Contact Contacts
API provider

DeepInfra

What this provider sells and at what price. A price belongs to the offer, not the model: at another provider the same model may cost several times more or less.

98 models with a price
СШАcountry
resold models
official API response price source

Models & prices

Model Developer Input, $/1M Output, $/1M Blended, $/1M
Kimi K3 Moonshot AI (Kimi) $2.7 $13.5 $5.4
GLM 5.2 Zhipu AI / Z.ai $0.93 $3 $1.45
Kimi K2.7 Code Moonshot AI (Kimi) $0.74 $3.5 $1.43
MiniMax M3 MiniMax $0.3 $1.2 $0.53
Qwen3.7 Max Alibaba (Qwen) $2.5 $7.5 $3.75
Nemotron 3 Nano Omni NVIDIA $0.2 $0.8 $0.35
DeepSeek V4 Flash DeepSeek $0.09 $0.18 $0.11
DeepSeek V4 Pro DeepSeek $1.3 $2.6 $1.63
MiMo V2.5 Xiaomi $0.4 $2 $0.8
MiMo V2.5 Pro Xiaomi $1 $3 $1.5
Qwen3.6 27B Alibaba (Qwen) $0.32 $3.2 $1.04
Kimi K2.6 Moonshot AI (Kimi) $0.75 $3.5 $1.44
Qwen3.6 35B-A3B Alibaba (Qwen) $0.1 $0.95 $0.31
Gemma 4 26B A4B IT Google DeepMind $0.07 $0.34 $0.14
Gemma 4 31B Google DeepMind $0.13 $0.38 $0.19
GLM 5.1 Zhipu AI / Z.ai $1.05 $3.5 $1.66
MiniMax M2.7 MiniMax $0.25 $1 $0.44
Qwen3.5 9B Alibaba (Qwen) $0.1 $0.15 $0.11
Qwen3.5 27B deprecated Alibaba (Qwen) $0.26 $2.6 $0.85
Qwen3.5 35B A3B Alibaba (Qwen) $0.14 $1 $0.36
Qwen3.5 122B-A10B Alibaba (Qwen) $0.29 $2.4 $0.82
Qwen3.5 397B-A17B Alibaba (Qwen) $0.45 $3 $1.09
MiniMax M2.5 MiniMax $0.15 $1.15 $0.4
GLM 5 Zhipu AI / Z.ai $0.6 $2.08 $0.97
Kimi K2.5 Moonshot AI (Kimi) $0.45 $2.25 $0.9
Qwen3 32B and another 1 Alibaba (Qwen) $0.08 $0.28 $0.13
Qwen3 Next 80B A3B Thinking Alibaba (Qwen) $0.14 $1.4 $0.46
Qwen 3 Coder 480B Turbo and another 1 Alibaba (Qwen) $0.3 $1 $0.48
GLM 4.7 Flash Zhipu AI / Z.ai $0.06 $0.4 $0.15
Hermes 3 70B Nous Research $0.3 $0.3 $0.3
Mistral: Mistral Small 3 Mistral AI $0.05 $0.08 $0.06
GLM 4.7 Zhipu AI / Z.ai $0.4 $1.75 $0.74
Nemotron 3 Nano 30B A3B NVIDIA $0.05 $0.2 $0.09
Mixtral 8x7B Mistral AI $0.4 $0.4 $0.4
DeepSeek Reasoner DeepSeek $0.7 $2.4 $1.13
DeepSeek V3.2 DeepSeek $0.26 $0.38 $0.29
GLM 4.6 Zhipu AI / Z.ai $0.5 $2 $0.88
Hermes 3 Llama 3.1 405b Nous Research $1 $1 $1
Kimi K2 0905 deprecated Moonshot AI (Kimi) $0.5 $2 $0.88
Qwen3 Max Alibaba (Qwen) $1.2 $6 $2.4
DeepSeek V3.1 DeepSeek $0.27 $1 $0.45
MythoMax 13B Community $0.08 $0.09 $0.08
GPT OSS 120B and another 1 OpenAI $0.04 $0.17 $0.07
GPT OSS 20B and another 1 OpenAI $0.03 $0.14 $0.06
DeepSeek V3.1 Terminus DeepSeek $0.27 $1 $0.45
GLM 4.5 Zhipu AI / Z.ai $0.4 $1.6 $0.7
Llama 3.3 Nemotron Super 49B v1.5 and another 1 Meta AI $0.1 $0.4 $0.18
Qwen3 235B A22B Thinking-2507 deprecated Alibaba (Qwen) $0.3 $2.9 $0.95
Qwen3 Coder 480B A35B Alibaba (Qwen) $0.4 $1.6 $0.7
Qwen3 235B A22B Instruct 2507 Alibaba (Qwen) $0.09 $0.6 $0.22
Kimi K2 Instruct Moonshot AI (Kimi) $0.5 $2 $0.88
Mistral Small 3.2 Mistral AI $0.08 $0.2 $0.11
Gemini 2.5 Flash Google DeepMind $0.3 $2.5 $0.85
Gemini 2.5 Pro Google DeepMind $1.25 $10 $3.44
DeepSeek R1 0528 and another 1 DeepSeek $0.5 $2.15 $0.91
Claude Opus 4 Anthropic $16.5 $82.5 $33
Claude Sonnet 4 Anthropic $3.3 $16.5 $6.6
Qwen 3 235b A22B Alibaba (Qwen) $0.18 $0.54 $0.27
Llama 3.1 Nemotron 70B Instruct Meta AI $0.6 $0.6 $0.6
Qwen: QwQ 32B Alibaba (Qwen) $0.15 $0.4 $0.21
WizardLM-2 8x22B Microsoft $0.48 $0.48 $0.48
Llama 4 Scout 17B 16E Instruct and another 1 Meta AI $0.08 $0.3 $0.14
Llama Guard 4 12B Meta AI $0.18 $0.18 $0.18
Llama 4 Maverick 17b 128e Instruct and another 1 Meta AI $0.15 $0.6 $0.26
DeepSeek Chat 0324 DeepSeek $0.25 $0.88 $0.41
Qwen2.5 VL 32B Instruct Alibaba (Qwen) $0.2 $0.6 $0.3
Gemma 3 12B IT Google DeepMind $0.05 $0.1 $0.06
Gemma 3 27B Google DeepMind $0.09 $0.16 $0.11
Gemma 3 4B IT Google DeepMind $0.04 $0.08 $0.05
DeepSeek R1 (Turbo) DeepSeek $1 $3 $1.5
Qwen3 30B A3B Alibaba (Qwen) $0.08 $0.29 $0.13
DeepSeek R1 Distill Llama 70B DeepSeek $0.2 $0.6 $0.3
Llama Guard 3 8B Meta AI $0.06 $0.06 $0.06
Deepseek R1 Distill Qwen 32B DeepSeek $0.27 $0.27 $0.27
DeepSeek V3 DeepSeek $0.38 $0.89 $0.51
Gemini 2.0 Flash Google DeepMind $0.1 $0.4 $0.18
Phi 4 Microsoft $0.07 $0.14 $0.09
Llama 3.3 70B Euryale Community $0.65 $0.75 $0.68
Llama 3.3 70B Instruct Meta AI $0.23 $0.4 $0.27
Llama 3.3 70B and another 1 Meta AI $0.1 $0.32 $0.16
NVIDIA Nemotron Nano 9B v2 NVIDIA $0.04 $0.16 $0.07
Qwen3 Next 80B A3B Instruct and another 1 Alibaba (Qwen) $0.09 $1.1 $0.34
Llama 3.2 11b Vision Instruct Meta AI $0.05 $0.05 $0.05
Llama 3.2 3B Instruct Meta AI $0.02 $0.02 $0.02
Qwen2.5 72B Instruct Alibaba (Qwen) $0.12 $0.39 $0.19
Qwen2.5 7B Instruct Alibaba (Qwen) $0.04 $0.1 $0.06
Llama 3.1 70B Euryale Community $0.65 $0.75 $0.68
Llama 3.1 70B Meta AI $0.4 $0.4 $0.4
Llama 3.1 8B Meta AI $0.03 $0.05 $0.04
Meta Llama 3.1 8B Instruct Turbo Meta AI $0.02 $0.03 $0.02
Mistral Nemo Mistral AI $0.02 $0.04 $0.03
Meta: Llama 3 8B Instruct Meta AI $0.03 $0.06 $0.04
Qwen 3 14b Alibaba (Qwen) $0.06 $0.24 $0.11
Claude 3.7 Sonnet Latest Anthropic $3.3 $16.5 $6.6
DeepSeek R1 0528 Turbo DeepSeek $1 $3 $1.5
L3 8B Lunaris V1 Turbo Community $0.04 $0.05 $0.04
Llama 3.1 70B Instruct Turbo Meta AI $0.1 $0.28 $0.15
Olmocr 7B 0725 Allen Institute for AI $0.27 $1.5 $0.58

These are this provider’s prices, not the market’s best: the same model may cost differently at another provider. The blended price uses a three-input-tokens-to-one-output scheme — the way to compare models whose output costs several times more than input. Only the base per-token rate counts, without batch or discounted tiers; input and output come from one price list, not two minimums from different ones.