Inference provider
Novita AI API pricing: every model, compared
We track 105 Novita AI prices that other providers also sell. Novita AI has the lowest listed price for 35 of them; for the rest, the table shows how much more you pay than at the cheapest provider.
Standard list prices in USD. Last price change Oct 26, 2026. Novita AI's official pricing page. How we rank.
LLMs, most widely offered first
Novita AI LLM prices vs the cheapest provider
| Model | Rank | Cheapest elsewhere | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|---|
| gpt-oss-120b | #3 of 18 | W&B Inference (CoreWeave)you pay 54% more here | $0.05 | $0.25 | 131K |
| GLM-5.2 | #4 of 13 | DeepInfrayou pay 85% more here | $1.40 | $4.40 | 1M |
| Llama-3.3-70B-Instruct | #3 of 13 | Nebius Token Factoryyou pay 2% more here | $0.135 | $0.40 | 12K |
| GLM-5.3 | #4 of 12 | DeepInfrayou pay 28% more here | $1.40 | $4.40 | 1M |
| GLM-5.3-Flash | #1 of 11 | Novita AI is cheapest | $0.15 | $0.50 | 1M |
| DeepSeek V4 Flash 0731 | #7 of 10 | DeepInfrayou pay 529% more here | $0.44 | $1.32 | 1M |
| gpt-oss-20b | #3 of 10 | W&B Inference (CoreWeave)you pay 23% more here | $0.04 | $0.15 | 131K |
| Llama-3.1-8B-Instruct | #1 of 10 | Novita AI is cheapest | $0.02 | $0.05 | 16K |
| Kimi K3 | #3 of 9 | SiliconFlowyou pay 11% more here | $3.00 | $15.00 | 1M |
| DeepSeek V4 Pro 0813 | #3 of 8 | DeepInfrayou pay 22% more here | $1.32 | $3.96 | 1M |
| DeepSeek-R1 | #5 of 8 | SiliconFlowyou pay 335% more here | $4.00 | $4.00 | 64K |
| DeepSeek-V3 | #5 of 8 | SiliconFlowyou pay 103% more here | $0.89 | $0.89 | 64K |
| DeepSeek-V3.2 | #2 of 8 | DeepInfrayou pay 4% more here | $0.269 | $0.40 | 164K |
| DeepSeek-V4.1-Flash | #3 of 8 | DeepInfrayou pay 150% more here | $0.30 | $1.20 | 1M |
| Kimi K2.6 | #4 of 8 | W&B Inference (CoreWeave)you pay 8% more here | $0.80 | $3.40 | 262K |
| Kimi K2.7 Code | #4 of 8 | DeepInfrayou pay 26% more here | $0.95 | $4.00 | 262K |
| DeepSeek-V3.1 | #2 of 7 | DeepInfrayou pay 6% more here | $0.27 | $1.00 | 131K |
| DeepSeek-V4-Flash | #3 of 7 | DeepInfrayou pay 56% more here | $0.14 | $0.28 | 1M |
| Gemma 4 26B A4B IT | #4 of 7 | DeepInfrayou pay 44% more here | $0.13 | $0.40 | 262K |
| GLM-5.1 | #3 of 7 | DeepInfrayou pay 28% more here | $1.38 | $4.40 | 205K |
| Kimi K2.5 | #3 of 7 | DeepInfrayou pay 33% more here | $0.60 | $3.00 | 262K |
| Llama 3.2 3B Instruct | #3 of 7 | Lambdayou pay 100% more here | $0.03 | $0.05 | 33K |
| Llama 4 Scout 17B 16E Instruct | #4 of 7 | Lambdayou pay 352% more here | $0.18 | $0.59 | 131K |
| MiniMax-M3 | #3 of 7 | W&B Inference (CoreWeave)you pay 27% more here | $0.30 | $1.20 | 1M |
| Qwen3.8 27B | #3 of 7 | DeepInfrayou pay 1% more here | $0.42 | $3.00 | 1M |
| DeepSeek V4 Pro | #4 of 6 | DeepInfrayou pay 23% more here | $1.60 | $3.20 | 1M |
| DeepSeek V4.1 Flash 1017 | #2 of 6 | DeepInfrayou pay 150% more here | $0.30 | $1.20 | 1M |
| DeepSeek-R1-0528 | #3 of 6 | Lambdayou pay 283% more here | $0.70 | $2.50 | 164K |
| deepseek-r1-distill-llama-70b | #5 of 6 | DeepInfrayou pay 167% more here | $0.80 | $0.80 | 8K |
| Gemma 4 31B IT | #3 of 6 | W&B Inference (CoreWeave)you pay 28% more here | $0.14 | $0.40 | 262K |
| Llama 4 Maverick 17B 128E Instruct FP8 | #3 of 6 | Lambdayou pay 564% more here | $0.27 | $0.85 | 1M |
| Qwen2.5-72B-Instruct | #3 of 6 | Nebius Token Factoryyou pay 95% more here | $0.38 | $0.40 | 32K |
| Qwen3 235B A22B Instruct 2507 | #2 of 6 | DeepInfrayou pay 4% more here | $0.09 | $0.58 | 131K |
| Qwen3.6 35B-A3B | #3 of 6 | DeepInfrayou pay 78% more here | $0.248 | $1.49 | 262K |
| Deepseek R1 Distill Qwen 32B | #3 of 5 | Nscaleyou pay 100% more here | $0.30 | $0.30 | 64K |
| deepseek-v3-0324 | #3 of 5 | Lambdayou pay 61% more here | $0.27 | $1.12 | 164K |
| Gemma-3-27b-it | #2 of 5 | DeepInfrayou pay 39% more here | $0.119 | $0.20 | 98K |
| GLM-4.6 | #3 of 5 | DeepInfrayou pay 10% more here | $0.55 | $2.20 | 205K |
| GLM-4.7 | #2 of 5 | DeepInfrayou pay 36% more here | $0.60 | $2.20 | 205K |
| GLM-5 | #3 of 5 | DeepInfrayou pay 60% more here | $1.00 | $3.20 | 203K |
| Llama 3.2 1B Instruct | #1 of 5 | Novita AI is cheapest | $0.02 | $0.02 | 131K |
| Qwen3.5 397B-A17B | #2 of 5 | DeepInfrayou pay 24% more here | $0.60 | $3.60 | 262K |
| Qwen3.8 2.4T A95B | #1 of 5 | Novita AI is cheapest | $2.00 | $6.00 | 1M |
| DeepSeek V4 Flash Vision Exp | #2 of 4 | DeepSeekyou pay 26% more here | $0.44 | $1.32 | 1M |
| DeepSeek-V3.1-Terminus | #1 of 4 | Novita AI is cheapest | $0.27 | $1.00 | 131K |
| GLM-4.5 | #3 of 4 | DeepInfrayou pay 43% more here | $0.60 | $2.20 | 131K |
| GLM-4.5-Air | #1 of 4 | Novita AI is cheapest | $0.13 | $0.85 | 131K |
| GLM-4.7-Flash | #3 of 4 | DeepInfrayou pay 5% more here | $0.07 | $0.40 | 200K |
| Kimi K2 Instruct | #2 of 4 | DeepInfrayou pay 15% more here | $0.57 | $2.30 | 131K |
| llama3-70b-instruct | #1 of 4 | Novita AI is cheapest | $0.51 | $0.74 | 8K |
| llama3-8b-instruct | #2 of 4 | DeepInfrayou pay 7% more here | $0.04 | $0.04 | 8K |
| MiniMax-M2.5 | #1 of 4 | Novita AI is cheapest | $0.30 | $1.20 | 205K |
| MiniMax-M2.7 | #2 of 4 | DeepInfrayou pay 20% more here | $0.30 | $1.20 | 205K |
| Qwen2.5-7B-Instruct | #3 of 4 | SiliconFlowyou pay 40% more here | $0.07 | $0.07 | 32K |
| qwen2.5-vl-72b-instruct | #2 of 4 | Nebius Token Factoryyou pay 113% more here | $0.80 | $0.80 | 33K |
| Qwen3 VL 30B A3B Instruct | #3 of 4 | DeepInfrayou pay 24% more here | $0.20 | $0.70 | 131K |
| Qwen3-Coder-480B-A35B-Instruct | #2 of 4 | SiliconFlowyou pay 54% more here | $0.38 | $1.55 | 262K |
| qwen3-next-80b-a3b-thinking | #3 of 4 | Nebius Token Factoryyou pay 18% more here | $0.15 | $1.50 | 131K |
| Qwen3.5 122B-A10B | #3 of 4 | SiliconFlowyou pay 54% more here | $0.40 | $3.20 | 262K |
| Qwen3.5 27B | #2 of 4 | SiliconFlowyou pay 20% more here | $0.30 | $2.40 | 262K |
| Qwen3.5 35B-A3B | #3 of 4 | DeepInfrayou pay 94% more here | $0.25 | $2.00 | 262K |
| Qwen3.6 27B | #3 of 4 | SiliconFlowyou pay 32% more here | $0.60 | $3.60 | 262K |
| Qwen3.7 Max | #1 of 4 | Novita AI is cheapest | $1.25 | $3.75 | 1M |
| Qwen3.8 Flash | #2 of 4 | DeepInfrayou pay 28% more here | $0.15 | $0.47 | 1M |
| Qwen3.8 Max | #2 of 4 | DeepInfrayou pay 21% more here | $2.00 | $6.00 | 1M |
| deepseek-r1-distill-qwen-14b | #2 of 3 | Nscaleyou pay 114% more here | $0.15 | $0.15 | 33K |
| Gemma 3 12B IT | #1 of 3 | Novita AI is cheapest | $0.05 | $0.10 | 131K |
| GLM-4.5V | #1 of 3 | Novita AI is cheapest | $0.60 | $1.80 | 66K |
| GLM-5V-Turbo | #1 of 3 | Novita AI is cheapest | $1.20 | $4.00 | 205K |
| Hy3 | #2 of 3 | SiliconFlowyou pay 8% more here | $0.14 | $0.58 | 262K |
| Kimi K2 Thinking | #1 of 3 | Novita AI is cheapest | $0.60 | $2.50 | 262K |
| minimax-m2 | #1 of 3 | Novita AI is cheapest | $0.30 | $1.20 | 205K |
| minimax-m2.1 | #1 of 3 | Novita AI is cheapest | $0.30 | $1.20 | 205K |
| MiniMax-M3.1-Flash | #1 of 3 | Novita AI is cheapest | $0.15 | $0.60 | 1M |
| MythoMax L2 13B | #1 of 3 | Novita AI is cheapest | $0.09 | $0.09 | 4K |
| Qwen3 VL 235B A22B Instruct | #3 of 3 | DeepInfrayou pay 62% more here | $0.30 | $1.50 | 131K |
| qwen3-235b-a22b-thinking-2507 | #3 of 3 | Fireworks AIyou pay 153% more here | $0.30 | $3.00 | 131K |
| Qwen3-Coder-30B-A3B-Instruct | #1 of 3 | Novita AI is cheapest | $0.07 | $0.27 | 160K |
| Qwen3-Next 80B-A3B Instruct | #2 of 3 | DeepInfrayou pay 42% more here | $0.15 | $1.50 | 131K |
| Qwen3-VL-30B-A3B-Thinking | #2 of 3 | Fireworks AIyou pay 52% more here | $0.20 | $1.00 | 131K |
| Qwen3-VL-8B-Instruct | #1 of 3 | Novita AI is cheapest | $0.08 | $0.50 | 131K |
| DeepSeek R1 (Turbo) | #1 of 2 | Novita AI is cheapest | $0.70 | $2.50 | 64K |
| DeepSeek-V3.2-Exp | #1 of 2 | Novita AI is cheapest | $0.27 | $0.41 | 164K |
| GLM-4.6V | #1 of 2 | Novita AI is cheapest | $0.30 | $0.90 | 131K |
| GLM-5-Turbo | #1 of 2 | Novita AI is cheapest | $1.20 | $4.00 | 203K |
| Hy4 preview | #1 of 2 | Novita AI is cheapest | $0.834 | $2.50 | 1M |
| Kimi K3.1 Pro | #1 of 2 | Novita AI is cheapest | $2.00 | $10.00 | 1M |
| Kimi K3.1 Pro Highspeed | #1 of 2 | Novita AI is cheapest | $4.00 | $20.00 | 1M |
| l3.1-70b-euryale-v2.2 | #2 of 2 | DeepInfrayou pay 74% more here | $1.48 | $1.48 | 8K |
| Ling 3.0 Flash | #1 of 2 | Novita AI is cheapest | $0.06 | $0.18 | 262K |
| MiMo-V2.5 | #1 of 2 | Novita AI is cheapest | $0.168 | $0.336 | 1M |
| MiMo-V2.5-Pro | #1 of 2 | Novita AI is cheapest | $0.522 | $1.04 | 1M |
| MiMo-V2.6-Flash | #1 of 2 | Novita AI is cheapest | $0.14 | $0.28 | 1M |
| MiMo-V2.6-Pro | #2 of 2 | DeepInfrayou pay 1% more here | $0.435 | $0.87 | 1M |
| MiniMax M1 80K | #2 of 2 | Fireworks AIyou pay 863% more here | $0.55 | $2.20 | 1M |
| Nemotron 3 Nano 30B A3B | #1 of 2 | Novita AI is cheapest | $0.05 | $0.20 | 262K |
| Qwen-MT Plus | #1 of 2 | Novita AI is cheapest | $0.25 | $0.75 | 16K |
| Qwen3 30B A3b fp8 | #2 of 2 | Cloudflare Workers AIyou pay 48% more here | $0.09 | $0.45 | 41K |
| Qwen3 Coder Next | #1 of 2 | Novita AI is cheapest | $0.20 | $1.50 | 262K |
| qwen3-32b-fp8 | #2 of 2 | Lambdayou pay 200% more here | $0.10 | $0.45 | 41K |
| qwen3-max | #2 of 2 | DeepInfrayou pay 54% more here | $2.11 | $8.45 | 262K |
| qwen3-vl-235b-a22b-thinking | #2 of 2 | Fireworks AIyou pay 347% more here | $0.98 | $3.95 | 131K |
| Step 3.7 Flash | #1 of 2 | Novita AI is cheapest | $0.20 | $1.15 | 262K |
| Step 5 Preview | #1 of 2 | Novita AI is cheapest | $1.00 | $2.70 | 1M |
| WizardLM 2 8x22B | #2 of 2 | DeepInfrayou pay 29% more here | $0.62 | $0.62 | 66K |
Rank and difference use the blended price (3 input : 1 output tokens). Equal prices share a rank.
Ranked for your volume
gpt-oss-120b monthly cost by provider
Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.
More requirements: caching, context, features, provider
| Provider | Estimated / month | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
1 W&B Inference (CoreWeave)lowest for your volumePricing page | $0.64 | $0.03 | $0.17 | Not listed | 131,000 |
2 DeepInfraPricing page | $0.71 | $0.037 | $0.17 | Not listed | 131,072 |
3 Novita AIPricing page | $1.00 | $0.05 | $0.25 | Not listed | 131,072 |
4 SiliconFlowPricing page | $1.40 | $0.05 | $0.45 | Not listed | 131,000 |
5 OVHcloud AI EndpointsBilled in EUR: €0.08 input, €0.40 output per 1M tokens. USD at the ECB rate of Oct 30, 2026 (1.1172).Pricing page | $1.79 | $0.0894 | $0.4469 | Not listed | 131,000 |
6 BasetenPricing page | $2.00 | $0.10 | $0.50 | $0.10 | 128,072 |
7 Amazon BedrockPricing page | $2.70 | $0.15 | $0.60 | Not listed | 131,072 |
8 Fireworks AIPricing page | $2.70 | $0.15 | $0.60 | $0.015 | 131,072 |
9 Microsoft Azure AI FoundryPricing page | $2.70 | $0.15 | $0.60 | Not listed | 131,072 |
10 Nebius Token FactoryPricing page | $2.70 | $0.15 | $0.60 | Not listed | 131,072 |
Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.
Ranked #1? Show it on your site
Novita AI has the lowest blended list price (3 input : 1 output tokens) for these models. The badge states that basis, updates daily and always shows the current rank, whatever it is; ranking is by price only.
<a href="https://aiselect.online/models/glm-5-3-flash"><img src="https://aiselect.online/badge/glm-5-3-flash/novita.svg" alt="GLM-5.3-Flash API price ranking on AISelect" height="20"></a>
<a href="https://aiselect.online/models/llama-3-1-8b-instruct"><img src="https://aiselect.online/badge/llama-3-1-8b-instruct/novita.svg" alt="Llama-3.1-8B-Instruct API price ranking on AISelect" height="20"></a>
<a href="https://aiselect.online/models/llama-3-2-1b-instruct"><img src="https://aiselect.online/badge/llama-3-2-1b-instruct/novita.svg" alt="Llama 3.2 1B Instruct API price ranking on AISelect" height="20"></a>Compare more
Other providers
Alibaba Cloud Model Studio, Amazon Bedrock, Anthropic, Baseten, Cloudflare Workers AI, Cohere, DeepInfra, DeepSeek, fal, Fireworks AI, FriendliAI, Google Cloud Vertex AI, Google Gemini API, IBM watsonx.ai, Lambda, Microsoft Azure AI Foundry, Mistral AI, Moonshot AI, Nebius Token Factory, Nscale, OpenAI, Oracle Cloud Generative AI, OVHcloud AI Endpoints, Perplexity, Replicate, SambaNova, Scaleway, SiliconFlow, Together AI, W&B Inference (CoreWeave), xAI, Z.ai