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, with models DeepInfra lists no paid price for at the end. Listed prices from LiteLLM, OpenRouter and Vercel.
Models served
134
on this provider
Cheapest input
$0.019
per 1M tokens
Cheapest output
$0.02
per 1M tokens
Max context
10.5M
tokens
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
| Model ID | |||||
|---|---|---|---|---|---|
| Mistral Nemo Instruct 2407 | Mistral | 131K | $0.019 | $0.03 | deepinfra/mistralai/Mistral-Nemo-Instruct-2407 |
| Gemma 4 E4b It | 131K | $0.02 | $0.10 | deepinfra/google/gemma-4-E4B-it | |
| Llama 3.1 8B Instruct Turbo | Meta | 131K | $0.02 | $0.04 | 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 |
| gpt-oss-20b | OpenAI | 131K | $0.03 | $0.14 | deepinfra/openai/gpt-oss-20b |
| Llama 3 8B Instruct | Meta | 8K | $0.03 | $0.06 | deepinfra/meta-llama/Meta-Llama-3-8B-Instruct |
| Llama 3.1 8B Instruct | Meta | 200K | $0.03 | $0.05 | deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct |
| gpt-oss-120b | OpenAI | 131K | $0.037 | $0.17 | deepinfra/openai/gpt-oss-120b |
| Nvidia Nemotron Nano 9B V2 | NVIDIA | 131K | $0.04 | $0.16 | deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2 |
| Qwen2.5 7B Instruct | Alibaba | 33K | $0.04 | $0.10 | deepinfra/Qwen/Qwen2.5-7B-Instruct |
| Sao10K: l3-8b-lunaris-v1-turbo | Sao10K | 8K | $0.04 | $0.05 | deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo |
| Llama 3.2 11B Vision Instruct | Meta | 131K | $0.049 | $0.049 | deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct |
| Gemma 3 12B | 131K | $0.05 | $0.15 | deepinfra/google/gemma-3-12b-it | |
| Gemma 3 4B | 131K | $0.05 | $0.10 | deepinfra/google/gemma-3-4b-it | |
| Mistral Small 3 | Mistral | 33K | $0.05 | $0.08 | deepinfra/mistralai/Mistral-Small-24B-Instruct-2501 |
| Nemotron 3 Nano 30B A3B | NVIDIA | 262K | $0.05 | $0.20 | deepinfra/nvidia/Nemotron-3-Nano-30B-A3B |
| Llama Guard 3 8B | Meta | 131K | $0.055 | $0.055 | deepinfra/meta-llama/Llama-Guard-3-8B |
| GLM 4.7 Flash | Zhipu | 203K | $0.06 | $0.40 | deepinfra/zai-org/GLM-4.7-Flash |
| inclusionAI: Ling 3.0 Flash | InclusionAI | 262K | $0.06 | $0.18 | deepinfra/inclusionAI/Ling-3.0-flash |
| Gemma 4 26B A4B | 262K | $0.07 | $0.34 | deepinfra/google/gemma-4-26B-A4B-it | |
| Phi 4 | Microsoft | 16K | $0.07 | $0.14 | deepinfra/microsoft/phi-4 |
| Mistral Small 3.2 24B Instruct 2506 | Mistral | 128K | $0.075 | $0.20 | deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506 |
| DeepSeek V4 Flash 0731 | DeepSeek | 1M | $0.08 | $0.18 | deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731 |
| Gemma 3 27B | 131K | $0.08 | $0.16 | deepinfra/google/gemma-3-27b-it | |
| Nvidia Nemotron 3.5 Lightning | NVIDIA | 262K | $0.08 | $0.20 | deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning |
| Qwen3 32B | Alibaba | 131K | $0.08 | $0.28 | deepinfra/Qwen/Qwen3-32B |
| Nvidia Nemotron 3 Super 120B A12b | NVIDIA | 262K | $0.085 | $0.40 | deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B |
| DeepSeek V4 Flash 0423 | DeepSeek | 1M | $0.09 | $0.18 | deepinfra/deepseek-ai/DeepSeek-V4-Flash |
| Gemma 4 31B It Turbo | 262K | $0.09 | $0.34 | deepinfra/google/gemma-4-31B-it-turbo | |
| Qwen3 235B A22b Instruct 2507 | Alibaba | 262K | $0.09 | $0.55 | deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507 |
| Qwen3 Next 80B A3B Instruct | Alibaba | 262K | $0.09 | $1.10 | deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct |
| Gemini 2.0 Flash 001 | 1M | $0.10 | $0.40 | deepinfra/google/gemini-2.0-flash-001 | |
| Llama 3.3 70B Instruct Turbo | Meta | 131K | $0.10 | $0.32 | deepinfra/meta-llama/Llama-3.3-70B-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 |
| Llama 4 Scout 17B 16e Instruct | Meta | 10.5M | $0.10 | $0.30 | deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct |
| Qwen3.5-9B | Alibaba | 262K | $0.10 | $0.15 | deepinfra/Qwen/Qwen3.5-9B |
| Qwen3.6 35B A3B | Alibaba | 262K | $0.10 | $0.95 | deepinfra/Qwen/Qwen3.6-35B-A3B |
| Seed 2.0 Mini | Other | 256K | $0.10 | $0.40 | deepinfra/ByteDance/Seed-2.0-mini |
| Qwen3 14B | Alibaba | 41K | $0.12 | $0.24 | deepinfra/Qwen/Qwen3-14B |
| Qwen3 30B A3B | Alibaba | 131K | $0.12 | $0.50 | deepinfra/Qwen/Qwen3-30B-A3B |
| Gemma 4 31B | 262K | $0.13 | $0.38 | deepinfra/google/gemma-4-31B-it | |
| Hy3 | Tencent | 262K | $0.14 | $0.58 | deepinfra/tencent/Hy3 |
| Qwen3 Next 80B A3B Thinking | Alibaba | 262K | $0.14 | $1.40 | deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking |
| Qwen3.5-35B-A3B | Alibaba | 262K | $0.14 | $1.00 | deepinfra/Qwen/Qwen3.5-35B-A3B |
| GPT OSS 120B Turbo | OpenAI | 131K | $0.15 | $0.60 | deepinfra/openai/gpt-oss-120b-Turbo |
| Qwen3 VL 30B A3B Instruct | Alibaba | 262K | $0.15 | $0.60 | deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct |
| 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 |
| DeepSeek R1 Distill Llama 70B | DeepSeek | 131K | $0.20 | $0.60 | deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B |
1–50 of 135
Page 1 of 3
Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 1 price older, back to Sep 22, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI