DeepInfra LLM API pricing
Every model DeepInfra serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.
Models served
67
on this provider
Cheapest input
$0.02
per 1M tokens
Cheapest output
$0.02
per 1M tokens
Max context
10.5M
tokens
| Model ID | |||||
|---|---|---|---|---|---|
| Meta Llama 3.1 8B Instruct Turbo | Meta | 131K | $0.02 | $0.03 | deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo |
| Llama 3.2 3B Instruct | Meta | 131K | $0.02 | $0.02 | deepinfra/meta-llama/Llama-3.2-3B-Instruct |
| Mistral Nemo Instruct 2407 | Mistral | 131K | $0.02 | $0.04 | deepinfra/mistralai/Mistral-Nemo-Instruct-2407 |
| Meta Llama 3 8B Instruct | Meta | 8K | $0.03 | $0.06 | deepinfra/meta-llama/Meta-Llama-3-8B-Instruct |
| Meta Llama 3.1 8B Instruct | Meta | 131K | $0.03 | $0.05 | deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct |
| L3 8B Lunaris V1 Turbo | Other | 8K | $0.04 | $0.05 | deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo |
| Qwen2 5 7B Instruct | Alibaba | 33K | $0.04 | $0.10 | deepinfra/Qwen/Qwen2.5-7B-Instruct |
| Gemma 3 4B | 131K | $0.04 | $0.08 | deepinfra/google/gemma-3-4b-it | |
| Nvidia Nemotron Nano 9B | NVIDIA | 131K | $0.04 | $0.16 | deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2 |
| gpt-oss-20b | OpenAI | 131K | $0.04 | $0.15 | deepinfra/openai/gpt-oss-20b |
| Llama 3.2 11B Vision Instruct | Meta | 131K | $0.05 | $0.05 | deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct |
| Gemma 3 12B | 131K | $0.05 | $0.10 | deepinfra/google/gemma-3-12b-it | |
| Mistral Small 3 | Mistral | 33K | $0.05 | $0.08 | deepinfra/mistralai/Mistral-Small-24B-Instruct-2501 |
| gpt-oss-120b | OpenAI | 131K | $0.05 | $0.45 | deepinfra/openai/gpt-oss-120b |
| Llama Guard 3 8B | Meta | 131K | $0.06 | $0.06 | deepinfra/meta-llama/Llama-Guard-3-8B |
| Qwen3 14B | Alibaba | 41K | $0.06 | $0.24 | deepinfra/Qwen/Qwen3-14B |
| Phi 4 | Microsoft | 16K | $0.07 | $0.14 | deepinfra/microsoft/phi-4 |
| Mistral Small 3.2 24B Instruct 2506 | Mistral | 128K | $0.07 | $0.20 | deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506 |
| MythoMax 13B | Other | 4K | $0.08 | $0.09 | deepinfra/Gryphe/MythoMax-L2-13b |
| Qwen3 30B A3B | Alibaba | 131K | $0.08 | $0.29 | deepinfra/Qwen/Qwen3-30B-A3B |
| Llama 4 Scout 17B 16e Instruct | Meta | 10.5M | $0.08 | $0.30 | deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct |
| Qwen3 235B A22b Instruct 2507 | Alibaba | 262K | $0.09 | $0.60 | deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507 |
| Gemma 3 27B | 131K | $0.09 | $0.16 | deepinfra/google/gemma-3-27b-it | |
| Qwen3 32B | Alibaba | 131K | $0.10 | $0.28 | deepinfra/Qwen/Qwen3-32B |
| Meta Llama 3.1 70B Instruct Turbo | Meta | 131K | $0.10 | $0.28 | deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo |
| Llama 3.3 Nemotron Super 49B V1.5 | NVIDIA | 131K | $0.10 | $0.40 | deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 |
| Gemini 2.0 Flash 001 | 1M | $0.10 | $0.40 | deepinfra/google/gemini-2.0-flash-001 | |
| Qwen2 5 72B Instruct | Alibaba | 131K | $0.12 | $0.39 | deepinfra/Qwen/Qwen2.5-72B-Instruct |
| Llama 3.3 70B Instruct Turbo | Meta | 131K | $0.13 | $0.39 | deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo |
| Qwen3 Next 80B A3B Instruct | Alibaba | 262K | $0.14 | $1.40 | deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct |
| Qwen3 Next 80B A3B Thinking | Alibaba | 262K | $0.14 | $1.40 | deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking |
| Llama 4 Maverick 17B 128e Instruct FP8 | Meta | 1M | $0.15 | $0.60 | deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 |
| QwQ 32B | Alibaba | 131K | $0.15 | $0.40 | deepinfra/Qwen/QwQ-32B |
| Llama Guard 4 12B | Meta | 164K | $0.18 | $0.18 | deepinfra/meta-llama/Llama-Guard-4-12B |
| Qwen3 235B A22B | Alibaba | 262K | $0.18 | $0.54 | deepinfra/Qwen/Qwen3-235B-A22B |
| R1 Distill Llama 70B | DeepSeek | 131K | $0.20 | $0.60 | deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B |
| Qwen2 5 VL 32B Instruct | Alibaba | 128K | $0.20 | $0.60 | deepinfra/Qwen/Qwen2.5-VL-32B-Instruct |
| Llama 3.3 70B Instruct | Meta | 131K | $0.23 | $0.40 | deepinfra/meta-llama/Llama-3.3-70B-Instruct |
| DeepSeek V3 0324 | DeepSeek | 164K | $0.25 | $0.88 | deepinfra/deepseek-ai/DeepSeek-V3-0324 |
| DeepSeek R1 Distill Qwen 32B | DeepSeek | 131K | $0.27 | $0.27 | deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B |
| DeepSeek V3.1 Terminus | DeepSeek | 164K | $0.27 | $1.00 | deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus |
| Olmocr 7B 0725 FP8 | Allen AI | 16K | $0.27 | $1.50 | deepinfra/allenai/olmOCR-7B-0725-FP8 |
| DeepSeek V3 1 | DeepSeek | 164K | $0.27 | $1.00 | deepinfra/deepseek-ai/DeepSeek-V3.1 |
| Qwen3 Coder 480B A35b Instruct Turbo | Alibaba | 262K | $0.29 | $1.20 | deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo |
| Qwen3 235B A22B Thinking 2507 | Alibaba | 262K | $0.30 | $2.90 | deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507 |
| Hermes 3 70B Instruct | Nous Research | 131K | $0.30 | $0.30 | deepinfra/NousResearch/Hermes-3-Llama-3.1-70B |
| Gemini 2.5 Flash | 1M | $0.30 | $2.50 | deepinfra/google/gemini-2.5-flash | |
| DeepSeek | DeepSeek | 164K | $0.38 | $0.89 | deepinfra/deepseek-ai/DeepSeek-V3 |
| Mixtral 8x7B Instruct V0 1 | Mistral | 33K | $0.40 | $0.40 | deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1 |
| GLM 4.5 | Zhipu | 131K | $0.40 | $1.60 | deepinfra/zai-org/GLM-4.5 |
1–50 of 67
Page 1 of 2
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI