AI API price index · open-model host · read 17 Nov 2026
DeepInfra API pricing
98 prices as DeepInfra publishes them — 81 text models, 17 embeddings — read on its own pricing page on 17 Nov 2026. Its current text models cost $0.03 to $14.25 per million output tokens.
Free tier No free tier or free credit is stated on the pricing page: "You have to add a card or pre-pay or you won't be able to use our services."
What to know before you build on DeepInfra
- The page prices 74 text models and 17 embedding models; embeddings run from $0.005 to $0.01 per million tokens.
- Seven models carried a discount on 17 November 2026, up to 51% off (DeepSeek-V4.1-Flash-1017). The index ranks the struck-through list price.
- Priority costs 1.5× the standard price and Flex 0.8×, where a model offers them.
- There is no free tier: "You have to add a card or pre-pay or you won't be able to use our services."
- Dedicated GPUs are billed by the minute: an H100 80GB is $2.90 an hour, a B200 $4.89.
- It resells Anthropic's Claude, Google's Gemini and Alibaba's Qwen Max and Flash, ranked here only at their maker's price. Most cost the same as at the maker; Claude Sonnet 5 is dearer ($3.00 in, $15.00 out against Anthropic's $2.00 and $10.00), and three Qwen models are cheaper (Qwen4-Max is $1.413 and $4.24 against Alibaba's $1.50 and $4.50).
Against the other 31
Across the index, 390 current text models run from $0.03 to $50.00 per million output tokens — 1667×. DeepInfra’s cheapest, Mistral-Nemo-Instruct-2407 at $0.03, has nothing cheaper anywhere in the index; its dearest, Kimi-K3, costs $14.25. A cheaper model is a different model, not the same one for less — compare capability before price.
The same model elsewhere
Open-weight models DeepInfra sells that other hosts price too — the only like-for-like comparison in the index.
- Qwen3.8 27B — Cerebras $0.99 / $1.49 · DeepInfra $0.20 / $2.50 · Alibaba Cloud Model Studio (Qwen) $0.50 / $3.00 · Nebius Token Factory $0.45 / $3.00 · Novita AI $0.42 / $3.00 · Cloudflare Workers AI $0.45 / $3.20 · Groq $0.80 / $4.00 — 2.7× apart
- GLM 5.3 — DeepInfra $0.90 / $4.00 · Cloudflare Workers AI $1.40 / $4.40 · Fireworks AI $1.40 / $4.40 · Mistral AI $1.40 / $4.40 · Nebius Token Factory $1.40 / $4.40 · Novita AI $1.40 / $4.40 · Perplexity $1.40 / $4.40 · Together AI $1.40 / $4.40 · Z.ai $1.40 / $4.40 · SambaNova Cloud $2.80 / $8.80 — 2.2× apart
- DeepSeek V4.1 Flash — DeepInfra $0.20 / $0.60 · Azure AI Foundry Models $0.30 / $1.20 · Fireworks AI $0.30 / $1.20 · Google Vertex AI (Agent Platform) $0.30 / $1.20 · Novita AI $0.30 / $1.20 · Together AI $0.30 / $1.20 — 2.0× apart
- DeepSeek V4.1 Flash 1017 — DeepInfra $0.20 / $0.60 · Cloudflare Workers AI $0.30 / $1.20 · DeepSeek $0.30 / $1.20 · Nebius Token Factory $0.30 / $1.20 · Novita AI $0.30 / $1.20 — 2.0× apart
- GLM 5.2 — DeepInfra $0.75 / $2.40 · Cloudflare Workers AI $1.40 / $4.40 · Google Vertex AI (Agent Platform) $1.40 / $4.40 · Nebius Token Factory $1.40 / $4.40 · Novita AI $1.40 / $4.40 · Together AI $1.40 / $4.40 · Z.ai $1.40 / $4.40 — 1.8× apart
- DeepSeek V4 Pro 0813 — DeepInfra $1.30 / $2.60 · Cloudflare Workers AI $1.32 / $3.96 · DeepSeek $1.32 / $3.96 · Nebius Token Factory $1.32 / $3.96 · Novita AI $1.32 / $3.96 · Perplexity $1.32 / $3.96 · Together AI $1.32 / $3.96 — 1.5× apart
- DeepSeek V4 Pro — DeepInfra $1.30 / $2.60 · Novita AI $1.60 / $3.20 · Azure AI Foundry Models $1.74 / $3.48 — 1.3× apart
- Kimi K3 — DeepInfra $2.85 / $14.25 · Amazon Bedrock $3.00 / $15.00 · Fireworks AI $3.00 / $15.00 · Moonshot AI (Kimi) $3.00 / $15.00 · Nebius Token Factory $3.00 / $15.00 · Novita AI $3.00 / $15.00 · Perplexity $3.00 / $15.00 · Together AI $3.00 / $15.00 — 1.1× apart
- GLM 5.3 Flash — Cloudflare Workers AI $0.15 / $0.50 · DeepInfra $0.15 / $0.50 · Fireworks AI $0.15 / $0.50 · Nebius Token Factory $0.15 / $0.50 · Novita AI $0.15 / $0.50 · Perplexity $0.15 / $0.50 · Together AI $0.15 / $0.50 · Z.ai $0.15 / $0.50 — the same everywhere
- Kimi K3.1 Pro — DeepInfra $2.00 / $10.00 · Moonshot AI (Kimi) $2.00 / $10.00 · Nebius Token Factory $2.00 / $10.00 · Novita AI $2.00 / $10.00 — the same everywhere
Input / output per 1M tokens, standard tier.
The same model at its maker
DeepInfra resells models other companies make. Here is each one beside its maker's own price, both at the standard global rate and the standard prompt length.
| Model | DeepInfra | At its maker | Difference |
|---|---|---|---|
| Qwen4-Max | $1.413 / $4.24 | $1.50 / $4.50 Alibaba Cloud Model Studio (Qwen) | Cheaper here |
| Qwen3.8-Flash | $0.113 / $0.382 | $0.15 / $0.47 Alibaba Cloud Model Studio (Qwen) | Cheaper here |
| Qwen3.8-Max | $1.65 / $4.951 | $2.00 / $6.00 Alibaba Cloud Model Studio (Qwen) | Cheaper here |
| Qwen3.7-Max | $2.50 / $7.50 | $2.50 / $7.50 Alibaba Cloud Model Studio (Qwen) | The same price |
| gemini-3.7-flash | $0.75 / $3.75 | — | Not in the index at its maker |
| gemini-3.5-flash | $1.50 / $9.00 | — | Not in the index at its maker |
| gemini-3.1-flash-lite | $0.25 / $1.50 | $0.25 / $1.50 Google Gemini | The same price |
| gemini-3.1-pro | $2.00 / $12.00 | — | Not in the index at its maker |
| gemini-2.5-pro | $1.25 / $10.00 | — | Not in the index at its maker |
| gemini-2.5-flash | $0.30 / $2.50 | — | Not in the index at its maker |
| claude-sonnet-5-5 | $2.00 / $10.00 | $2.00 / $10.00 Anthropic | The same price |
| claude-opus-5-5 | $4.00 / $20.00 | $4.00 / $20.00 Anthropic | The same price |
| claude-opus-5 | $5.00 / $25.00 | $5.00 / $25.00 Anthropic | The same price |
| claude-fable-5 | $10.00 / $50.00 | $10.00 / $50.00 Anthropic | The same price |
| claude-sonnet-5 | $3.00 / $15.00 | $2.00 / $10.00 Anthropic | Dearer here |
| claude-haiku-4-5 | $1.00 / $5.00 | $1.00 / $5.00 Anthropic | The same price |
| claude-sonnet-4-6 | $3.00 / $15.00 | $3.00 / $15.00 Anthropic | The same price |
| claude-opus-4-7 | $5.00 / $25.00 | $5.00 / $25.00 Anthropic | The same price |
| claude-opus-4-8 | $5.00 / $25.00 | $5.00 / $25.00 Anthropic | The same price |
Input / output per 1M tokens (embeddings: input only). 10 of 19 cost the same here as at their maker. The index ranks each of these models once, at its maker’s price.
Text models
| Model | Input | Cached input | Output | Note |
|---|---|---|---|---|
| DeepSeek-V4.1-Flash-1017 | $0.20 | $0.006 | $0.60 | regular price (struck through on the page beside a 51% discount); context 1024k |
| DeepSeek-V4.1-Flash-1017 | $0.098 | $0.0029 | $0.294 | promotional: 51% off as shown on the page; context 1024k · Not ranked: promotional price; the index ranks the regular price. |
| DeepSeek-V4.1-Flash | $0.20 | $0.006 | $0.60 | regular price (struck through on the page beside a 30% discount); context 1024k |
| DeepSeek-V4.1-Flash | $0.14 | $0.0042 | $0.42 | promotional: 30% off as shown on the page; context 1024k · Not ranked: promotional price; the index ranks the regular price. |
| DeepSeek-V4-Pro-0813 | $1.30 | $0.10 | $2.60 | context 1024k |
| DeepSeek-V4-Flash-0731 | $0.06 | $0.015 | $0.18 | context 1024k |
| DeepSeek-V4-Pro | $1.30 | $0.10 | $2.60 | context 1024k |
| DeepSeek-V4-Flash | $0.09 | $0.018 | $0.18 | context 1024k |
| DeepSeek-V4-Flash-Vision-Exp | $0.44 | $0.014 | $1.32 | regular price (struck through on the page beside a 51% discount); context 1024k |
| DeepSeek-V4-Flash-Vision-Exp | $0.2156 | $0.0069 | $0.6468 | promotional: 51% off as shown on the page; context 1024k · Not ranked: promotional price; the index ranks the regular price. |
| DeepSeek-V3.2 | $0.26 | $0.13 | $0.38 | context 160k |
| DeepSeek-V3.1 | $0.25 | $0.13 | $0.95 | context 160k |
| DeepSeek-V3 | $0.32 | — | $0.89 | context 160k |
| DeepSeek-R1-0528 | $0.50 | $0.35 | $2.15 | context 160k |
| Kimi-K3.1-Pro | $2.00 | $0.20 | $10.00 | regular price (struck through on the page beside a 5% discount); context 1024k |
| Kimi-K3.1-Pro | $1.90 | $0.19 | $9.50 | promotional: 5% off as shown on the page; context 1024k · Not ranked: promotional price; the index ranks the regular price. |
| Kimi-K3 | $2.85 | $0.285 | $14.25 | context 1024k |
| Kimi-K2.6 | $0.75 | $0.15 | $3.50 | context 256k |
| GLM-5.3 | $0.90 | $0.20 | $4.00 | regular price (struck through on the page beside a 38% discount); context 1024k |
| GLM-5.3 | $0.5625 | $0.125 | $2.50 | promotional: 38% off as shown on the page; context 1024k · Not ranked: promotional price; the index ranks the regular price. |
| GLM-5.3-Flash | $0.15 | $0.03 | $0.50 | context 1024k |
| GLM-5.2 | $0.75 | $0.14 | $2.40 | regular price (struck through on the page beside a 25% discount); context 1024k |
| GLM-5.2 | $0.5625 | $0.105 | $1.80 | promotional: 25% off as shown on the page; context 1024k · Not ranked: promotional price; the index ranks the regular price. |
| GLM-4.7 | $0.40 | $0.08 | $1.75 | context 198k |
| GLM-4.6 | $0.50 | $0.10 | $2.00 | context 198k |
| Qwen4-Max | $1.413 | $0.071 | $4.24 | context 976k · Not ranked: the same model Alibaba sells; ranked once, at Alibaba's own price. |
| Qwen3.8-Flash | $0.113 | $0.0141 | $0.382 | context 976k · Not ranked: the same model Alibaba sells; ranked once, at Alibaba's own price. |
| Qwen3.8-27B | $0.20 | $0.05 | $2.50 | regular price (struck through on the page beside a 25% discount); context 256k |
| Qwen3.8-27B | $0.15 | $0.0375 | $1.875 | promotional: 25% off as shown on the page; context 256k · Not ranked: promotional price; the index ranks the regular price. |
| Qwen3.6-27B | $0.32 | — | $3.20 | context 256k |
| Qwen3.6-35B-A3B | $0.10 | $0.10 | $0.95 | context 256k |
| Qwen3.5-397B-A17B | $0.45 | $0.22 | $3.00 | context 256k |
| Qwen3.5-35B-A3B | $0.14 | $0.05 | $1.00 | context 256k |
| Qwen3.5-27B | $0.26 | — | $2.60 | context 256k |
| Qwen3.5-9B | $0.10 | — | $0.15 | context 256k |
| Qwen3.8-Max | $1.65 | $0.206 | $4.951 | context 250k · Not ranked: the same model Alibaba sells; ranked once, at Alibaba's own price. |
| Qwen3.7-Max | $2.50 | $0.50 | $7.50 | context 250k · Not ranked: the same model Alibaba sells; ranked once, at Alibaba's own price. |
| Qwen3-VL-30B-A3B-Instruct | $0.15 | — | $0.60 | context 256k |
| Qwen3-VL-235B-A22B-Instruct | $0.20 | $0.11 | $0.88 | context 256k |
| Qwen3-Next-80B-A3B-Instruct | $0.09 | — | $1.10 | context 256k |
| Qwen3-Coder-480B-A35B-Instruct-Turbo | $0.30 | $0.10 | $1.00 | context 256k |
| Qwen3-235B-A22B-Instruct-2507 | $0.09 | — | $0.55 | context 256k |
| Qwen3-32B | $0.08 | — | $0.28 | context 40k |
| Qwen3-30B-A3B | $0.12 | — | $0.50 | context 40k |
| Qwen3-14B | $0.12 | — | $0.24 | context 40k |
| Qwen2.5-72B-Instruct | $0.36 | — | $0.40 | context 32k |
| Llama-4-Scout-17B-16E | $0.10 | — | $0.30 | context 320k |
| Llama-Guard-4-12B | $0.18 | — | $0.18 | context 160k · Not ranked: a safety classifier, not a general model. |
| Llama-3.3-70B-Instruct-Turbo | $0.10 | — | $0.32 | context 128k |
| Meta-Llama-3.1-8B-Instruct-Turbo | $0.02 | — | $0.04 | context 128k |
| gemini-3.7-flash | $0.75 | — | $3.75 | context 976k · Not ranked: Google's own model, resold here; the index ranks a maker's model only at its maker's own price. |
| gemini-3.5-flash | $1.50 | — | $9.00 | context 976k · Not ranked: Google's own model, resold here; the index ranks a maker's model only at its maker's own price. |
| gemini-3.1-flash-lite | $0.25 | — | $1.50 | context 976k · Not ranked: the same model Google sells; ranked once, at Google's own price. |
| gemini-3.1-pro | $2.00 | — | $12.00 | context 976k · Not ranked: Google's own model, resold here; the index ranks a maker's model only at its maker's own price. |
| gemini-2.5-pro | $1.25 | — | $10.00 | context 976k · Not ranked: Google's own model, resold here; the index ranks a maker's model only at its maker's own price. |
| gemini-2.5-flash | $0.30 | — | $2.50 | context 976k · Not ranked: Google's own model, resold here; the index ranks a maker's model only at its maker's own price. |
| gemma-4-31B-it-Ultra | $0.27 | — | $0.76 | context 128k |
| gemma-4-31B-it-turbo | $0.09 | $0.05 | $0.34 | context 256k |
| gemma-4-31B-it | $0.20 | — | $0.40 | context 256k |
| gemma-4-26B-A4B-it | $0.07 | — | $0.34 | context 256k |
| gemma-3-27b-it | $0.08 | — | $0.16 | context 128k |
| gemma-3-12b-it | $0.05 | — | $0.15 | context 128k |
| gemma-3-4b-it | $0.05 | — | $0.10 | context 128k |
| NVIDIA-Nemotron-3.5-Lightning | $0.06 | $0.03 | $0.16 | context 256k |
| NVIDIA-Nemotron-3.5-Super-VL | $0.15 | $0.02 | $0.50 | context 256k |
| Nemotron-Content-Safety-3.5 | $0.20 | — | $0.20 | context 128k |
| NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.50 | $0.10 | $2.20 | context 256k |
| NVIDIA-Nemotron-3-Super-120B-A12B | $0.075 | — | $0.40 | context 256k |
| claude-sonnet-5-5 | $2.00 | — | $10.00 | context 976k · Not ranked: the same model Anthropic sells; ranked once, at Anthropic's own price. |
| claude-opus-5-5 | $4.00 | $0.20 | $20.00 | context 976k · Not ranked: the same model Anthropic sells; ranked once, at Anthropic's own price. |
| claude-opus-5 | $5.00 | — | $25.00 | context 976k · Not ranked: the same model Anthropic sells; ranked once, at Anthropic's own price. |
| claude-fable-5 | $10.00 | — | $50.00 | context 976k · Not ranked: the same model Anthropic sells; ranked once, at Anthropic's own price. |
| claude-sonnet-5 | $3.00 | — | $15.00 | context 976k · Not ranked: the same model Anthropic sells; ranked once, at Anthropic's own price. |
| claude-haiku-4-5 | $1.00 | — | $5.00 | context 195k · Not ranked: the same model Anthropic sells; ranked once, at Anthropic's own price. |
| claude-sonnet-4-6 | $3.00 | — | $15.00 | context 976k · Not ranked: the same model Anthropic sells; ranked once, at Anthropic's own price. |
| claude-opus-4-7 | $5.00 | — | $25.00 | context 976k · Not ranked: the same model Anthropic sells; ranked once, at Anthropic's own price. |
| claude-opus-4-8 | $5.00 | — | $25.00 | context 976k · Not ranked: the same model Anthropic sells; ranked once, at Anthropic's own price. |
| phi-4 | $0.07 | — | $0.14 | context 16k |
| Mistral-Small-3.2-24B-Instruct-2506 | $0.075 | — | $0.20 | context 125k |
| Mistral-Small-24B-Instruct-2501 | $0.05 | — | $0.08 | context 32k |
| Mistral-Nemo-Instruct-2407 | $0.029 | — | $0.03 | context 128k |
Embeddings
| Model | Input | Cached input | Note |
|---|---|---|---|
| bge-base-en-v1.5 | $0.005 | — | context 512 |
| bge-en-icl | $0.01 | — | context 8k |
| bge-large-en-v1.5 | $0.01 | — | context 512 |
| bge-m3 | $0.01 | — | context 8k |
| bge-m3-multi | $0.01 | — | context 512 |
| gte-base | $0.005 | — | context 512 |
| gte-large | $0.01 | — | context 512 |
| e5-base-v2 | $0.005 | — | context 512 |
| e5-large-v2 | $0.01 | — | context 512 |
| multilingual-e5-large | $0.01 | — | context 512 |
| multilingual-e5-large-instruct | $0.01 | — | context 512 |
| all-MiniLM-L12-v2 | $0.005 | — | context 512 |
| all-MiniLM-L6-v2 | $0.005 | — | context 512 |
| all-mpnet-base-v2 | $0.005 | — | context 512 |
| multi-qa-mpnet-base-dot-v1 | $0.005 | — | context 512 |
| paraphrase-MiniLM-L6-v2 | $0.005 | — | context 512 |
| text2vec-base-chinese | $0.005 | — | context 512 |
71 of these 98 prices are ranked in the index; the rest say why in their note. Text and embeddings per 1M tokens unless the row says otherwise.
Discounts and surcharges, as published
- Service tiers: Standard is 1x the base price, Priority 1.5x ("scheduled ahead of standard traffic"), Flex 0.8x ("lower cost for non-production and asynchronous work, in exchange for slower responses and occasional unavailability"). Availability varies by model.
- Seven models carried a percentage discount on 17 November 2026, shown beside the struck-through list price: DeepSeek-V4.1-Flash-1017 and DeepSeek-V4-Flash-Vision-Exp 51% off, DeepSeek-V4.1-Flash 30%, GLM-5.3 38%, GLM-5.2 25%, Qwen3.8-27B 25%, Kimi-K3.1-Pro 5%. The index ranks the list price.
- Cached input is billed at the cached price the table prints beside the input price, where one is printed.
Where these numbers come from
Read on deepinfra.com/pricing on 17 Nov 2026. Macrostack measures nothing and is paid by no provider on this index. Prices change; the date is the claim.
The other providers in the index
- The AI API price index — every provider, cheapest first, and the download
- Free LLM APIs — which providers let you use a model free, and the catch with each
- OpenAI API pricing — model maker
- Anthropic API pricing — model maker
- Google Gemini API pricing — model maker
- Mistral AI API pricing — model maker
- Cohere API pricing — model maker
- Groq API pricing — open-model host
- Together AI API pricing — open-model host
- Fireworks AI API pricing — open-model host
- Replicate API pricing — open-model host
- Deepgram API pricing — voice
- ElevenLabs API pricing — voice
- DeepSeek API pricing — model maker
- xAI API pricing — model maker
- Azure OpenAI API pricing — cloud platform
- Amazon Bedrock API pricing — cloud platform
- Voyage AI API pricing — model maker
- AssemblyAI API pricing — voice
- Speechmatics API pricing — voice
- Cartesia API pricing — voice
- MiniMax API pricing — model maker
- Z.ai API pricing — model maker
- Cerebras API pricing — open-model host
- Novita AI API pricing — open-model host
- Moonshot AI (Kimi) API pricing — model maker
- Alibaba Cloud Model Studio (Qwen) API pricing — model maker
- Perplexity API pricing — model maker
- Cloudflare Workers AI API pricing — open-model host
- Nebius Token Factory API pricing — open-model host
- SambaNova Cloud API pricing — open-model host
- Google Vertex AI (Agent Platform) API pricing — cloud platform
- Azure AI Foundry Models API pricing — cloud platform
Questions
- How much does the DeepInfra API cost?
- On 17 Nov 2026, DeepInfra's current text models cost $0.03 to $14.25 per million output tokens at the standard tier (Mistral-Nemo-Instruct-2407 to Kimi-K3). The full list, with input and cached-input prices, is on this page.
- Is DeepInfra cheaper than buying from the model maker directly?
- For 10 of 19 models the price is the same: on 17 Nov 2026 Qwen4-Max cost $1.413 in and $4.24 out per million tokens on DeepInfra, against $1.50 and $4.50 at Alibaba Cloud Model Studio (Qwen); Qwen3.8-Flash cost $0.113 in and $0.382 out per million tokens on DeepInfra, against $0.15 and $0.47 at Alibaba Cloud Model Studio (Qwen); Qwen3.8-Max cost $1.65 in and $4.951 out per million tokens on DeepInfra, against $2.00 and $6.00 at Alibaba Cloud Model Studio (Qwen). The reasons to choose one over the other are billing, data residency, compliance and the rest of the cloud you already use, not the token price.
- Does DeepInfra have a free tier?
- What DeepInfra's own pages say: No free tier or free credit is stated on the pricing page: "You have to add a card or pre-pay or you won't be able to use our services."
- Does DeepInfra offer discounts?
- Service tiers: Standard is 1x the base price, Priority 1.5x ("scheduled ahead of standard traffic"), Flex 0.8x ("lower cost for non-production and asynchronous work, in exchange for slower responses and occasional unavailability"). Availability varies by model. Seven models carried a percentage discount on 17 November 2026, shown beside the struck-through list price: DeepSeek-V4.1-Flash-1017 and DeepSeek-V4-Flash-Vision-Exp 51% off, DeepSeek-V4.1-Flash 30%, GLM-5.3 38%, GLM-5.2 25%, Qwen3.8-27B 25%, Kimi-K3.1-Pro 5%. The index ranks the list price. Cached input is billed at the cached price the table prints beside the input price, where one is printed.