6-Plus","modality":"text","unit":"1M tokens","input":0.5,"cachedInput":null,"output":3,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Qwen3.7-Plus","modality":"text","unit":"1M tokens","input":0.32,"cachedInput":null,"output":1.28,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Qwen3.7-Max","modality":"text","unit":"1M tokens","input":1.5,"cachedInput":0.3,"output":4.5,"price":null,"tier":"serverless","condition":"Docs model table prints $2.50 / $0.50 cached / $7.50 for 'Qwen3.7 Max' — conflict with the pricing page","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Qwen3.8 Flash","modality":"text","unit":"1M tokens","input":0.15,"cachedInput":null,"output":0.47,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Qwen2.5 7B Instruct Turbo","modality":"text","unit":"1M tokens","input":0.3,"cachedInput":null,"output":0.3,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"MiniMax M2.7","modality":"text","unit":"1M tokens","input":0.3,"cachedInput":0.06,"output":1.2,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":"minimax-m2.7","readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Gemma 4 31B","modality":"text","unit":"1M tokens","input":0.39,"cachedInput":null,"output":0.97,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Inkling","modality":"text","unit":"1M tokens","input":1,"cachedInput":0.17,"output":4.05,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Cogito v2.1 671B","modality":"text","unit":"1M tokens","input":1.25,"cachedInput":null,"output":1.25,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Rnj-1 Instruct","modality":"text","unit":"1M tokens","input":0.15,"cachedInput":null,"output":0.15,"price":null,"tier":"serverless","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Ternary Bonsai 27B","modality":"text","unit":"1M tokens","input":0,"cachedInput":null,"output":0,"price":null,"tier":"serverless","condition":"Priced at zero (docs print 'Free')","inIndex":false,"whyNot":"printed as free — no per-token price to rank","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Tev1 4B Experimental","modality":"text","unit":"1M tokens","input":0.04,"cachedInput":null,"output":0,"price":null,"tier":"serverless","condition":"Output printed as 'Free'; docs print input $0.042","inIndex":false,"whyNot":"printed as free — no per-token price to rank","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Whisper Large v3","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0015,"usdPerAudioHour":0.09,"tier":"serverless","condition":"Per audio minute; docs list openai/whisper-large-v3 as 50% off in the Batch API","inIndex":true,"whyNot":null,"openModel":"whisper-large-v3","readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Whisper Large v3 (Streaming)","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0035,"usdPerAudioHour":0.21,"tier":"serverless","condition":"Per audio minute","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"NVIDIA Parakeet TDT 0.6B v3","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0015,"usdPerAudioHour":0.09,"tier":"serverless","condition":"Per audio minute","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"NVIDIA Nemotron 3 ASR Streaming 0.6B","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0015,"usdPerAudioHour":0.09,"tier":"serverless","condition":"Per audio minute","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"NVIDIA Nemotron 3.5 ASR","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0045,"usdPerAudioHour":0.27,"tier":"serverless","condition":"Per audio minute (docs list 'NVIDIA Nemotron 3.5 ASR Streaming 0.6B' at $0.0015 — different model string)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"GPT Image 2","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.053,"tier":"serverless","condition":"Per image; docs: per-image prices are estimates and vary with resolution/quality","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"GPT Image 1.5","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.034,"tier":"serverless","condition":"Per image; estimate, varies with parameters","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Nano Banana Pro (Gemini 3 Pro Image)","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.134,"tier":"serverless","condition":"Per image at 1K or 2K; docs: about $0.24 at 4K","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Gemini 3.1 Flash Image (Nano Banana 2)","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.05,"tier":"serverless","condition":"Per image; docs print $0.04657 at 512x512, varies","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Gemini Flash Image 2.5 (Nano Banana)","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.039,"tier":"serverless","condition":"Per image; estimate, varies","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"FLUX.2 [pro]","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.03,"tier":"serverless","condition":"Per image; estimate, varies","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"FLUX.2 [dev]","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.0154,"tier":"serverless","condition":"Per image; estimate, varies","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"FLUX.2 [flex]","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.03,"tier":"serverless","condition":"Per image; estimate, varies","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Ideogram 4.0","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.06,"tier":"serverless","condition":"Per image; estimate, varies","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Qwen Image 2.0","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.04,"tier":"serverless","condition":"Per image; docs print $0.035+","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Qwen Image 2.0 Pro","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.08,"tier":"serverless","condition":"Per image; docs print $0.075+","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"Wan 2.6 Image","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.03,"tier":"serverless","condition":"Per image; estimate, varies","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"NVIDIA HGX H100","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":5.49,"tier":"dedicated inference","condition":"Per GPU per hour, on-demand pay as you go; reserved = Contact sales","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"NVIDIA HGX B200","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":8.99,"tier":"dedicated inference","condition":"Per GPU per hour, on-demand pay as you go","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"NVIDIA HGX H100","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":3.99,"tier":"GPU clusters","condition":"Per GPU per hour, on-demand; preemptible $1.99; reserved $3.69 (3-30 d) / $3.45 (31-90 d) / $3.19 (91-180 d)","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"NVIDIA HGX H200","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":5.99,"tier":"GPU clusters","condition":"Per GPU per hour, on-demand; preemptible $2.99; reserved $4.99 / $4.15 / $3.99","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"NVIDIA HGX B200","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":8.19,"tier":"GPU clusters","condition":"Per GPU per hour, on-demand; preemptible $4.09; reserved $7.99 / $7.79 / $6.79","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"together","model":"NVIDIA HGX B300","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":9.99,"tier":"GPU clusters","condition":"Per GPU per hour, on-demand; preemptible $4.99; reserved = Contact us","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://www.together.ai/pricing"},{"provider":"fireworks","model":"Ember-1","modality":"text","unit":"1M tokens","input":3,"cachedInput":0.3,"output":15,"price":null,"tier":"serverless","condition":"Standard mode; Priority $3.75 / $0.375 / $18.75","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"Kimi K3","modality":"text","unit":"1M tokens","input":3,"cachedInput":0.3,"output":15,"price":null,"tier":"serverless","condition":"Standard mode; Priority $3.75 / $0.375 / $18.75","inIndex":true,"whyNot":null,"openModel":"kimi-k3","readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"Kimi K3 Fast","modality":"text","unit":"1M tokens","input":4.5,"cachedInput":0.45,"output":22.5,"price":null,"tier":"serverless","condition":"Fast serving path; Priority not available","inIndex":false,"whyNot":"faster serving path of a model ranked under its default name","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"Kimi K3 (US)","modality":"text","unit":"1M tokens","input":4.5,"cachedInput":0.45,"output":22.5,"price":null,"tier":"serverless","condition":"US variant, Standard mode; Priority $5.625 / $0.5625 / $28.125","inIndex":false,"whyNot":"US-served variant of a model ranked under its default name","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"DeepSeek V4.1 Flash","modality":"text","unit":"1M tokens","input":0.3,"cachedInput":0.006,"output":1.2,"price":null,"tier":"serverless","condition":"Standard mode; Priority $0.375 / $0.0075 / $1.50","inIndex":true,"whyNot":null,"openModel":"deepseek-v4.1-flash","readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"DeepSeek V4.1 Flash (US)","modality":"text","unit":"1M tokens","input":0.45,"cachedInput":0.009,"output":1.8,"price":null,"tier":"serverless","condition":"US variant, Standard mode; Priority $0.5625 / $0.01125 / $2.25","inIndex":false,"whyNot":"US-served variant of a model ranked under its default name","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"GLM 5.3 Flash","modality":"text","unit":"1M tokens","input":0.15,"cachedInput":0.03,"output":0.5,"price":null,"tier":"serverless","condition":"Standard mode; Priority $0.1875 / $0.0375 / $0.625","inIndex":true,"whyNot":null,"openModel":"glm-5.3-flash","readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"GLM 5.3 Flash (US)","modality":"text","unit":"1M tokens","input":0.225,"cachedInput":0.045,"output":0.75,"price":null,"tier":"serverless","condition":"US variant, Standard mode; Priority $0.28125 / $0.05625 / $0.9375","inIndex":false,"whyNot":"US-served variant of a model ranked under its default name","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"GLM 5.3","modality":"text","unit":"1M tokens","input":1.4,"cachedInput":0.26,"output":4.4,"price":null,"tier":"serverless","condition":"Standard mode; Priority $1.75 / $0.325 / $5.50","inIndex":true,"whyNot":null,"openModel":"glm-5.3","readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"GLM 5.3 (US)","modality":"text","unit":"1M tokens","input":2.1,"cachedInput":0.39,"output":6.6,"price":null,"tier":"serverless","condition":"US variant, Standard mode; Priority $2.625 / $0.4875 / $8.25","inIndex":false,"whyNot":"US-served variant of a model ranked under its default name","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"GLM 5.3 Fast","modality":"text","unit":"1M tokens","input":2.1,"cachedInput":0.39,"output":6.6,"price":null,"tier":"serverless","condition":"Fast serving path; Priority not available","inIndex":false,"whyNot":"faster serving path of a model ranked under its default name","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"Qwen 3.8 Max","modality":"text","unit":"1M tokens","input":2,"cachedInput":0.25,"output":6,"price":null,"tier":"serverless","condition":"Standard mode; Priority $3.00 / $0.375 / $9.00","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"MiniMax M3","modality":"text","unit":"1M tokens","input":0.3,"cachedInput":0.06,"output":1.2,"price":null,"tier":"serverless","condition":"Standard mode; Priority $0.45 / $0.09 / $1.80","inIndex":true,"whyNot":null,"openModel":"minimax-m3","readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"OpenAI GPT OSS 120B","modality":"text","unit":"1M tokens","input":0.15,"cachedInput":0.015,"output":0.6,"price":null,"tier":"serverless","condition":"Standard mode; Priority $0.18 / $0.018 / $0.72","inIndex":true,"whyNot":null,"openModel":"gpt-oss-120b","readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"NVIDIA Nemotron 3.5 Lightning 30B A3B","modality":"text","unit":"1M tokens","input":0.05,"cachedInput":0.01,"output":0.2,"price":null,"tier":"serverless","condition":"Standard mode; Priority $0.0625 / $0.0125 / $0.25","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"NVIDIA Nemotron 3 Ultra (Preview)","modality":"text","unit":"1M tokens","input":0.6,"cachedInput":0.12,"output":2.4,"price":null,"tier":"serverless","condition":"Standard mode; Priority $0.75 / $0.15 / $3.00","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"Less than 4B parameters","modality":"text","unit":"1M tokens","input":0.1,"cachedInput":null,"output":0.1,"price":null,"tier":"serverless","condition":"size band; one price applies uniformly to input and output, no cached rate","inIndex":false,"whyNot":"a size band, not a named model","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"4B – 16B parameters","modality":"text","unit":"1M tokens","input":0.2,"cachedInput":null,"output":0.2,"price":null,"tier":"serverless","condition":"size band; one price applies uniformly to input and output, no cached rate","inIndex":false,"whyNot":"a size band, not a named model","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"More than 16B parameters","modality":"text","unit":"1M tokens","input":0.9,"cachedInput":null,"output":0.9,"price":null,"tier":"serverless","condition":"size band; one price applies uniformly to input and output, no cached rate","inIndex":false,"whyNot":"a size band, not a named model","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"MoE up to 56B parameters (e.g. Mixtral 8x7B)","modality":"text","unit":"1M tokens","input":0.5,"cachedInput":null,"output":0.5,"price":null,"tier":"serverless","condition":"size band; one price applies uniformly to input and output, no cached rate","inIndex":false,"whyNot":"a size band, not a named model","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"MoE 56.1B – 176B parameters (e.g. DBRX, Mixtral 8x22B)","modality":"text","unit":"1M tokens","input":1.2,"cachedInput":null,"output":1.2,"price":null,"tier":"serverless","condition":"size band; one price applies uniformly to input and output, no cached rate","inIndex":false,"whyNot":"a size band, not a named model","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"up to 150M","modality":"embeddings","unit":"1M tokens","input":0.008,"cachedInput":null,"output":null,"price":null,"tier":"serverless","condition":"size band (base model parameter count); billed on input tokens only","inIndex":false,"whyNot":"a size band, not a named model","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"150M – 350M","modality":"embeddings","unit":"1M tokens","input":0.016,"cachedInput":null,"output":null,"price":null,"tier":"serverless","condition":"size band (base model parameter count); billed on input tokens only","inIndex":false,"whyNot":"a size band, not a named model","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"Qwen3 8B","modality":"embeddings","unit":"1M tokens","input":0.1,"cachedInput":null,"output":null,"price":null,"tier":"serverless","condition":"billed on input tokens only (fireworks.ai/pricing prints '$0.1')","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"H100 80 GB GPU","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":8,"tier":"on-demand deployment","condition":"Per GPU, billed per GPU second ($0.134/minute); region-restricted 1.5x premium","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"H200 141 GB GPU","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":8,"tier":"on-demand deployment","condition":"Per GPU, billed per GPU second ($0.134/minute)","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"B200 180 GB GPU","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":13,"tier":"on-demand deployment","condition":"Per GPU, billed per GPU second ($0.217/minute)","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"B300 288 GB GPU","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":15,"tier":"on-demand deployment","condition":"Per GPU, billed per GPU second ($0.250/minute)","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"fireworks","model":"GB300 288 GB GPU","modality":"compute","unit":"hour","input":null,"cachedInput":null,"output":null,"price":20,"tier":"on-demand deployment","condition":"Per GPU, billed per GPU second ($0.334/minute)","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://docs.fireworks.ai/serverless/pricing"},{"provider":"replicate","model":"CPU (Small) (cpu-small)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.000025,"tier":"hardware","condition":"1x CPU, 2GB RAM; $0.09/hr","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"CPU (cpu)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.0001,"tier":"hardware","condition":"4x CPU, 8GB RAM; $0.36/hr","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"Nvidia T4 GPU (gpu-t4)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.000225,"tier":"hardware","condition":"1x GPU, 16GB GPU RAM; $0.81/hr","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"Nvidia L40S GPU (gpu-l40s)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.000975,"tier":"hardware","condition":"1x GPU, 48GB GPU RAM; $3.51/hr","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"2x Nvidia L40S GPU (gpu-l40s-2x)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.00195,"tier":"hardware","condition":"2x GPU, 96GB GPU RAM; $7.02/hr","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"Nvidia A100 (80GB) GPU (gpu-a100-large)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.0014,"tier":"hardware","condition":"1x GPU, 80GB GPU RAM; $5.04/hr","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"2x Nvidia A100 (80GB) GPU (gpu-a100-large-2x)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.0028,"tier":"hardware","condition":"2x GPU, 160GB GPU RAM; $10.08/hr","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"Nvidia H100 GPU (gpu-h100)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.001525,"tier":"hardware","condition":"1x GPU, 80GB GPU RAM; $5.49/hr","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"4x Nvidia A100 (80GB) GPU (gpu-a100-large-4x)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.0056,"tier":"hardware (additional)","condition":"$20.16/hr; available with committed spend contracts","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"8x Nvidia A100 (80GB) GPU (gpu-a100-large-8x)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.0112,"tier":"hardware (additional)","condition":"$40.32/hr; available with committed spend contracts","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"2x Nvidia H100 GPU (gpu-h100-2x)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.00305,"tier":"hardware (additional)","condition":"$10.98/hr; available with committed spend contracts","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"4x Nvidia H100 GPU (gpu-h100-4x)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.0061,"tier":"hardware (additional)","condition":"$21.96/hr; available with committed spend contracts","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"8x Nvidia H100 GPU (gpu-h100-8x)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.0122,"tier":"hardware (additional)","condition":"$43.92/hr; available with committed spend contracts","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"Nvidia H200 GPU (gpu-h200)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.001525,"tier":"hardware (additional)","condition":"$5.49/hr; 'H200 capacity is available with committed spend contracts.'","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"2x Nvidia H200 GPU (gpu-h200-2x)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.00305,"tier":"hardware (additional)","condition":"$10.98/hr; available with committed spend contracts","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"4x Nvidia H200 GPU (gpu-h200-4x)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.0061,"tier":"hardware (additional)","condition":"$21.96/hr; available with committed spend contracts","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"8x Nvidia H200 GPU (gpu-h200-8x)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.0122,"tier":"hardware (additional)","condition":"$43.92/hr; available with committed spend contracts","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"4x Nvidia L40S GPU (gpu-l40s-4x)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.0039,"tier":"hardware (additional)","condition":"$14.04/hr; available with committed spend contracts","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"8x Nvidia L40S GPU (gpu-l40s-8x)","modality":"compute","unit":"second","input":null,"cachedInput":null,"output":null,"price":0.0078,"tier":"hardware (additional)","condition":"$28.08/hr; available with committed spend contracts","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"deepseek-ai / deepseek-r1","modality":"text","unit":"1M tokens","input":3.75,"cachedInput":null,"output":10,"price":null,"tier":"official model","condition":"Output printed per thousand tokens ($0.01 / thousand output tokens), converted to $10.00 per 1M; input printed per million","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"black-forest-labs / flux-1.1-pro","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.04,"tier":"official model","condition":"per output image","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"black-forest-labs / flux-dev","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.025,"tier":"official model","condition":"per output image","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"black-forest-labs / flux-schnell","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.003,"tier":"official model","condition":"Printed as $3.00 per thousand output images, converted to $0.003 per image","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"ideogram-ai / ideogram-v3-quality","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.09,"tier":"official model","condition":"per output image","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"replicate","model":"recraft-ai / recraft-v3","modality":"image","unit":"image","input":null,"cachedInput":null,"output":null,"price":0.04,"tier":"official model","condition":"per output image","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://replicate.com/pricing"},{"provider":"deepgram","model":"Flux English","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0065,"usdPerAudioHour":0.39,"tier":"pay-as-you-go","condition":"streaming; promotional","inIndex":false,"whyNot":"promotional price; the index ranks the regular price","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Flux English","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0077,"usdPerAudioHour":0.462,"tier":"pay-as-you-go","condition":"streaming; regular price","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Flux English","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0057,"usdPerAudioHour":0.342,"tier":"growth","condition":"streaming; promotional","inIndex":false,"whyNot":"Growth plan (prepaid from $4,000 a year); the index ranks pay-as-you-go","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Flux English","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0065,"usdPerAudioHour":0.39,"tier":"growth","condition":"streaming; regular price","inIndex":false,"whyNot":"Growth plan (prepaid from $4,000 a year); the index ranks pay-as-you-go","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Flux Multilingual","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0078,"usdPerAudioHour":0.468,"tier":"pay-as-you-go","condition":"streaming","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Flux Multilingual","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0068,"usdPerAudioHour":0.408,"tier":"growth","condition":"streaming","inIndex":false,"whyNot":"Growth plan (prepaid from $4,000 a year); the index ranks pay-as-you-go","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Nova-3 Monolingual","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0048,"usdPerAudioHour":0.288,"tier":"pay-as-you-go","condition":"streaming; promotional","inIndex":false,"whyNot":"promotional price; the index ranks the regular price","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Nova-3 Monolingual","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0077,"usdPerAudioHour":0.462,"tier":"pay-as-you-go","condition":"streaming; regular price","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Nova-3 Monolingual","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0042,"usdPerAudioHour":0.252,"tier":"growth","condition":"streaming; promotional","inIndex":false,"whyNot":"Growth plan (prepaid from $4,000 a year); the index ranks pay-as-you-go","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Nova-3 Monolingual","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0065,"usdPerAudioHour":0.39,"tier":"growth","condition":"streaming; regular price","inIndex":false,"whyNot":"Growth plan (prepaid from $4,000 a year); the index ranks pay-as-you-go","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Nova-3 Multilingual","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0058,"usdPerAudioHour":0.348,"tier":"pay-as-you-go","condition":"streaming; promotional","inIndex":false,"whyNot":"promotional price; the index ranks the regular price","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Nova-3 Multilingual","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0092,"usdPerAudioHour":0.552,"tier":"pay-as-you-go","condition":"streaming; regular price","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Nova-3 Multilingual","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.005,"usdPerAudioHour":0.3,"tier":"growth","condition":"streaming; promotional","inIndex":false,"whyNot":"Growth plan (prepaid from $4,000 a year); the index ranks pay-as-you-go","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Nova-3 Multilingual","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0078,"usdPerAudioHour":0.468,"tier":"growth","condition":"streaming; regular price","inIndex":false,"whyNot":"Growth plan (prepaid from $4,000 a year); the index ranks pay-as-you-go","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Nova-3 Monolingual","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0043,"usdPerAudioHour":0.258,"tier":"pay-as-you-go","condition":"pre-recorded","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Nova-3 Monolingual","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0036,"usdPerAudioHour":0.216,"tier":"growth","condition":"pre-recorded","inIndex":false,"whyNot":"Growth plan (prepaid from $4,000 a year); the index ranks pay-as-you-go","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Nova-3 Multilingual","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0052,"usdPerAudioHour":0.312,"tier":"pay-as-you-go","condition":"pre-recorded","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Nova-3 Multilingual","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0043,"usdPerAudioHour":0.258,"tier":"growth","condition":"pre-recorded","inIndex":false,"whyNot":"Growth plan (prepaid from $4,000 a year); the index ranks pay-as-you-go","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Whisper Large","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0048,"usdPerAudioHour":0.288,"tier":"pay-as-you-go","condition":"pre-recorded","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Whisper Large","modality":"speech-to-text","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.0048,"usdPerAudioHour":0.288,"tier":"growth","condition":"pre-recorded","inIndex":false,"whyNot":"Growth plan (prepaid from $4,000 a year); the index ranks pay-as-you-go","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Nova-2","modality":"speech-to-text","unit":"hour","input":null,"cachedInput":null,"output":null,"price":0.35,"usdPerAudioHour":0.35,"tier":"pay-as-you-go","condition":"streaming; legacy model, FAQ only, 'for existing deployments'","inIndex":false,"whyNot":"legacy model, existing deployments only","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Enhanced","modality":"speech-to-text","unit":"hour","input":null,"cachedInput":null,"output":null,"price":0.99,"usdPerAudioHour":0.99,"tier":"pay-as-you-go","condition":"legacy model, FAQ only, mode not stated","inIndex":false,"whyNot":"legacy model, existing deployments only","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Base","modality":"speech-to-text","unit":"hour","input":null,"cachedInput":null,"output":null,"price":0.87,"usdPerAudioHour":0.87,"tier":"pay-as-you-go","condition":"legacy model, FAQ only, mode not stated","inIndex":false,"whyNot":"legacy model, existing deployments only","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Flux TTS","modality":"text-to-speech","unit":"1K characters","input":null,"cachedInput":null,"output":null,"price":0.045,"usdPerMillionChars":45,"tier":"pay-as-you-go","condition":"matching-credit promo up to $500 through Dec 31, 2026","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Flux TTS","modality":"text-to-speech","unit":"1K characters","input":null,"cachedInput":null,"output":null,"price":0.0405,"usdPerMillionChars":40.5,"tier":"growth","condition":"matching-credit promo up to $500 through Dec 31, 2026","inIndex":false,"whyNot":"Growth plan (prepaid from $4,000 a year); the index ranks pay-as-you-go","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Aura-2","modality":"text-to-speech","unit":"1K characters","input":null,"cachedInput":null,"output":null,"price":0.03,"usdPerMillionChars":30,"tier":"pay-as-you-go","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Aura-2","modality":"text-to-speech","unit":"1K characters","input":null,"cachedInput":null,"output":null,"price":0.027,"usdPerMillionChars":27,"tier":"growth","condition":null,"inIndex":false,"whyNot":"Growth plan (prepaid from $4,000 a year); the index ranks pay-as-you-go","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Aura-1","modality":"text-to-speech","unit":"1K characters","input":null,"cachedInput":null,"output":null,"price":0.015,"usdPerMillionChars":15,"tier":"pay-as-you-go","condition":null,"inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Aura-1","modality":"text-to-speech","unit":"1K characters","input":null,"cachedInput":null,"output":null,"price":0.0135,"usdPerMillionChars":13.5,"tier":"growth","condition":null,"inIndex":false,"whyNot":"Growth plan (prepaid from $4,000 a year); the index ranks pay-as-you-go","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Standard","modality":"voice-agent","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.075,"tier":"pay-as-you-go","condition":"calculated based on websocket connection time","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Standard","modality":"voice-agent","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.068,"tier":"growth","condition":"calculated based on websocket connection time","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Standard - BYO TTS","modality":"voice-agent","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.065,"tier":"pay-as-you-go","condition":"bring your own TTS","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Standard - BYO TTS","modality":"voice-agent","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.051,"tier":"growth","condition":"bring your own TTS","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Custom - BYO LLM","modality":"voice-agent","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.065,"tier":"pay-as-you-go","condition":"bring your own LLM; from the page's structured data — the visible table shows only one cell ($0.059/min) for this row","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Custom - BYO LLM","modality":"voice-agent","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.059,"tier":"growth","condition":"bring your own LLM; visible table shows this as the row's only cell, structured data assigns it to Growth","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Custom - BYO LLM + TTS","modality":"voice-agent","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.05,"tier":"pay-as-you-go","condition":"bring your own LLM and TTS","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Custom - BYO LLM + TTS","modality":"voice-agent","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.041,"tier":"growth","condition":"bring your own LLM and TTS","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Advanced","modality":"voice-agent","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.163,"tier":"pay-as-you-go","condition":null,"inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Advanced","modality":"voice-agent","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.146,"tier":"growth","condition":null,"inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Advanced - BYO TTS","modality":"voice-agent","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.122,"tier":"pay-as-you-go","condition":"bring your own TTS","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"deepgram","model":"Advanced - BYO TTS","modality":"voice-agent","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.11,"tier":"growth","condition":"bring your own TTS","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://deepgram.com/pricing"},{"provider":"elevenlabs","model":"v4","modality":"text-to-speech","unit":"1K characters","input":null,"cachedInput":null,"output":null,"price":0.08,"usdPerMillionChars":80,"tier":"pay-as-you-go","condition":"regular price — the only price on the page since the 72%-off promotion ended on 12 Oct (re-read 16 Oct)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"v4 Turbo","modality":"text-to-speech","unit":"1K characters","input":null,"cachedInput":null,"output":null,"price":0.04,"usdPerMillionChars":40,"tier":"pay-as-you-go","condition":"regular price — the only price on the page since the 72%-off promotion ended on 12 Oct (re-read 16 Oct)","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"v3","modality":"text-to-speech","unit":"1K characters","input":null,"cachedInput":null,"output":null,"price":0.08,"usdPerMillionChars":80,"tier":"pay-as-you-go","condition":"same rate printed for every plan; 5,000 character limit","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"v3 Conversational","modality":"text-to-speech","unit":"1K characters","input":null,"cachedInput":null,"output":null,"price":0.04,"usdPerMillionChars":40,"tier":"pay-as-you-go","condition":"same rate printed for every plan","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"v2 Multilingual","modality":"text-to-speech","unit":"1K characters","input":null,"cachedInput":null,"output":null,"price":0.08,"usdPerMillionChars":80,"tier":"pay-as-you-go","condition":"same rate printed for every plan; 10,000 character limit","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"Flash / Turbo","modality":"text-to-speech","unit":"1K characters","input":null,"cachedInput":null,"output":null,"price":0.04,"usdPerMillionChars":40,"tier":"pay-as-you-go","condition":"same rate printed for every plan; 40,000 character limit","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"Scribe v2","modality":"speech-to-text","unit":"hour","input":null,"cachedInput":null,"output":null,"price":0.22,"usdPerAudioHour":0.22,"tier":"pay-as-you-go","condition":"batch; keyterm prompting +$0.050/hr, transcript editing +$0.070/hr","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"Scribe v2 Medical","modality":"speech-to-text","unit":"hour","input":null,"cachedInput":null,"output":null,"price":0.22,"usdPerAudioHour":0.22,"tier":"pay-as-you-go","condition":"clinical audio; HIPAA-eligible","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"Scribe v2 Realtime","modality":"speech-to-text","unit":"hour","input":null,"cachedInput":null,"output":null,"price":0.39,"usdPerAudioHour":0.39,"tier":"pay-as-you-go","condition":"realtime/streaming; keyterm prompting +$0.080/hr, transcript editing +$0.120/hr","inIndex":true,"whyNot":null,"openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"Speech Engine","modality":"voice-agent","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.08,"tier":"pay-as-you-go","condition":"additional minutes beyond plan inclusion","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"Speech Engine","modality":"voice-agent","unit":"minute","input":null,"cachedInput":null,"output":null,"price":0.16,"tier":"pay-as-you-go","condition":"burst pricing","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"Free","modality":"plan","unit":"month","input":null,"cachedInput":null,"output":null,"price":0,"tier":"monthly billing","condition":"10k credits per month","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"Starter","modality":"plan","unit":"month","input":null,"cachedInput":null,"output":null,"price":6,"tier":"monthly billing","condition":"30k credits per month; first month $1 (83% off) until Oct 18; annual equivalent $5/mo","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"Creator","modality":"plan","unit":"month","input":null,"cachedInput":null,"output":null,"price":22,"tier":"monthly billing","condition":"121k credits per month; first month $11 (50% off); annual equivalent $18.33/mo","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"Pro","modality":"plan","unit":"month","input":null,"cachedInput":null,"output":null,"price":99,"tier":"monthly billing","condition":"600k credits per month; annual equivalent $82.50/mo","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"Scale","modality":"plan","unit":"month","input":null,"cachedInput":null,"output":null,"price":299,"tier":"monthly billing","condition":"1.8M credits per month, 3 seats; annual equivalent $249.17/mo","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"Business","modality":"plan","unit":"month","input":null,"cachedInput":null,"output":null,"price":990,"tier":"monthly billing","condition":"6M credits per month, 10 seats; annual equivalent $825/mo","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"},{"provider":"elevenlabs","model":"Enterprise","modality":"plan","unit":"month","input":null,"cachedInput":null,"output":null,"price":null,"tier":"custom","condition":"custom number of credits and seats","inIndex":false,"whyNot":"not ranked in the index (shown on the provider's page)","openModel":null,"readOn":"2026-10-16","sourceUrl":"https://elevenlabs.io/pricing/api"}]}