AI API price index · open-model host · read 17 Nov 2026
Novita AI API pricing
75 prices as Novita AI publishes them — 72 text models, 2 embeddings, 1 images and documents — read on its own pricing page on 17 Nov 2026. Its current text models cost $0.05 to $20.00 per million output tokens.
Free tier No free credit is stated on the pricing page. Two models are printed as Free for input and output (zai-org/glm-new and Apodex 1.1 Mini), and the footer says "Free to start".
What to know before you build on Novita AI
- Novita's pricing page lists 73 language models priced per token, from DeepSeek, Moonshot (Kimi), Qwen, Z.ai (GLM), Meta (Llama), Google (Gemma), OpenAI (gpt-oss), Tencent, Xiaomi and others.
- Batch inference is 50% off input and output tokens on supported models, at an introductory rate.
- Some models charge for writing the prompt cache: Kimi K3 $3 per 1M tokens for five minutes and $6 for an hour.
- It also resells Exa and Tavily search calls (Exa neural search $0.007 a request, Tavily basic search $0.008). Those are other companies' APIs and are not listed here.
- This page covers the language and embedding models; Novita's image, audio, video and GPU prices sit on other tabs of the same page.
Against the other 31
Across the index, 390 current text models run from $0.03 to $50.00 per million output tokens — 1667×. Novita AI’s cheapest, Llama 3 8B Stheno V3.2 at $0.05, has 2 cheaper text models elsewhere; its dearest, Kimi K3.1 Pro Highspeed, costs $20.00. A cheaper model is a different model, not the same one for less — compare capability before price.
The same model elsewhere
Open-weight models Novita AI sells that other hosts price too — the only like-for-like comparison in the index.
- gpt-oss-120b — Novita AI $0.05 / $0.25 · Google Vertex AI (Agent Platform) $0.09 / $0.36 · SambaNova Cloud $0.22 / $0.59 · Amazon Bedrock $0.15 / $0.60 · Fireworks AI $0.15 / $0.60 · Groq $0.15 / $0.60 · Nebius Token Factory $0.15 / $0.60 · Together AI $0.15 / $0.60 · Cerebras $0.35 / $0.75 · Cloudflare Workers AI $0.35 / $0.75 — 3.0× apart
- Llama 3.3 70B — Novita AI $0.135 / $0.40 · Azure AI Foundry Models $0.71 / $0.71 · Amazon Bedrock $0.72 / $0.72 · Google Vertex AI (Agent Platform) $0.72 / $0.72 · SambaNova Cloud $0.60 / $1.20 — 3.0× apart
- 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
Novita AI 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 | Novita AI | At its maker | Difference |
|---|---|---|---|
| Qwen3.8 Flash | $0.15 / $0.47 | $0.15 / $0.47 Alibaba Cloud Model Studio (Qwen) | The same price |
| Qwen4 Max | $1.413 / $4.24 | $1.50 / $4.50 Alibaba Cloud Model Studio (Qwen) | Cheaper here |
| Qwen3.8 Max | $2.00 / $6.00 | $2.00 / $6.00 Alibaba Cloud Model Studio (Qwen) | The same price |
| Qwen3.7 Max | $1.25 / $3.75 | $2.50 / $7.50 Alibaba Cloud Model Studio (Qwen) | Cheaper here |
Input / output per 1M tokens (embeddings: input only). 2 of 4 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 1017serverless | $0.30 | $0.006 | $1.20 | Context 1M |
| DeepSeek V4.1 Flashserverless | $0.30 | $0.006 | $1.20 | Context 1M |
| DeepSeek V4 Pro 0813serverless | $1.32 | $0.044 | $3.96 | Context 1M |
| DeepSeek V4 Flash 0731serverless | $0.44 | $0.028 | $1.32 | Context 1M |
| DeepSeek V4 Proserverless | $1.60 | $0.135 | $3.20 | Context 1M |
| DeepSeek R1 0528serverless | $0.70 | $0.35 | $2.50 | Context 160K |
| DeepSeek R1 Turboserverless | $0.70 | — | $2.50 | Context 63K |
| zai-org/glm-newserverless | $0.00 | — | $0.00 | Context 193K; printed as Free · Not ranked: printed as free — no per-token price to rank. |
| GLM 5.3 FlashXserverless | $0.37 | $0.075 | $1.25 | Context 1M |
| GLM 5.3 Flashserverless | $0.15 | $0.03 | $0.50 | Context 1M |
| GLM 5.3serverless | $1.40 | $0.26 | $4.40 | Context 1M |
| GLM 5.2serverless | $1.40 | $0.26 | $4.40 | Context 1M |
| GLM 5.1serverless | $1.38 | $0.26 | $4.40 | Context 200K |
| GLM 5serverless | $1.00 | $0.20 | $3.20 | Context 198K |
| GLM 4.7 Flashserverless | $0.07 | $0.01 | $0.40 | Context 195K |
| GLM 4.7serverless | $0.60 | $0.11 | $2.20 | Context 200K |
| AutoGLM Phone 9B Multilingualserverless | $0.035 | — | $0.138 | Context 64K |
| GLM 4.6Vserverless | $0.30 | $0.055 | $0.90 | Context 128K |
| GLM 4.6serverless | $0.55 | $0.11 | $2.20 | Context 200K |
| GLM 4.5Vserverless | $0.60 | $0.11 | $1.80 | Context 64K |
| GLM 4.5 Airserverless | $0.13 | $0.025 | $0.85 | Context 128K |
| Kimi K3.1 Pro Highspeedserverless | $4.00 | $0.20 | $20.00 | Context 1M; cache write (5m) $4, cache write (1h) $8 |
| Kimi K3.1 Proserverless | $2.00 | $0.20 | $10.00 | Context 1M; cache write (5m) $2, cache write (1h) $4 |
| Kimi K3serverless | $3.00 | $0.30 | $15.00 | Context 1M; cache write (5m) $3, cache write (1h) $6 |
| Kimi K2.7 Codeserverless | $0.95 | $0.19 | $4.00 | Context 256K |
| Kimi K2.6serverless | $0.80 | $0.16 | $3.40 | Context 256K |
| Kimi K2.5serverless | $0.60 | $0.10 | $3.00 | Context 256K |
| Kimi K2 Thinkingserverless | $0.60 | $0.15 | $2.50 | Context 256K |
| Kimi K2 Instruct 0905serverless | $0.60 | — | $2.50 | Context 256K |
| Kimi K2 Instructserverless | $0.57 | — | $2.30 | Context 128K |
| Llama 3.1 8B Instructserverless | $0.02 | — | $0.05 | Context 16K |
| Llama 3.3 70B Instructserverless | $0.135 | — | $0.40 | Context 12K |
| Llama 4 Maverick Instructserverless | $0.27 | — | $0.85 | Context 1M |
| Llama 4 Scout Instructserverless | $0.18 | — | $0.59 | Context 128K |
| Qwen3.8 Flashserverless | $0.15 | $0.016 | $0.47 | Context 977K; cache write (5m) $0.2 · Not ranked: the same model Alibaba sells; ranked once, at Alibaba's own price. |
| Qwen4 Maxserverless | $1.413 | $0.071 | $4.24 | Context 977K; cache write (5m) $1.767, cache write (1h) $2.827 · Not ranked: the same model Alibaba sells; ranked once, at Alibaba's own price. |
| Qwen3.8 27Bserverless | $0.42 | $0.085 | $3.00 | Context 977K |
| Qwen3.8 2.4T A95Bserverless | $2.00 | $0.25 | $6.00 | Context 977K |
| Qwen3.8 Maxserverless | $2.00 | $0.25 | $6.00 | Context 977K; cache write (5m) $2.5 · Not ranked: the same model Alibaba sells; ranked once, at Alibaba's own price. |
| Qwen3.7 Maxserverless | $1.25 | $0.25 | $3.75 | Context 977K · Not ranked: the same model Alibaba sells; ranked once, at Alibaba's own price. |
| Qwen3.6 27Bserverless | $0.60 | — | $3.60 | Context 256K |
| Qwen3.5 27Bserverless | $0.30 | — | $2.40 | Context 256K |
| Qwen3.5 122B A10Bserverless | $0.40 | — | $3.20 | Context 256K |
| Qwen3.5 35B A3Bserverless | $0.25 | — | $2.00 | Context 256K |
| Qwen3.5 397B A17Bserverless | $0.60 | — | $3.60 | Context 256K |
| Qwen3.6 35B A3Bserverless | $0.248 | — | $1.485 | Context 256K |
| Qwen3 VL 30B A3B Instructserverless | $0.20 | — | $0.70 | Context 128K |
| Qwen3 Omni 30B A3B Thinkingserverless | — | — | — | Context 64K; input printed as "-" and output as "Omnimodal" — no per-token price · Not ranked: no per-token price. |
| Qwen MT Plusserverless | $0.25 | — | $0.75 | Context 16K |
| Gemma 4 26B A4Bserverless | $0.13 | — | $0.40 | Context 256K |
| Gemma 4 31Bserverless | $0.14 | — | $0.40 | Context 256K |
| Gemma 3 27Bserverless | $0.119 | — | $0.20 | Context 96K |
| WizardLM 2 8x22Bserverless | $0.62 | — | $0.62 | Context 64K |
| Apodex 1.1 Miniserverless | $0.00 | — | $0.00 | Context 256K; printed as Free · Not ranked: printed as free — no per-token price to rank. |
| Ling 3.1 Flash 1019serverless | $0.30 | $0.06 | $0.90 | Context 977K |
| Ling 3.0 Flash Finserverless | $0.075 | $0.015 | $0.22 | Context 256K |
| Ling 3.0 Flashserverless | $0.06 | $0.012 | $0.18 | Context 256K |
| Ling 3.0 Flash VLserverless | $0.075 | $0.015 | $0.22 | Context 256K |
| Ling 3.0 Flash Santeserverless | $0.075 | $0.015 | $0.22 | Context 256K |
| Macaron V1 Ventiserverless | $0.825 | $0.165 | $2.475 | Context 1M |
| Macaron V1 Tallserverless | $0.2475 | $0.044 | $1.43 | Context 256K |
| NVIDIA Nemotron 3 Nano 30B A3Bserverless | $0.05 | — | $0.20 | Context 256K |
| OpenAI GPT OSS 120Bserverless | $0.05 | — | $0.25 | Context 128K |
| Step 5 Previewserverless | $1.00 | $0.10 | $2.70 | Context 977K |
| Step 3.7 Flashserverless | $0.20 | $0.04 | $1.15 | Context 256K |
| Hy4 Flashserverless | $0.07 | $0.003 | $0.281 | Context 977K |
| Hy4serverless | $0.417 | $0.021 | $1.2505 | Context 977K; $0.834 in, $0.042 cached and $2.501 out printed struck through beside it, with no reason or end date |
| Hy4 Previewserverless | $0.834 | $0.042 | $2.501 | Context 977K |
| Hy3serverless | $0.14 | $0.035 | $0.58 | Context 256K |
| MiMo V2.6 Flashserverless | $0.14 | $0.0028 | $0.28 | Context 1M |
| MiMo V2.6 Proserverless | $0.435 | $0.0036 | $0.87 | Context 1M |
| Llama 3 8B Stheno V3.2serverless | $0.05 | — | $0.05 | Context 8K |
Embeddings
| Model | Input | Cached input | Note |
|---|---|---|---|
| Qwen3 Embedding 8Bserverless | $0.07 | — | Context 32K |
| BAAI:BGE-M3serverless | $0.01 | — | Context 8K |
Images and documents
| Model | Price | Note |
|---|---|---|
| DeepSeek OCR 2serverless | $0.03 per 1M tokens | Document OCR; input and output each $0.03 per 1M tokens; context 8K |
67 of these 75 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
- "Batch inference is available at an introductory 50% discount on input and output tokens for supported models."
- Hy4 is $0.417 in, $0.021 cached and $1.2505 out per 1M tokens, with $0.834, $0.042 and $2.501 printed struck through beside it; no reason or end date is printed.
- Some models charge for writing the prompt cache: Kimi K3 $3 per 1M tokens for a 5-minute cache and $6 for an hour; Qwen4 Max $1.767 and $2.827.
Where these numbers come from
Read on novita.ai/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
- Moonshot AI (Kimi) API pricing — model maker
- Alibaba Cloud Model Studio (Qwen) API pricing — model maker
- Perplexity API pricing — model maker
- DeepInfra API pricing — open-model host
- 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 Novita AI API cost?
- On 17 Nov 2026, Novita AI's current text models cost $0.05 to $20.00 per million output tokens at the standard tier (Llama 3 8B Stheno V3.2 to Kimi K3.1 Pro Highspeed). The full list, with input and cached-input prices, is on this page.
- Is Novita AI cheaper than buying from the model maker directly?
- For 2 of 4 models the price is the same: on 17 Nov 2026 Qwen3.8 Flash cost $0.15 in and $0.47 out per million tokens on Novita AI, against $0.15 and $0.47 at Alibaba Cloud Model Studio (Qwen); Qwen4 Max cost $1.413 in and $4.24 out per million tokens on Novita AI, against $1.50 and $4.50 at Alibaba Cloud Model Studio (Qwen); Qwen3.8 Max cost $2.00 in and $6.00 out per million tokens on Novita AI, 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 Novita AI have a free tier?
- What Novita AI's own pages say: No free credit is stated on the pricing page. Two models are printed as Free for input and output (zai-org/glm-new and Apodex 1.1 Mini), and the footer says "Free to start".
- Does Novita AI offer discounts?
- "Batch inference is available at an introductory 50% discount on input and output tokens for supported models." Hy4 is $0.417 in, $0.021 cached and $1.2505 out per 1M tokens, with $0.834, $0.042 and $2.501 printed struck through beside it; no reason or end date is printed. Some models charge for writing the prompt cache: Kimi K3 $3 per 1M tokens for a 5-minute cache and $6 for an hour; Qwen4 Max $1.767 and $2.827.