Provider model catalog
DeepInfra models
Serverless inference for open-source models
113 unique catalog models
Model pricing and capabilities
- olmOCR-7B-0725-FP8$0.270 / 1M tokens input
- claude-3-7-sonnet-latest$3.30 / 1M tokens input
- claude-4-opus$16.5 / 1M tokens input
- claude-4-sonnet$3.30 / 1M tokens input
- claude-fable-5$10.0 / 1M tokens input
- Seed-2.0-code$0.500 / 1M tokens input
- Seed-2.0-pro$0.500 / 1M tokens input
- DeepSeek-R1$0.700 / 1M tokens input
- DeepSeek-R1-0528$0.500 / 1M tokens input
- DeepSeek-R1-0528-Turbo$1.00 / 1M tokens input
- DeepSeek-R1-Distill-Llama-70B$0.200 / 1M tokens input
- DeepSeek-R1-Distill-Qwen-32B$0.270 / 1M tokens input
- DeepSeek-R1-Turbo$1.00 / 1M tokens input
- DeepSeek-V3$0.320 / 1M tokens input
- DeepSeek-V3-0324$0.240 / 1M tokens input
- DeepSeek-V3.1$0.250 / 1M tokens input
- DeepSeek-V3.1-Terminus$0.270 / 1M tokens input
- DeepSeek-V3.2$0.260 / 1M tokens input
- DeepSeek-V4-Flash$0.090 / 1M tokens input
- DeepSeek-V4-Flash-0731$0.060 / 1M tokens input
- DeepSeek-V4-Pro$1.30 / 1M tokens input
- DeepSeek-V4-Pro-0813$1.30 / 1M tokens input
- gemini-2.0-flash-001$0.100 / 1M tokens input
- gemini-2.5-flash$0.300 / 1M tokens input
All 113 DeepInfra models
- gemini-2.5-pro$1.25 / 1M tokens
- gemma-3-12b-it$0.050 / 1M tokens
- gemma-3-27b-it$0.080 / 1M tokens
- gemma-3-4b-it$0.050 / 1M tokens
- gemma-4-26B-A4B-it$0.070 / 1M tokens
- gemma-4-31B-it$0.200 / 1M tokens
- gemma-4-E4B-it$0.020 / 1M tokens
- MythoMax-L2-13b$0.080 / 1M tokens
- Llama-3.2-11B-Vision-Instruct$0.049 / 1M tokens
- Llama-3.2-3B-Instruct$0.020 / 1M tokens
- Llama-3.3-70B-Instruct$0.230 / 1M tokens
- Llama-3.3-70B-Instruct-Turbo$0.100 / 1M tokens
- Llama-4-Maverick-17B-128E-Instruct-FP8$0.200 / 1M tokens
- Llama-4-Scout-17B-16E-Instruct$0.100 / 1M tokens
- Llama-Guard-3-8B$0.055 / 1M tokens
- Llama-Guard-4-12B$0.180 / 1M tokens
- Meta-Llama-3-8B-Instruct$0.030 / 1M tokens
- Meta-Llama-3.1-70B-Instruct$0.400 / 1M tokens
- Meta-Llama-3.1-70B-Instruct-Turbo$0.100 / 1M tokens
- Meta-Llama-3.1-8B-Instruct$0.030 / 1M tokens
- Meta-Llama-3.1-8B-Instruct-Turbo$0.020 / 1M tokens
- phi-4$0.070 / 1M tokens
- WizardLM-2-8x22B$0.480 / 1M tokens
- MiniMax-M2.7$0.250 / 1M tokens
- MiniMax-M3$0.280 / 1M tokens
- Mistral-Nemo-Instruct-2407$0.020 / 1M tokens
- Mistral-Small-24B-Instruct-2501$0.050 / 1M tokens
- Mistral-Small-3.2-24B-Instruct-2506$0.075 / 1M tokens
- Mixtral-8x7B-Instruct-v0.1$0.400 / 1M tokens
- Kimi-K2-Instruct$0.500 / 1M tokens
- Kimi-K2-Instruct-0905$0.500 / 1M tokens
- Kimi-K2.5$0.450 / 1M tokens
- Kimi-K2.6$0.750 / 1M tokens
- Kimi-K2.7-Code$0.680 / 1M tokens
- Kimi-K3$2.85 / 1M tokens
- Hermes-3-Llama-3.1-405B$1.00 / 1M tokens
- Hermes-3-Llama-3.1-70B$0.300 / 1M tokens
- Llama-3.1-Nemotron-70B-Instruct$0.600 / 1M tokens
- Llama-3.3-Nemotron-Super-49B-v1.5$0.100 / 1M tokens
- NVIDIA-Nemotron-Nano-9B-v2$0.040 / 1M tokens
- gpt-oss-120b$0.037 / 1M tokens
- gpt-oss-20b$0.030 / 1M tokens
- Qwen2.5-72B-Instruct$0.120 / 1M tokens
- Qwen2.5-7B-Instruct$0.040 / 1M tokens
- Qwen2.5-VL-32B-Instruct$0.200 / 1M tokens
- Qwen3-14B$0.060 / 1M tokens
- Qwen3-235B-A22B$0.180 / 1M tokens
- Qwen3-235B-A22B-Instruct-2507$0.090 / 1M tokens
- Qwen3-235B-A22B-Thinking-2507$0.300 / 1M tokens
- Qwen3-30B-A3B$0.120 / 1M tokens
- Qwen3-32B$0.080 / 1M tokens
- Qwen3-Coder-480B-A35B-Instruct$0.400 / 1M tokens
- Qwen3-Coder-480B-A35B-Instruct-Turbo$0.300 / 1M tokens
- Qwen3-Max$1.20 / 1M tokens
- Qwen3-Next-80B-A3B-Instruct$0.090 / 1M tokens
- Qwen3-Next-80B-A3B-Thinking$0.140 / 1M tokens
- Qwen3-VL-235B-A22B-Instruct$0.200 / 1M tokens
- Qwen3-VL-30B-A3B-Instruct$0.150 / 1M tokens
- Qwen3.5-122B-A10B$0.290 / 1M tokens
- Qwen3.5-27B$0.260 / 1M tokens
- Qwen3.5-35B-A3B$0.140 / 1M tokens
- Qwen3.5-397B-A17B$0.450 / 1M tokens
- Qwen3.5-9B$0.100 / 1M tokens
- Qwen3.6-27B$0.320 / 1M tokens
- Qwen3.6-35B-A3B$0.100 / 1M tokens
- Qwen3.7-Max$2.50 / 1M tokens
- Qwen3.8-2.4T-A95B$2.00 / 1M tokens
- Qwen3.8-27B$0.400 / 1M tokens
- Qwen3.8-Max$1.65 / 1M tokens
- QwQ-32B$0.150 / 1M tokens
- L3-8B-Lunaris-v1-Turbo$0.040 / 1M tokens
- L3.1-70B-Euryale-v2.2$0.650 / 1M tokens
- L3.3-70B-Euryale-v2.3$0.650 / 1M tokens
- Step-3.7-Flash$0.200 / 1M tokens
- Hy3$0.140 / 1M tokens
- Hy4-preview$0.834 / 1M tokens
- Inkling$0.950 / 1M tokens
- Inkling-Small$0.450 / 1M tokens
- MiMo-V2.5$0.400 / 1M tokens
- MiMo-V2.5-Pro$1.00 / 1M tokens
- MiMo-V2.6-Flash$0.140 / 1M tokens
- GLM-4.5$0.400 / 1M tokens
- GLM-4.6$0.500 / 1M tokens
- GLM-4.7$0.400 / 1M tokens
- GLM-4.7-Flash$0.060 / 1M tokens
- GLM-5$0.600 / 1M tokens
- GLM-5.1$1.05 / 1M tokens
- GLM-5.2$0.750 / 1M tokens
- GLM-5.3-Flash$0.150 / 1M tokens