tokenstat
tokenstat
Router

DeepInfra

Published API prices under DeepInfra in the merged catalog. Free and $0 offers are omitted. A router can charge a different price than the lab that trained the model.

100 models · as of · All models · AI plans

Showing 48 of 100 · page 1 / 3

ModelInputOutputContextOffers
DeepSeek: V4.1 Flashdeepseek/deepseek-v4.1-flash
scoresreasoningtools
$0.2$0.61.1M3
Z.ai: GLM-5.3zai/glm-5.3
scoresreasoningtools
$0.9$41.0M1
DeepSeek: V4 Pro 0813deepseek/deepseek-v4-pro-0813
scoresreasoningtools
$1.30$2.601.0M2
Qwen3.8 Maxqwen/qwen3.8-max
scoresreasoningtools
$1.65$4.951.0M1
Moonshot: Kimi K3moonshot/kimi-k3
scoresreasoningtools
$2.85$14.251.1M1
Z.ai: GLM-5.2zai/glm-5.2
scoresreasoningtools
$0.75$2.401.0M1
Anthropic: Claude Fable 5anthropic/claude-fable-5
scoresreasoningtools
$10$501M1
Alibaba: Qwen3 MaxQwen/Qwen3-Max
reasoningtools
$1.20$6262K2
Qwen3.8 27BQwen/Qwen3.8-27B
scoresreasoningtools
$0.2$2.501.1M1
DeepSeek: V4 Flashdeepseek/deepseek-v4-flash
scoresreasoningtools
$0.08$0.181.1M2
DeepSeek: V4 Prodeepseek/deepseek-v4-pro
scoresreasoningtools
$1.30$2.601.1M2
DeepSeek: V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017
scoresreasoningtools
$0.2$0.61.1M3
MiMo V2.6 Flashtencent/mimo-v2.6-flash
scoresreasoningtools
$0.14$0.281.1M2
MiMo V2.6 Protencent/mimo-v2.6-pro
scoresreasoningtools
$0.43$0.871.1M2
Mistral: GLM-5.3-Flashmistral/zai-glm-5-3-flash
scoresreasoningtools
$0.15$0.51.0M1
Qwen3.8 2.4T A95BQwen/Qwen3.8-2.4T-A95B
scoresreasoningtools
$2$61.0M1
DeepSeek: V4 Flash 0731deepseek/deepseek-v4-flash-0731
scoresreasoningtools
$0.06$0.181.0M2
DeepSeek: V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp
scoresreasoningtools
$0.44$1.321.0M1
Qwen3.8 FlashQwen/Qwen3.8-Flash
reasoningtools
$0.113$0.3821.0M1
NVIDIA: Step 5 Previewnvidia/step-5-preview
scoresreasoningtools
$1$2.701.0M2
Hy4 previewtencent/Hy4-preview
scoresreasoningtools
$0.834$2.501.0M2
Qwen3.7 MaxQwen/Qwen3.7-Max
scoresreasoningtools
$2.50$7.501.1M1
Qwen3.6 35B-A3BQwen/Qwen3.6-35B-A3B
scoresreasoningtools
$0.1$0.951.0M1
MiniMax: M3minimax/MiniMax-M3
scoresreasoningtools
$0.28$1.101.0M1
NVIDIA: Nemotron Ultranvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
scoresreasoningtools
$0.5$2.201.0M1
Inkling Thinkingtogether_ai/thinkingmachines/Inkling
scoresreasoningtools
$0.95$4.051.0M2
Moonshot: Kimi K2.7 Codemoonshot/kimi-k2.7-code
scoresreasoningtools
$0.68$3.40271K1
Hy3 (Free)tencent/Hy3
reasoningtools
$0.13$0.53262K2
Meta: Muse Glimmer 30Bmeta/muse-glimmer-30b
scoresreasoningtools
$0.3$1.20131K2
NVIDIA: Nemotron 3 Super 120B A12Bnvidia/NVIDIA-Nemotron-3-Super-120B-A12B
scoresreasoningtools
$0.085$0.41.0M1
Moonshot: Kimi K2.5moonshot/kimi-k2.5
scoresreasoningtools
$0.45$2.25262K2
Moonshot: Kimi K2.6moonshot/kimi-k2.6
scoresreasoningtools
$0.75$3.50262K1
NVIDIA: Nemotron 3 Nano Omni 30B A3B Reasoningnvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428
scoresreasoningtools
$0.2$0.8262K1
Qwen3 Coder 480B A35B Instruct TurboQwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
tools
$0.3$1262K1
Qwen3.5 122B-A10BQwen/Qwen3.5-122B-A10B
scoresreasoningtools
$0.29$2.40262K1
Qwen3.5 27BQwen/Qwen3.5-27B
scoresreasoningtools
$0.26$2.60262K1
Qwen3.5 35B-A3BQwen/Qwen3.5-35B-A3B
scoresreasoningtools
$0.14$1262K1
Qwen3.5 397B-A17BQwen/Qwen3.5-397B-A17B
scoresreasoningtools
$0.45$3262K1
Qwen3.5 9BQwen/Qwen3.5-9B
scoresreasoningtools
$0.1$0.15262K2
Qwen3.6 27BQwen/Qwen3.6-27B
scoresreasoningtools
$0.32$3.20262K1
Google: Gemma 4 26B A4Bgemini/gemma-4-26b-a4b-it
scoresreasoningtools
$0.07$0.34262K2
Google: Gemma 4 31Bgemini/gemma-4-31b-it
scoresreasoningtools
$0.2$0.4262K2
MiniMax: M2.7MiniMax/MiniMax-M2.7
scoresreasoningtools
$0.25$1262K1
Alibaba: GLM-5alibaba/glm-5
scoresreasoningtools
$0.6$2.08205K1
Google: Gemma 4 E4B ITgoogle/gemma-4-E4B-it
reasoningtools
$0.02$0.1131K1
NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B
scoresreasoningtools
$0.05$0.2262K2
MiniMax: M2.5minimax/MiniMax-M2.5
scoresreasoningtools
$0.15$1.15229K1
Z.ai: GLM-5.1zai/GLM-5.1
scoresreasoningtools
$1.05$3.50205K1

Bring your provider usage into one workspace

Run agents in local project folders, open another computer when you need it, and track the sessions and tokens your coding tools record. See the published API price of work your subscriptions covered.