tokenstat
tokenstat
Router

DeepInfra

Paid list rates under DeepInfra in the merged catalog. Free and $0 offers are omitted. Router rates are not the same as first-party list prices.

47 models · as of · All models · Plans

Showing 47 of 47

ModelInputOutputContextOffers
Deepseek V4 Flash 0731deepseek-ai/DeepSeek-V4-Flash-0731
scoresreasoningtools
$0.09$0.181.0M1
MiMo V2.5xiaomi/mimo-v2.5
scoresreasoningtools
$0.4$21.1M1
MiMo-V2.5-Procrof/mimo-v2.5-pro
scoresreasoningtools
$1$31.1M1
DeepSeek V4 Prodeepseek-ai/DeepSeek-V4-Pro
scoresreasoningtools
$1.30$2.601.0M1
GLM 5.2zai-org/GLM-5.2
scoresreasoningtools
$0.75$2.401.0M1
DeepSeek V4 Flashdeepseek-ai/DeepSeek-V4-Flash
reasoningtools
$0.09$0.181.0M1
Kimi K3moonshotai/kimi-k3
scoresreasoningtools
$2.70$13.501.0M1
MiniMax M3minimax/minimax-m3
scoresreasoningtools
$0.3$1.201.0M1
Inklingvenice/inkling
scoresreasoningtools
$0.95$4.051.0M1
Inkling Smallthinkingmachines/inkling-small
scoresreasoningtools
$0.45$1.201.0M1
Qwen3.7 Maxqwen/qwen3.7-max
scoresreasoningtools
$2.50$7.501M1
Kimi K2.6moonshotai/Kimi-K2.6
scoresreasoningtools
$0.75$3.50262K1
Kimi K2.7 Codemoonshotai/kimi-k2.7-code
scoresreasoningtools
$0.74$3.50262K1
Hy3cortecs/hy3
reasoningtools
$0.14$0.58262K1
Kimi K2.5moonshotai/Kimi-K2.5
scoresreasoningtools
$0.45$2.25262K1
Qwen3 Coder 480B A35B Instruct TurboQwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
tools
$0.3$1262K1
Qwen3.5 397B A17BQwen/Qwen3.5-397B-A17B
scoresreasoningtools
$0.45$3262K1
Qwen3.5 9BQwen/Qwen3.5-9B
scoresreasoningtools
$0.1$0.15262K1
Qwen3.5-122B-A10BQwen/Qwen3.5-122B-A10B
scoresreasoningtools
$0.29$2.40262K1
Qwen3.5-27BQwen/Qwen3.5-27B
reasoningtools
$0.26$2.60262K1
Qwen3.5-35B-A3BQwen/Qwen3.5-35B-A3B
scoresreasoningtools
$0.14$1262K1
Qwen3.6 27BQwen/Qwen3.6-27B
scoresreasoningtools
$0.32$3.20262K1
Qwen3.6 35B A3BQwen/Qwen3.6-35B-A3B
scoresreasoningtools
$0.1$0.95262K1
Google: Gemma 4 26B A4B ITgoogle/gemma-4-26B-A4B-it
scoresreasoningtools
$0.07$0.34262K1
Google: Gemma 4 31Bgoogle/gemma-4-31b-it
scoresreasoningtools
$0.13$0.38262K1
Nemotron 3 Nano Omni 30B A3B Reasoningnvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning
reasoningtools
$0.2$0.8262K1
Step 3.7 Flashstepfun/step-3.7-flash
scoresreasoningtools
$0.2$1.15262K1
GLM-5zai-org/GLM-5
reasoningtools
$0.6$2.08205K1
GLM-5.1zai-org/GLM-5.1
scoresreasoningtools
$1.05$3.50205K1
MiniMax M2.7MiniMax/MiniMax-M2.7
scoresreasoningtools
$0.25$1205K1
Nemotron 3 Nano 30B A3Bnvidia/Nemotron-3-Nano-30B-A3B
scoresreasoningtools
$0.05$0.2262K1
MiniMax-M2.5MiniMaxAI/MiniMax-M2.5
reasoningtools
$0.15$1.15205K1
GLM-4.7-Flashzai-org/GLM-4.7-Flash
reasoningtools
$0.06$0.4203K1
Gemma 4 E4B ITgoogle/gemma-4-E4B-it
reasoningtools
$0.02$0.1131K1
Qwen3 MaxQwen/Qwen3-Max
reasoningtools
$1.20$6262K1
GLM-4.6zai-org/GLM-4.6
scoresreasoningtools
$0.5$2205K1
GLM-4.7zai-org/GLM-4.7
scoresreasoningtools
$0.4$1.75205K1
Qwen3 Next 80B A3B InstructQwen/Qwen3-Next-80B-A3B-Instruct
tools
$0.09$1.10262K1
Llama 4 Maverick 17B Instructmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
tools
$0.2$0.81.0M1
Llama 4 Scout 17Bmeta-llama/Llama-4-Scout-17B-16E-Instruct
scorestools
$0.1$0.3328K1
DeepSeek V3.2deepseek-ai/DeepSeek-V3.2
scoresreasoningtools
$0.26$0.38164K1
DeepSeek-R1-0528deepseek-ai/DeepSeek-R1-0528
reasoningtools
$0.5$2.15164K1
Llama 3.3 Nemotron Super 49B v1.5nvidia/Llama-3.3-Nemotron-Super-49B-v1.5
reasoningtools
$0.4$0.4131K1
OpenAI: GPT OSS 120Bopenai/gpt-oss-120b
scoresreasoningtools
$0.037$0.17131K1
OpenAI: GPT OSS 20Bopenai/gpt-oss-20b
scoresreasoningtools
$0.03$0.14131K1
Qwen3 32BQwen/Qwen3-32B
scoresreasoningtools
$0.08$0.28131K1
Meta: Llama 3.3 70B Turbometa-llama/Llama-3.3-70B-Instruct-Turbo
tools
$0.1$0.32131K1

Price this against your own usage

List rates are only half the story. The CLI measures what your coding harnesses actually spent on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash