Novita AI
Inference
Models
130
Frontier
0
Cheaper here
9
than the headline price
Dearer here
38
than the headline price
Cheapest listing per model, USD per million tokens.
| Model | Here, input / output | Released |
|---|---|---|
| Qwen3.8 Max Alibaba Qwenqwen3.8-max | $2.00 / $6.00 | Sep 2026 |
| DeepSeek V4 Flash Vision Exp | $0.44 / $1.32 +26% vs DeepSeek | Aug 2026 |
| GLM 5.3 Zhipu AIglm-5.3 | $1.40 / $4.40 | Aug 2026 |
| Ling 3.0 Flash Independentling-3.0-flash | $0.06 / $0.18 | Jul 2026 |
| Kimi K3 | $3.00 / $15.00 | Jul 2026 |
| Hy3 | $0.14 / $0.58 | Jul 2026 |
| GLM 5.2 Zhipu AIglm-5.2 | $1.40 / $4.40 | Jun 2026 |
| Kimi K2.7 Code Moonshot AIkimi-k2.7-code | $0.95 / $4.00 | Jun 2026 |
| MiniMax M3 | $0.30 / $1.20 | May 2026 |
| Step 3.7 Flash Independentstep-3.7-flash | $0.20 / $1.15 | May 2026 |
| Qwen3.7 Max Alibaba Qwenqwen3.7-max | $1.25 / $3.75 −50% vs Alibaba DashScope | May 2026 |
| Qwen3.6 35B A3B Alibaba Qwenqwen3.6-35b-a3b | $0.248 / $1.49 +87% vs W&B Inference | Apr 2026 |
| Qwen3.6 27B Alibaba Qwenqwen3.6-27b | $0.60 / $3.60 +42% vs AIHubMix | Apr 2026 |
| DeepSeek V4 Flash | $0.14 / $0.28 −67% vs DeepSeek | Apr 2026 |
| DeepSeek V4 Pro DeepSeekdeepseek-v4-pro-0813 | $1.32 / $3.96 | Apr 2026 |
| MiMo V2.5 Xiaomimimo-v2.5 | $0.168 / $0.336 +41% vs GMI Cloud | Apr 2026 |
| MiMo V2.5 Pro Xiaomimimo-v2.5-pro | $0.522 / $1.04 +71% vs GMI Cloud | Apr 2026 |
| Kimi K2.6 Moonshot AIkimi-k2.6 | $0.80 / $3.40 −15% vs Moonshot AI | Apr 2026 |
| GLM 5.1 Zhipu AIglm-5.1 | $1.38 / $4.40 −1% vs Z.ai | Apr 2026 |
| Gemma 4 26B A4B IT | $0.13 / $0.40 −25% vs Vertex AI | Apr 2026 |
| Gemma 4 31B IT | $0.14 / $0.40 | Apr 2026 |
| MiniMax M2.7 MiniMaxminimax-m2.7 | $0.30 / $1.20 +43% vs GMI Cloud | Mar 2026 |
| Qwen3.5 122B A10B Alibaba Qwenqwen3.5-122b-a10b | $0.40 / $3.20 +255% vs AIHubMix | Feb 2026 |
| Qwen3.5 27B Alibaba Qwenqwen3.5-27b | $0.30 / $2.40 | Feb 2026 |
| Qwen3.5 35B A3B Alibaba Qwenqwen3.5-35b-a3b | $0.25 / $2.00 +94% vs DeepInfra | Feb 2026 |
| Qwen3.5 397B A17B Alibaba Qwenqwen3.5-397b-a17b | $0.60 / $3.60 +265% vs AIHubMix | Feb 2026 |
| MiniMax M2.5 MiniMaxminimax-m2.5 | $0.30 / $1.20 | Feb 2026 |
| GLM 5 | $1.00 / $3.20 | Feb 2026 |
| Qwen3 Coder Next | $0.20 / $1.50 +119% vs AIHubMix | Feb 2026 |
| Kimi K2.5 Moonshot AIkimi-k2.5 | $0.60 / $3.00 | Jan 2026 |
| Qwen3 Max | $2.11 / $8.45 | Jan 2026 |
| GLM 4.7 Flash Zhipu AIglm-4.7-flash | $0.07 / $0.40 | Jan 2026 |
| GLM 4.7 Zhipu AIglm-4.7 | $0.60 / $2.20 | Dec 2025 |
| Nemotron 3 Nano 30B A3B | $0.05 / $0.20 | Dec 2025 |
| GLM 4 6v Zhipu AIglm-4.6v | $0.30 / $0.90 | Dec 2025 |
| DeepSeek V3.2 DeepSeekdeepseek-v3.2 | $0.269 / $0.40 −3% vs DeepSeek | Dec 2025 |
| Kimi K2 Thinking | $0.60 / $2.50 +19% vs GMI Cloud | Nov 2025 |
| Qwen3 VL 8B Instruct | $0.08 / $0.50 | Oct 2025 |
| Qwen3 VL 30B A3B Instruct | $0.20 / $0.70 +24% vs DeepInfra | Oct 2025 |
| GLM 4.6 Zhipu AIglm-4.6 | $0.55 / $2.20 −4% vs Z.ai | Sep 2025 |
| DeepSeek V3.2 Exp DeepSeekdeepseek-v3.2-exp | $0.27 / $0.41 | Sep 2025 |
| Qwen3 VL 235B A22B Instruct | $0.30 / $1.50 −14% vs Alibaba DashScope | Sep 2025 |
| DeepSeek V3.1 Terminus DeepSeekdeepseek-v3.1-terminus | $0.27 / $1.00 | Sep 2025 |
| Qwen3 Next 80B A3B Instruct | $0.15 / $1.50 +18% vs Alibaba DashScope | Sep 2025 |
| GLM 4 5v Zhipu AIglm-4.5v | $0.60 / $1.80 | Aug 2025 |
| gpt-oss-120b | $0.05 / $0.25 +54% vs W&B Inference | Aug 2025 |
| gpt-oss-20b | $0.04 / $0.15 +23% vs W&B Inference | Aug 2025 |
| Qwen3 Coder 30B A3B Instruct | $0.07 / $0.27 | Jul 2025 |
| GLM 4.5 Air Zhipu AIglm-4.5-air | $0.13 / $0.85 −27% vs Z.ai | Jul 2025 |
| GLM 4.5 Zhipu AIglm-4.5 | $0.60 / $2.20 | Jul 2025 |
| Qwen3 235B A22B Thinking 2507 | $0.30 / $3.00 +153% vs Fireworks AI | Jul 2025 |
| Kimi K2 Moonshot AIkimi-k2-0905 | $0.60 / $2.50 +12% vs Vercel AI Gateway | Jul 2025 |
| DeepSeek R1 DeepSeekdeepseek-r1-0528 | $0.70 / $2.50 +20% vs DeepSeek | May 2025 |
| Qwen3 30B A3B Alibaba Qwenqwen3-30b-a3b-fp8 | $0.09 / $0.45 | Apr 2025 |
| Qwen3 32B Alibaba Qwenqwen3-32b-fp8 | $0.10 / $0.45 +200% vs Lambda AI | Apr 2025 |
| Llama 4 Scout 17B 16e Instruct | $0.18 / $0.59 | Apr 2025 |
| Llama 4 Maverick 17B 128e Instruct Metallama-4-maverick-17b-128e-instruct-fp8 | $0.27 / $0.85 | Apr 2025 |
| Gemma 3 12B IT | $0.05 / $0.10 | Mar 2025 |
| Gemma 3 27B IT | $0.119 / $0.20 | Mar 2025 |
| Qwen2.5 VL 72B Instruct Alibaba Qwenqwen2.5-vl-72b-instruct | $0.80 / $0.80 +113% vs Nebius AI Studio | Feb 2025 |
| Llama 3.3 70B Instruct Metallama-3.3-70b-instruct | $0.135 / $0.40 | Dec 2024 |
| Llama 3.2 3B Instruct Metallama-3.2-3b-instruct | $0.03 / $0.05 +75% vs DeepInfra | Sep 2024 |
| Llama 3.2 1B Instruct Metallama-3.2-1b-instruct | $0.02 / $0.02 | Sep 2024 |
| Qwen 2.5 72B Instruct Alibaba Qwenqwen-2.5-72b-instruct | $0.38 / $0.40 | Sep 2024 |
| Llama 3.1 8B Instruct Metallama-3.1-8b-instruct | $0.02 / $0.05 | Jul 2024 |
| Mistral Nemo | $0.04 / $0.17 | Jul 2024 |
| Mythomax L2 13B | $0.09 / $0.09 | Jul 2023 |
| DeepSeek V3.1 DeepSeekdeepseek-v3.1 | $0.27 / $1.00 +6% vs DeepInfra | - |
| DeepSeek V3 DeepSeekdeepseek-v3-0324 | $0.27 / $1.12 | - |
| Qwen3 Next 80B A3B Thinking | $0.15 / $1.50 +18% vs Alibaba DashScope | - |
| DeepSeek R1 Distill Llama 70B | $0.80 / $0.80 +167% vs DeepInfra | - |
| Qwen3 235B A22B Instruct 2507 | $0.09 / $0.58 +39% vs GMI Cloud | - |
| Kimi K2 Instruct | $0.57 / $2.30 +15% vs DeepInfra | - |
| Qwen3 Coder 480B A35B Instruct | $0.38 / $1.55 +9% vs Vertex AI | - |
| DeepSeek R1 Distill Qwen 32B | $0.30 / $0.30 +100% vs Nscale | - |
| MiniMax M2 | $0.30 / $1.20 | - |
| Qwen3 235B A22B Alibaba Qwenqwen3-235b-a22b-fp8 | $0.20 / $0.80 +30% vs DeepInfra | - |
| MiniMax M2.1 MiniMaxminimax-m2.1 | $0.30 / $1.20 | - |
| Qwen3 Embedding 8B Alibaba Qwen · Embedding | $0.07 / $0.00 +600% vs Nebius AI Studio | - |
| Qwen3 VL 235B A22B Thinking | $0.98 / $3.95 +32% vs Alibaba DashScope | - |
| DeepSeek R1 Distill Qwen 14B | $0.15 / $0.15 +114% vs Nscale | - |
| Llama 3 70B Instruct | $0.51 / $0.74 | - |
| Qwen2.5 7B Instruct Alibaba Qwenqwen2.5-7b-instruct | $0.07 / $0.07 +27% vs DeepInfra | - |
| Qwen3 4B Alibaba Qwenqwen3-4b-fp8 | $0.03 / $0.03 | - |
| Qwen3 8B Alibaba Qwenqwen3-8b-fp8 | $0.035 / $0.138 | - |
| Qwen3 Embedding 0 6B Alibaba Qwen · Embeddingqwen3-embedding-0.6b | $0.07 / $0.00 +250% vs Databricks | - |
| DeepSeek OCR | $0.03 / $0.03 | - |
| DeepSeek Prover V2 671B | $0.70 / $2.50 +25% vs GMI Cloud | - |
| DeepSeek R1 Turbo | $0.70 / $2.50 | - |
| Llama 3 8B Instruct | $0.04 / $0.04 | - |
| MiniMax M1 80K | $0.55 / $2.20 +863% vs Fireworks AI | - |
| MiniMax M2.7 Highspeed MiniMaxminimax-m2.7-highspeed | $0.60 / $2.40 | - |
| Qwen3 Reranker 8B Alibaba Qwen · Rerank | $0.05 / $0.05 | - |
| Qwen3 VL 30B A3B Thinking | $0.20 / $1.00 +52% vs Fireworks AI | - |
| Community | $0.89 / $0.89 | - |
| DeepSeek OCR 2 | $0.03 / $0.03 | - |
| DeepSeek R1 Qwen3 8B DeepSeekdeepseek-r1-0528-qwen3-8b | $0.06 / $0.09 | - |
| DeepSeek V3 Turbo | $0.40 / $1.30 | - |
| Hermes 2 Pro Llama 3 8B | $0.14 / $0.14 | - |
| MiniMax M2.5 Highspeed MiniMaxminimax-m2.5-highspeed | $0.60 / $2.40 | - |
1-100 of 130