DeepInfra models & pricing
DeepInfra hosts 137 models (137 with public pricing) covering 1 modalities. GPU inference for Llama, Qwen, DeepSeek, FLUX with per-token pricing. Cheapest input starts at $0.0190/M tokens; the most premium goes up to $16.50/M. Use Future AGI's Agent Command Center to route any DeepInfra model with cost-optimized fallback and unified observability.
137
chat 137
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Mistral Nemo Instruct 2407 | $0.0190/M | $0.0300/M | $0.0218/M | 131,072 | tools |
| Gemma 4 E4b IT | $0.0200/M | $0.1000/M | $0.0400/M | 131,072 | tools · reasoning |
| Llama 3.2 3B Instruct | $0.0200/M | $0.0200/M | $0.0200/M | 131,072 | tools |
| Llama 3.1 8B Instruct Turbo | $0.0200/M | $0.0400/M | $0.0250/M | 131,072 | tools |
| Llama 3.1 8B Instruct | $0.0300/M | $0.0500/M | $0.0350/M | 131,072 | tools |
| Llama 3 8B Instruct | $0.0300/M | $0.0600/M | $0.0375/M | 8,192 | tools |
| gpt-oss 20B | $0.0300/M | $0.140/M | $0.0575/M | 131,072 | tools |
| gpt-oss 120B | $0.0370/M | $0.170/M | $0.0702/M | 131,072 | tools |
| Nvidia Nvidia Nemotron nano 9B v2 | $0.0400/M | $0.160/M | $0.0700/M | 131,072 | tools |
| Qwen2.5 7B Instruct | $0.0400/M | $0.1000/M | $0.0550/M | 32,768 | |
| Sao10k L3 8B Lunaris V1 Turbo | $0.0400/M | $0.0500/M | $0.0425/M | 8,192 | |
| Llama 3.2 11B Vision Instruct | $0.0490/M | $0.0490/M | $0.0490/M | 131,072 | |
| Gemma 3 12B IT | $0.0500/M | $0.150/M | $0.0750/M | 131,072 | tools |
| Gemma 3 4B IT | $0.0500/M | $0.1000/M | $0.0625/M | 131,072 | tools |
| Mistral Small 24B Instruct 2501 | $0.0500/M | $0.0800/M | $0.0575/M | 32,768 | tools |
| Nvidia Nemotron 3 nano 30B A3B | $0.0500/M | $0.200/M | $0.0875/M | 262,144 | tools · reasoning · cache |
| Llama Guard 3 8B | $0.0550/M | $0.0550/M | $0.0550/M | 131,072 | |
| Inclusionai Ling 3.0 Flash | $0.0600/M | $0.180/M | $0.0900/M | 131,072 | tools · reasoning · cache |
| GLM 4.7 Flash | $0.0600/M | $0.400/M | $0.145/M | 202,752 | tools · reasoning · cache |
| Gemma 4 26B A4B IT | $0.0700/M | $0.340/M | $0.138/M | 262,144 | tools · vision · reasoning |
| Phi 4 | $0.0700/M | $0.140/M | $0.0875/M | 16,384 | tools |
| Mistral Small 3.2 24B Instruct 2506 | $0.0750/M | $0.200/M | $0.106/M | 128,000 | tools |
| DeepSeek V4 Flash 0731 | $0.0800/M | $0.180/M | $0.105/M | 1,048,576 | tools · reasoning · cache |
| Gemma 3 27B IT | $0.0800/M | $0.160/M | $0.100/M | 131,072 | tools |
| Nvidia Nvidia Nemotron 3.5 Lightning | $0.0800/M | $0.200/M | $0.110/M | 262,144 | tools · reasoning · cache |
| Qwen3 32B | $0.0800/M | $0.280/M | $0.130/M | 40,960 | tools |
| Nvidia Nvidia Nemotron 3 Super 120B A12B | $0.0850/M | $0.400/M | $0.164/M | 262,144 | tools · reasoning |
| DeepSeek V4 Flash | $0.0900/M | $0.180/M | $0.113/M | 1,048,576 | tools · reasoning · cache |
| Gemma 4 31B IT Turbo | $0.0900/M | $0.340/M | $0.153/M | 262,144 | tools · vision · reasoning · cache |
| Qwen3 235B A22B Instruct 2507 | $0.0900/M | $0.550/M | $0.205/M | 262,144 | tools |
| Qwen3 Next 80B A3B Instruct | $0.0900/M | $1.10/M | $0.343/M | 262,144 | tools |
| Bytedance Seed 2.0 mini | $0.1000/M | $0.400/M | $0.175/M | 256,000 | tools · vision · reasoning · cache |
| Gemini 2.0 Flash 001 Deprecated | $0.1000/M | $0.400/M | $0.175/M | 1,000,000 | tools |
| Llama 3.3 70B Instruct Turbo | $0.1000/M | $0.320/M | $0.155/M | 131,072 | tools |
| Llama 4 Scout 17B 16e Instruct | $0.1000/M | $0.300/M | $0.150/M | 327,680 | tools |
| Nvidia Llama 3.3 Nemotron Super 49B v1.5 | $0.1000/M | $0.400/M | $0.175/M | 131,072 | tools |
| Qwen3.5 9B | $0.1000/M | $0.150/M | $0.112/M | 262,144 | tools · vision |
| Qwen3.6 35B A3B | $0.1000/M | $0.950/M | $0.313/M | 262,144 | tools · vision · reasoning |
| Qwen3 14B | $0.120/M | $0.240/M | $0.150/M | 40,960 | tools |
| Qwen3 30B A3B | $0.120/M | $0.500/M | $0.215/M | 40,960 | tools |
| Gemma 4 31B IT | $0.130/M | $0.380/M | $0.193/M | 262,144 | tools · vision · reasoning |
| DeepSeek V4.1 Flash | $0.140/M | $0.420/M | $0.210/M | 1,048,576 | tools · vision · reasoning · cache |
| DeepSeek V4.1 Flash 1017 | $0.140/M | $0.420/M | $0.210/M | 1,048,576 | tools · vision · reasoning · cache |
| Qwen3.5 35B A3B | $0.140/M | $1.00/M | $0.355/M | 262,144 | tools · vision · reasoning · cache |
| Qwen3 Next 80B A3B Thinking | $0.140/M | $1.40/M | $0.455/M | 262,144 | tools |
| Tencent Hy3 | $0.140/M | $0.580/M | $0.250/M | 262,144 | tools · reasoning · cache |
| gpt-oss 120B Turbo | $0.150/M | $0.600/M | $0.262/M | 131,072 | tools · reasoning |
| Qwen3 VL 30B A3B Instruct | $0.150/M | $0.600/M | $0.262/M | 262,144 | tools · vision |
| QwQ 32B | $0.150/M | $0.400/M | $0.212/M | 131,072 | tools |
| Llama Guard 4 12B | $0.180/M | $0.180/M | $0.180/M | 163,840 | |
| Qwen3 235B A22B | $0.180/M | $0.540/M | $0.270/M | 40,960 | tools |
| DeepSeek R1 Distill Llama 70B | $0.200/M | $0.600/M | $0.300/M | 131,072 | |
| Llama 4 Maverick 17B 128e Instruct FP8 | $0.200/M | $0.800/M | $0.350/M | 1,048,576 | tools |
| Nvidia Nemotron Content Safety 3.5 | $0.200/M | $0.200/M | $0.200/M | 131,072 | vision |
| gpt-oss 120B Ultra | $0.200/M | $0.950/M | $0.387/M | 131,072 | tools · reasoning |
| Qwen2.5 VL 32B Instruct | $0.200/M | $0.600/M | $0.300/M | 128,000 | tools · vision |
| Qwen3 VL 235B A22B Instruct | $0.200/M | $0.880/M | $0.370/M | 262,144 | tools · vision · cache |
| Stepfun AI Step 3.7 Flash | $0.200/M | $1.15/M | $0.438/M | 262,144 | tools · vision · cache |
| Llama 3.3 70B Instruct | $0.230/M | $0.400/M | $0.272/M | 131,072 | tools |
| DeepSeek v3.0324 | $0.240/M | $0.900/M | $0.405/M | 163,840 | tools · cache |
| Bytedance Seed 1.8 | $0.250/M | $2.00/M | $0.688/M | 256,000 | tools · vision · reasoning · cache |
| DeepSeek v3.1 | $0.250/M | $0.950/M | $0.425/M | 163,840 | tools · reasoning |
| Gemini 3.1 Flash Lite | $0.250/M | $1.50/M | $0.563/M | 1,000,000 | tools · vision · reasoning · audio |
| MiniMax M2.7 | $0.250/M | $1.00/M | $0.438/M | 196,608 | tools · reasoning · cache |
| DeepSeek v3.2 | $0.260/M | $0.380/M | $0.290/M | 163,840 | tools · cache |
| Qwen3.5 27B | $0.260/M | $2.60/M | $0.845/M | 262,144 | tools · vision · reasoning |
| Allenai Olmocr 7B 0725 FP8 | $0.270/M | $1.50/M | $0.578/M | 16,384 | |
| DeepSeek R1 Distill Qwen 32B | $0.270/M | $0.270/M | $0.270/M | 131,072 | tools |
| DeepSeek V3.1 Terminus | $0.270/M | $1.00/M | $0.453/M | 163,840 | tools |
| Gemma 4 31B IT Ultra | $0.270/M | $0.760/M | $0.393/M | 131,072 | tools · vision · reasoning |
| MiniMax M3 | $0.280/M | $1.10/M | $0.485/M | 524,288 | tools · vision · reasoning · cache |
| Qwen3.5 122B A10B | $0.290/M | $2.40/M | $0.817/M | 262,144 | tools · vision · reasoning |
| Gemini 2.5 Flash | $0.300/M | $2.50/M | $0.850/M | 1,000,000 | tools · vision · reasoning · audio |
| Meta Models Muse Glimmer 30B | $0.300/M | $1.20/M | $0.525/M | 131,072 | tools · vision · reasoning · cache |
| Qwen3 235B A22B Thinking 2507 | $0.300/M | $2.90/M | $0.950/M | 262,144 | tools |
| Qwen3 Coder 480B A35B Instruct Turbo | $0.300/M | $1.00/M | $0.475/M | 262,144 | tools · cache |
| DeepSeek V3 | $0.320/M | $0.890/M | $0.462/M | 163,840 | tools |
| Qwen3.6 27B | $0.320/M | $3.20/M | $1.04/M | 262,144 | tools · vision · reasoning |
| Qwen2.5 72B Instruct | $0.360/M | $0.400/M | $0.370/M | 32,768 | tools |
| MiniMax M2.7 Turbo | $0.380/M | $1.70/M | $0.710/M | 196,608 | tools · reasoning · cache |
| Gryphe Mythomax L2 13B | $0.400/M | $0.400/M | $0.400/M | 4,096 | tools |
| Llama 3.1 70B Instruct | $0.400/M | $0.400/M | $0.400/M | 131,072 | tools |
| Llama 3.1 70B Instruct Turbo | $0.400/M | $0.400/M | $0.400/M | 131,072 | tools |
| Mixtral 8×7B Instruct v0.1 | $0.400/M | $0.400/M | $0.400/M | 32,768 | tools |
| Qwen3.8 27B | $0.400/M | $3.00/M | $1.05/M | 262,144 | tools · vision · reasoning · cache |
| Qwen3 Coder 480B A35B Instruct | $0.400/M | $1.60/M | $0.700/M | 262,144 | tools |
| Mimo v2.5 | $0.400/M | $2.00/M | $0.800/M | 262,144 | tools · vision · reasoning · cache |
| GLM 4.5 | $0.400/M | $1.60/M | $0.700/M | 131,072 | tools |
| GLM 4.7 | $0.400/M | $1.75/M | $0.738/M | 202,752 | tools · reasoning · cache |
| Kimi K2.5 | $0.450/M | $2.25/M | $0.900/M | 262,144 | tools · vision · reasoning · cache |
| Qwen3.5 397B A17B | $0.450/M | $3.00/M | $1.09/M | 262,144 | tools · vision · reasoning · cache |
| Thinkingmachines Inkling Small | $0.450/M | $1.20/M | $0.638/M | 524,288 | tools · vision · reasoning · cache |
| Microsoft Wizardlm 2.8x22b | $0.480/M | $0.480/M | $0.480/M | 65,536 | |
| Bytedance Seed 2.0 Code | $0.500/M | $3.00/M | $1.13/M | 256,000 | tools · vision · reasoning · cache |
| Bytedance Seed 2.0 Pro | $0.500/M | $3.00/M | $1.13/M | 256,000 | tools · vision · reasoning · cache |
| DeepSeek R1 0528 | $0.500/M | $2.15/M | $0.913/M | 163,840 | tools |
| Kimi K2 Instruct | $0.500/M | $2.00/M | $0.875/M | 131,072 | tools |
| Kimi K2 Instruct 0905 | $0.500/M | $2.00/M | $0.875/M | 262,144 | tools |
| Nvidia Nvidia Nemotron 3 Ultra 550B A55B | $0.500/M | $2.20/M | $0.925/M | 262,144 | tools · vision · reasoning · cache |
| GLM 4.6 | $0.500/M | $2.00/M | $0.875/M | 202,752 | tools · reasoning · cache |
| Nvidia Llama 3.1 Nemotron 70B Instruct | $0.600/M | $0.600/M | $0.600/M | 131,072 | tools |
| GLM 5 | $0.600/M | $2.08/M | $0.970/M | 202,752 | tools · reasoning · cache |
| Sao10k L3.3 70B Euryale v2.3 | $0.650/M | $0.750/M | $0.675/M | 131,072 | |
| Kimi K2.7 Code | $0.680/M | $3.40/M | $1.36/M | 262,144 | tools · vision · reasoning · cache |
| DeepSeek R1 | $0.700/M | $2.40/M | $1.13/M | 163,840 | tools |
| Nousresearch Hermes 3 Llama 3.1 70B | $0.700/M | $0.700/M | $0.700/M | 131,072 | |
| Gemini 3.7 Flash | $0.750/M | $3.75/M | $1.50/M | 1,000,000 | tools · vision · reasoning · audio |
| Kimi K2.6 | $0.750/M | $3.50/M | $1.44/M | 262,144 | tools · vision · reasoning · cache |
| GLM 5.2 | $0.750/M | $2.40/M | $1.16/M | 1,048,576 | tools · reasoning · cache |
| Sao10k L3.1 70B Euryale v2.2 | $0.850/M | $0.850/M | $0.850/M | 131,072 | |
| Thinkingmachines Inkling | $0.950/M | $4.05/M | $1.72/M | 524,288 | tools · vision · reasoning · cache |
| Claude Haiku 4.5 | $1.00/M | $5.00/M | $2.00/M | 200,000 | tools · vision · reasoning |
| DeepSeek R1 0528 Turbo | $1.00/M | $3.00/M | $1.50/M | 32,768 | tools |
| DeepSeek R1 Turbo | $1.00/M | $3.00/M | $1.50/M | 40,960 | tools |
| Nousresearch Hermes 3 Llama 3.1 405B | $1.00/M | $1.00/M | $1.00/M | 131,072 | tools |
| Mimo V2.5 Pro | $1.00/M | $3.00/M | $1.50/M | 1,048,576 | tools · reasoning · cache |
| GLM 5.1 | $1.05/M | $3.50/M | $1.66/M | 202,752 | tools · reasoning · cache |
| Qwen3 Max | $1.20/M | $6.00/M | $2.40/M | 256,000 | tools · cache |
| Qwen3 Max Thinking | $1.20/M | $6.00/M | $2.40/M | 256,000 | tools · cache |
| Gemini 2.5 Pro | $1.25/M | $10.00/M | $3.44/M | 1,000,000 | tools · vision · reasoning · audio |
| DeepSeek V4 Pro | $1.30/M | $2.60/M | $1.63/M | 1,048,576 | tools · cache |
| DeepSeek V4 Pro 0813 | $1.30/M | $2.60/M | $1.63/M | 1,048,576 | tools · cache |
| Gemini 3.5 Flash | $1.50/M | $9.00/M | $3.38/M | 1,000,000 | tools · vision · reasoning · audio |
| Qwen3.8 Max | $1.65/M | $4.95/M | $2.48/M | 256,000 | tools · cache |
| Claude Sonnet 5 | $2.00/M | $10.00/M | $4.00/M | 1,000,000 | tools · vision · reasoning |
| Gemini 3.1 Pro | $2.00/M | $12.00/M | $4.50/M | 1,000,000 | tools · vision · reasoning · audio |
| Qwen3.8 2.4t A95B | $2.00/M | $6.00/M | $3.00/M | 262,144 | tools · reasoning · cache |
| Qwen3.7 Max | $2.50/M | $7.50/M | $3.75/M | 256,000 | tools · cache |
| Kimi K3 | $2.85/M | $14.25/M | $5.70/M | 1,048,576 | tools · vision · cache |
| Claude Sonnet 4.6 | $3.00/M | $15.00/M | $6.00/M | 1,000,000 | tools · vision · reasoning |
| Claude 3.7 Sonnet latest | $3.30/M | $16.50/M | $6.60/M | 200,000 | tools |
| Claude 4 Sonnet | $3.30/M | $16.50/M | $6.60/M | 200,000 | tools |
| Claude Opus 4.7 | $5.00/M | $25.00/M | $10.00/M | 1,000,000 | tools · vision · reasoning |
| Claude Opus 4.8 | $5.00/M | $25.00/M | $10.00/M | 1,000,000 | tools · vision · reasoning |
| Claude Opus 5 | $5.00/M | $25.00/M | $10.00/M | 1,000,000 | tools · vision · reasoning |
| Claude Fable 5 | $10.00/M | $50.00/M | $20.00/M | 1,000,000 | tools · vision · reasoning |
| Claude 4 Opus | $16.50/M | $82.50/M | $33.00/M | 200,000 | tools |
FAQ
How many DeepInfra models are there?
137 DeepInfra models are listed across 1 modality on this page. 137 have public per-token pricing.
How is DeepInfra pricing verified?
Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.
Which DeepInfra model is cheapest?
Input pricing on DeepInfra starts at $0.0190 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.
Can I route to DeepInfra via an OpenAI-compatible API?
Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a DeepInfra target, and call DeepInfra models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.
Route any DeepInfra model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.