DeepInfra API Pricing 2026

Compare pricing for all DeepInfra LLM models. See input/output costs, context windows, and features.

Showing 67 models from DeepInfra. Prices are per 1 million tokens. Data sourced from official pricing pages via LiteLLM.

Models

67

Cheapest Input

$0.02

/1M tokens

Cheapest Output

$0.02

/1M tokens

Max Context

1.0M

tokens

67 models
Features
meta-llama/Llama-3.2-3B-Instruct$0.020$0.020131.1K131.1K
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo$0.020$0.030131.1K131.1K
mistralai/Mistral-Nemo-Instruct-2407$0.020$0.040131.1K131.1K
meta-llama/Meta-Llama-3-8B-Instruct$0.030$0.0608.2K8.2K
meta-llama/Meta-Llama-3.1-8B-Instruct$0.030$0.050131.1K131.1K
google/gemma-3-4b-it$0.040$0.080131.1K131.1K
nvidia/NVIDIA-Nemotron-Nano-9B-v2$0.040$0.160131.1K131.1K
openai/gpt-oss-20b$0.040$0.150131.1K131.1K
Qwen/Qwen2.5-7B-Instruct$0.040$0.10032.8K32.8K
Sao10K/L3-8B-Lunaris-v1-Turbo$0.040$0.0508.2K8.2K
meta-llama/Llama-3.2-11B-Vision-Instruct$0.049$0.049131.1K131.1K
google/gemma-3-12b-it$0.050$0.100131.1K131.1K
mistralai/Mistral-Small-24B-Instruct-2501$0.050$0.08032.8K32.8K
openai/gpt-oss-120b$0.050$0.450131.1K131.1K
meta-llama/Llama-Guard-3-8B$0.055$0.055131.1K131.1K
Qwen/Qwen3-14B$0.060$0.24041.0K41.0K
microsoft/phi-4$0.070$0.14016.4K16.4K
mistralai/Mistral-Small-3.2-24B-Instruct-2506$0.075$0.200128K128K
Gryphe/MythoMax-L2-13b$0.080$0.0904.1K4.1K
meta-llama/Llama-4-Scout-17B-16E-Instruct$0.080$0.300327.7K327.7K
Qwen/Qwen3-30B-A3B$0.080$0.29041.0K41.0K
google/gemma-3-27b-it$0.090$0.160131.1K131.1K
Qwen/Qwen3-235B-A22B-Instruct-2507$0.090$0.600262.1K262.1K
google/gemini-2.0-flash-001$0.100$0.4001M1M
meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo$0.100$0.280131.1K131.1K
nvidia/Llama-3.3-Nemotron-Super-49B-v1.5$0.100$0.400131.1K131.1K
Qwen/Qwen3-32B$0.100$0.28041.0K41.0K
Qwen/Qwen2.5-72B-Instruct$0.120$0.39032.8K32.8K
meta-llama/Llama-3.3-70B-Instruct-Turbo$0.130$0.390131.1K131.1K
Qwen/Qwen3-Next-80B-A3B-Instruct$0.140$1.40262.1K262.1K
Qwen/Qwen3-Next-80B-A3B-Thinking$0.140$1.40262.1K262.1K
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8$0.150$0.6001.0M1.0M
Qwen/QwQ-32B$0.150$0.400131.1K131.1K
meta-llama/Llama-Guard-4-12B$0.180$0.180163.8K163.8K
Qwen/Qwen3-235B-A22B$0.180$0.54041.0K41.0K
deepseek-ai/DeepSeek-R1-Distill-Llama-70B$0.200$0.600131.1K131.1K
Qwen/Qwen2.5-VL-32B-Instruct$0.200$0.600128K128K
meta-llama/Llama-3.3-70B-Instruct$0.230$0.400131.1K131.1K
deepseek-ai/DeepSeek-V3-0324$0.250$0.880163.8K163.8K
allenai/olmOCR-7B-0725-FP8$0.270$1.5016.4K16.4K
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B$0.270$0.270131.1K131.1K
deepseek-ai/DeepSeek-V3.1$0.270$1.00163.8K163.8K
deepseek-ai/DeepSeek-V3.1-Terminus$0.270$1.00163.8K163.8K
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo$0.290$1.20262.1K262.1K
google/gemini-2.5-flash$0.300$2.501M1M
NousResearch/Hermes-3-Llama-3.1-70B$0.300$0.300131.1K131.1K
Qwen/Qwen3-235B-A22B-Thinking-2507$0.300$2.90262.1K262.1K
deepseek-ai/DeepSeek-V3$0.380$0.890163.8K163.8K
meta-llama/Meta-Llama-3.1-70B-Instruct$0.400$0.400131.1K131.1K
mistralai/Mixtral-8x7B-Instruct-v0.1$0.400$0.40032.8K32.8K
Qwen/Qwen3-Coder-480B-A35B-Instruct$0.400$1.60262.1K262.1K
zai-org/GLM-4.5$0.400$1.60131.1K131.1K
microsoft/WizardLM-2-8x22B$0.480$0.48065.5K65.5K
deepseek-ai/DeepSeek-R1-0528$0.500$2.15163.8K163.8K
moonshotai/Kimi-K2-Instruct$0.500$2.00131.1K131.1K
moonshotai/Kimi-K2-Instruct-0905$0.500$2.00262.1K262.1K
nvidia/Llama-3.1-Nemotron-70B-Instruct$0.600$0.600131.1K131.1K
Sao10K/L3.1-70B-Euryale-v2.2$0.650$0.750131.1K131.1K
Sao10K/L3.3-70B-Euryale-v2.3$0.650$0.750131.1K131.1K
deepseek-ai/DeepSeek-R1$0.700$2.40163.8K163.8K
deepseek-ai/DeepSeek-R1-0528-Turbo$1.00$3.0032.8K32.8K
deepseek-ai/DeepSeek-R1-Turbo$1.00$3.0041.0K41.0K
NousResearch/Hermes-3-Llama-3.1-405B$1.00$1.00131.1K131.1K
google/gemini-2.5-pro$1.25$10.001M1M
anthropic/claude-3-7-sonnet-latest$3.30$16.50200K200K
anthropic/claude-4-sonnet$3.30$16.50200K200K
anthropic/claude-4-opus$16.50$82.50200K200K

每周大模型价格速递

AI Model 调价时第一时间通知你。免费、不发垃圾邮件、随时退订。