Deep Infra serves 44 of the models we track. You can connect your own Deep Infra key and pay them directly — add a key.
| Model | Made by | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
| GPT-OSS 20B | OpenAI | $0.03 | $0.14 | 131K |
| GPT-OSS 120B | OpenAI | $0.037 | $0.17 | 131K |
| nemotron-3-nano-30b-a3b | NVIDIA | $0.05 | $0.2 | 262K |
| Gemma 3 12B IT | NVIDIA | $0.05 | $0.15 | 131K |
| Gemma 3 4B IT | NVIDIA | $0.05 | $0.1 | 131K |
| GLM-4.7-Flash | Zhipu AI | $0.06 | $0.4 | 203K |
| DeepSeek V4 Flash 0731 | Alibaba | $0.06 | $0.18 | 1.0M |
| Gemma 4 26B A4B IT | $0.07 | $0.34 | 262K | |
| Gemma 3 27B IT | Amazon Bedrock | $0.08 | $0.16 | 131K |
| DeepSeek V4 Flash | DeepSeek | $0.09 | $0.18 | 1.0M |
| Qwen3 235B-A22B Instruct 2507 | Amazon Bedrock | $0.09 | $0.55 | 262K |
| Qwen3-Next 80B-A3B Instruct | Alibaba | $0.09 | $1.1 | 262K |
| Qwen3.6 35B-A3B | Alibaba | $0.1 | $0.95 | 262K |
| Gemma 4 31B IT | $0.13 | $0.38 | 262K | |
| GLM-5.3-Flash | Zhipu AI | $0.15 | $0.5 | 1.0M |
| MiniMax M2.5 | MiniMax | $0.15 | $1.15 | 197K |
| DeepSeek V4.1 Flash | DeepSeek | $0.2 | $0.6 | 1.0M |
| Step 3.7 Flash | StepFun | $0.2 | $1.15 | 262K |
| Qwen3 VL 235B A22B Instruct | Amazon Bedrock | $0.2 | $0.88 | 262K |
| DeepSeek V3.1 | DeepSeek | $0.25 | $0.95 | 164K |
| MiniMax-M2.7 | MiniMax | $0.25 | $1 | 197K |
| DeepSeek V3.2 | DeepSeek | $0.26 | $0.38 | 164K |
| Qwen3.5 27B | Alibaba | $0.26 | $2.6 | 262K |
| MiniMax-M3 | MiniMax | $0.28 | $1.1 | 524K |
| Qwen3.5 122B-A10B | Alibaba | $0.29 | $2.4 | 262K |
| Qwen3.6 27B | Alibaba | $0.32 | $3.2 | 262K |
| Llama 3.3 Nemotron Super 49B v1.5 | NVIDIA | $0.4 | $0.4 | 131K |
| GLM-4.7 | Zhipu AI | $0.4 | $1.75 | 203K |
| DeepSeek V4 Flash Vision Exp | DeepSeek | $0.44 | $1.32 | 1.0M |
| Kimi K2.5 | Moonshot AI | $0.45 | $2.25 | 262K |
| GLM-4.6 | Zhipu AI | $0.5 | $2 | 203K |
| DeepSeek R1 0528 | DeepSeek | $0.5 | $2.15 | 164K |
| GLM-5 | Zhipu AI | $0.6 | $2.08 | 203K |
| Kimi K2.7 Code | Moonshot AI | $0.68 | $3.4 | 262K |
| Kimi K2.6 | Moonshot AI | $0.75 | $3.5 | 262K |
| GLM-5.2 | Mistral | $0.75 | $2.4 | 1.0M |
| Inkling | NVIDIA | $0.95 | $4.05 | 524K |
| GLM-5.1 | Zhipu AI | $1.05 | $3.5 | 203K |
| GLM-5.3 | Zhipu AI | $1.2 | $4 | 1.0M |
| DeepSeek V4 Pro | DeepSeek | $1.3 | $2.6 | 1.0M |
| DeepSeek V4 Pro 0813 | NVIDIA | $1.3 | $2.6 | 1.0M |
| Qwen3.8 Max | Alibaba | $1.65 | $4.951 | 256K |
| Qwen3.7 Max | Alibaba | $2.5 | $7.5 | 256K |
| Kimi K3 | Moonshot AI | $2.85 | $14.25 | 1.0M |
Deep Infra serves 44 of the models we track, across 1 model type.
GPT-OSS 20B at $0.03 per million input tokens.
Yes. Deep Infra is one of the providers Serenities supports for bring-your-own-key, so you can connect your own account and pay Deep Infra directly.
