Novita AI API pricing
50 models · USD per 1M tokens · verified 2026-10-23
Novita AI serves 50 of the models we track, 45 of them open-weights. The cheapest is Llama 3.2 1B Instruct (instruct) at $0.02 input and $0.02 output per million tokens. For 20 of these models, Novita AI is the cheapest tracked host.
// models on Novita AI
| model | lab | in $/1M | out $/1M | ctx | vs best price |
|---|---|---|---|---|---|
| Llama 3.2 1B Instruct (instruct) BEST | Meta | $0.02 | $0.02 | 131K | best |
| Llama-3.1-8B-Instruct BEST | Meta | $0.02 | $0.05 | 16.4K | best |
| DeepSeek OCR 2 BEST | DeepSeek | $0.03 | $0.03 | 8.2K | best |
| AutoGLM Phone 9B Multilingual BEST | Z.AI (Zhipu) | $0.035 | $0.138 | 65.5K | best |
| Gemma 3 12B IT BEST | $0.05 | $0.10 | 131.1K | best | |
| DeepSeek R1 0528 Qwen3 8B BEST | DeepSeek | $0.06 | $0.09 | 128K | best |
| GPT OSS 120B | OpenAI | $0.05 | $0.25 | 131.1K | +42.2% |
| Gemma 3 27B IT | $0.119 | $0.20 | 131.1K | +39.2% | |
| Gemma 4 26B A4B IT | $0.13 | $0.40 | 262.1K | +43.6% | |
| Llama 3.3 70B Turbo | Meta | $0.135 | $0.40 | 131.1K | +29.9% |
| Gemma 4 31B IT BEST | $0.14 | $0.40 | 262.1K | best | |
| Qwen3.8 Flash | Alibaba (Qwen) | $0.15 | $0.47 | 1M | best |
| GLM-5.3-FlashX BEST | Z.AI (Zhipu) | $0.15 | $0.50 | 1M | −59.7% |
| MiniMax-M3.1-Flash BEST | MiniMax | $0.15 | $0.60 | 1M | best |
| Llama 4 Scout 17B | Meta | $0.18 | $0.59 | 327.7K | +88.3% |
| GLM-4.5-Air BEST | Z.AI (Zhipu) | $0.13 | $0.85 | 131.1K | −27.1% |
| Qwen3 VL 30B A3B Instruct | Alibaba (Qwen) | $0.20 | $0.70 | 262.1K | +23.8% |
| Qwen-MT Plus BEST | Alibaba (Qwen) | $0.25 | $0.75 | 16.4K | −89.8% |
| Qwen3 Omni 30B A3B Thinking BEST | Alibaba (Qwen) | $0.25 | $0.97 | 65.5K | best |
| GLM-4.6V BEST | Z.AI (Zhipu) | $0.30 | $0.90 | 128K | best |
| DeepSeek V4.1 Flash | DeepSeek | $0.30 | $1.20 | 1.05M | +75% |
| MiniMax-M3 | MiniMax | $0.30 | $1.20 | 1M | best |
| Qwen3.6 35B-A3B | Alibaba (Qwen) | $0.248 | $1.485 | 262.1K | −34% |
| DeepSeek V4 Flash 0731 | DeepSeek | $0.44 | $1.32 | 1.05M | +633.3% |
| Qwen3.5 35B-A3B | Alibaba (Qwen) | $0.25 | $2.00 | 262.1K | best |
| Qwen3.5 27B BEST | Alibaba (Qwen) | $0.30 | $2.40 | 262.1K | best |
| DeepSeek-V3 | DeepSeek | $0.89 | $0.89 | 163.8K | +92.4% |
| GLM-4.5V BEST | Z.AI (Zhipu) | $0.60 | $1.80 | 64K | best |
| MiniMax M1 80K BEST | MiniMax | $0.55 | $2.20 | 1M | best |
| GLM-4.6 | Z.AI (Zhipu) | $0.55 | $2.20 | 204.8K | −3.7% |
| GLM-4.7 | Z.AI (Zhipu) | $0.60 | $2.20 | 204.8K | best |
| Kimi K2 Instruct BEST | Moonshot AI | $0.57 | $2.30 | 131.1K | best |
| Qwen3.8 27B | Alibaba (Qwen) | $0.42 | $3.00 | 262.1K | +37.4% |
| Kimi K2 Instruct 0905 BEST | Moonshot AI | $0.60 | $2.50 | 262.1K | best |
| Qwen3.5 122B-A10B | Alibaba (Qwen) | $0.40 | $3.20 | 262.1K | best |
| DeepSeek R1 (Turbo) BEST | DeepSeek | $0.70 | $2.50 | 64K | best |
| DeepSeek-R1-0528 | DeepSeek | $0.70 | $2.50 | 163.8K | +26% |
| Qwen3.5 397B-A17B | Alibaba (Qwen) | $0.60 | $3.60 | 262.1K | best |
| Qwen3.6 27B | Alibaba (Qwen) | $0.60 | $3.60 | 262.1K | best |
| Kimi K2.6 | Moonshot AI | $0.80 | $3.40 | 262.1K | −15.3% |
| GLM-5 | Z.AI (Zhipu) | $1.00 | $3.20 | 204.8K | best |
| Kimi K2.7 Code HighSpeed | Moonshot AI | $0.95 | $4.00 | 262.1K | −50% |
| Qwen3.7 Max BEST | Alibaba (Qwen) | $1.25 | $3.75 | 1M | −50% |
| DeepSeek V4 Pro (0813) | DeepSeek | $1.32 | $3.96 | 1.05M | +100% |
| DeepSeek V4 Pro | DeepSeek | $1.60 | $3.20 | 1.05M | +23.1% |
| GLM-5.1 | Z.AI (Zhipu) | $1.38 | $4.40 | 200K | −0.7% |
| GLM-5.2 | Z.AI (Zhipu) | $1.40 | $4.40 | 1M | best |
| GLM-5.3 | Z.AI (Zhipu) | $1.40 | $4.40 | 1M | best |
| Qwen3.8 Max | Alibaba (Qwen) | $2.00 | $6.00 | 1M | best |
| Kimi K3 | Moonshot AI | $3.00 | $15.00 | 1.05M | best |
// how to read this page
Prices are Novita AI's base-tier list prices per million tokens. "vs best price" compares Novita AI's blended price (3 × input + output) / 4 with the lowest price we track for the same model, whether it comes from the lab's own API or another host. Open each model for its full price history and every host that serves it.