Provider
Deep Infra
Provider summary is pending review.
Visible model offerings
| Model | Provider ID | Input price | Output price | Context | Output |
|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | deepseek-ai/DeepSeek-V4-Flash | $0.09 / 1M tokens | $0.18 / 1M tokens | 1,048,576 | 16,384 |
| DeepSeek V4 Pro DeepSeek | deepseek-ai/DeepSeek-V4-Pro | $1.3 / 1M tokens | $2.6 / 1M tokens | 1,048,576 | 16,384 |
| Gemma 4 26B A4B IT Google | google/gemma-4-26B-A4B-it | $0.07 / 1M tokens | $0.34 / 1M tokens | 262,144 | 32,768 |
| Gemma 4 31B IT Google | google/gemma-4-31B-it | $0.13 / 1M tokens | $0.38 / 1M tokens | 262,144 | 32,768 |
| MiniMax-M2.5 MiniMax | MiniMaxAI/MiniMax-M2.5 | $0.15 / 1M tokens | $1.15 / 1M tokens | 196,608 | 131,072 |
| MiniMax-M2.7 MiniMax | MiniMaxAI/MiniMax-M2.7 | $0.25 / 1M tokens | $1 / 1M tokens | 196,608 | 131,072 |
| MiniMax-M3 MiniMax | MiniMaxAI/MiniMax-M3 | $0.3 / 1M tokens | $1.2 / 1M tokens | 524,288 | 128,000 |
| Kimi K2.5 Moonshot AI | moonshotai/Kimi-K2.5 | $0.45 / 1M tokens | $2.25 / 1M tokens | 262,144 | 32,768 |
| Kimi K2.6 Moonshot AI | moonshotai/Kimi-K2.6 | $0.75 / 1M tokens | $3.5 / 1M tokens | 262,144 | 16,384 |
| Kimi K2.7 Code Moonshot AI | moonshotai/Kimi-K2.7-Code | $0.74 / 1M tokens | $3.5 / 1M tokens | 262,144 | 262,144 |
| Llama 3.3 Nemotron Super 49B v1.5 NVIDIA | nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 | $0.4 / 1M tokens | $0.4 / 1M tokens | 131,072 | 131,072 |
| Nemotron 3 Nano 30B A3B NVIDIA | nvidia/Nemotron-3-Nano-30B-A3B | $0.05 / 1M tokens | $0.2 / 1M tokens | 262,144 | 262,144 |
| Nemotron 3 Nano Omni 30B A3B Reasoning NVIDIA | nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning | $0.2 / 1M tokens | $0.8 / 1M tokens | 262,144 | 65,536 |
| GPT OSS 120B OpenAI | openai/gpt-oss-120b | $0.037 / 1M tokens | $0.17 / 1M tokens | 131,072 | 16,384 |
| GPT OSS 20B OpenAI | openai/gpt-oss-20b | $0.03 / 1M tokens | $0.14 / 1M tokens | 131,072 | 16,384 |
| Qwen3 32B Alibaba | Qwen/Qwen3-32B | $0.08 / 1M tokens | $0.28 / 1M tokens | 40,960 | 16,384 |
| Qwen3.5 122B-A10B Alibaba | Qwen/Qwen3.5-122B-A10B | $0.29 / 1M tokens | $2.4 / 1M tokens | 262,144 | 65,536 |
| Qwen3.5 27B Alibaba | Qwen/Qwen3.5-27B | $0.26 / 1M tokens | $2.6 / 1M tokens | 262,144 | 65,536 |
| Qwen3.5 35B-A3B Alibaba | Qwen/Qwen3.5-35B-A3B | $0.14 / 1M tokens | $1 / 1M tokens | 262,144 | 81,920 |
| Qwen3.5 397B-A17B Alibaba | Qwen/Qwen3.5-397B-A17B | $0.45 / 1M tokens | $3 / 1M tokens | 262,144 | 81,920 |
| Qwen3.5 9B Alibaba | Qwen/Qwen3.5-9B | $0.1 / 1M tokens | $0.15 / 1M tokens | 262,144 | 65,536 |
| Qwen3.6 27B Alibaba | Qwen/Qwen3.6-27B | $0.32 / 1M tokens | $3.2 / 1M tokens | 262,144 | 65,536 |
| Qwen3.6 35B-A3B Alibaba | Qwen/Qwen3.6-35B-A3B | $0.15 / 1M tokens | $0.95 / 1M tokens | 262,144 | 81,920 |
| Qwen3.7 Max Alibaba | Qwen/Qwen3.7-Max | $2.5 / 1M tokens | $7.5 / 1M tokens | 256,000 | 65,536 |
| Qwen3 Max Alibaba | Qwen/Qwen3-Max | $1.2 / 1M tokens | $6 / 1M tokens | 256,000 | 65,536 |
| Qwen3-Next 80B-A3B Instruct Alibaba | Qwen/Qwen3-Next-80B-A3B-Instruct | $0.09 / 1M tokens | $1.1 / 1M tokens | 262,144 | 32,768 |
| MiMo-V2.5 Xiaomi | XiaomiMiMo/MiMo-V2.5 | $0.4 / 1M tokens | $2 / 1M tokens | 262,144 | 16,384 |
| MiMo-V2.5-Pro Xiaomi | XiaomiMiMo/MiMo-V2.5-Pro | $1 / 1M tokens | $3 / 1M tokens | 1,048,576 | 16,384 |
| GLM-4.6 Zhipu AI | zai-org/GLM-4.6 | $0.5 / 1M tokens | $2 / 1M tokens | 202,752 | 131,072 |
| GLM-4.7 Zhipu AI | zai-org/GLM-4.7 | $0.4 / 1M tokens | $1.75 / 1M tokens | 202,752 | 16,384 |
| GLM-4.7-Flash Zhipu AI | zai-org/GLM-4.7-Flash | $0.06 / 1M tokens | $0.4 / 1M tokens | 202,752 | 16,384 |
| GLM-5 Zhipu AI | zai-org/GLM-5 | $0.6 / 1M tokens | $2.08 / 1M tokens | 202,752 | 16,384 |
| GLM-5.1 Zhipu AI | zai-org/GLM-5.1 | $1.05 / 1M tokens | $3.5 / 1M tokens | 202,752 | 16,384 |
| GLM-5.2 Zhipu AI | zai-org/GLM-5.2 | $0.93 / 1M tokens | $3 / 1M tokens | 1,048,576 | 32,768 |