modelbenchmark.io

Dollars per million tokens

AI model pricing comparison

Input, output and cache-read in US dollars per million tokens. Blended is a 3:1 input mix. It is not a billed rate. Cost a workload or see what prompt caching saves.

Price
View

2,274 models

Cerebras-Llama-4-Scout-17B-16E-InstructMetafreefree—free128K
Gemma 4 31B IT (free)Googlefreefree$0.05free262K
Kimi K2Kimifreefree$0.40free128K
MiMo-V2.5-Pro—freefreefreefree1M
Llama 3.2 3b InstructMeta$0.0306$0.0493$0.0153$0.0353131K
gpt-oss-20bOpenAI$0.04$0.15$0.02$0.0675128K
GPT 5 NanoOpenAI$0.05$0.40$0.005$0.1375400K
Qwen3.5 9BAlibaba$0.05$0.15$0.025$0.075256K
Llama 3.1 8b InstructMeta$0.0544$0.085$0.0272$0.062131K
GPT-5.6 LunaOpenAI$0.06$0.37$0.02$0.13751.1M
Tencent Hy3—$0.066$0.26$0.029$0.1145262K
GLM 4.7 Flash ThinkingZhipu$0.07$0.40$0.035$0.1525200K
GLM-5.3-FlashZhipu$0.075$0.025$0.015$0.06251M
DeepSeek V4 FlashDeepSeek$0.098$0.196$0.028$0.12251M
Gemini 2.5 Flash LiteGoogle$0.10$0.40$0.01$0.1751M
GPT 4.1 NanoOpenAI$0.10$0.40$0.025$0.1751M
Mistral Small 3.2 (Mistral AI)Mistral$0.10$0.30$0.165$0.15128K
Qwen3 30B A3BAlibaba$0.10$0.30$0.05$0.1540K
Qwen3 32BAlibaba$0.10$0.30$0.05$0.1540K
Stepfun/Step-3.5 Flash—$0.10$0.30$0.05$0.1564K
Gemma 4 26B A4BGoogle$0.12$0.38$0.06$0.185262K
GLM 4.5 AirZhipu$0.12$0.80$0.06$0.29131K
Qwen3 235B A22B Thinking 2507Alibaba$0.13$0.60$0.055$0.2475262K
Qwen3.8 FlashAlibaba$0.14$0.42$0.016$0.21992K
GPT-4o miniOpenAI$0.15$0.60$0.075$0.2625128K
Qwen3 Next 80B A3B InstructAlibaba$0.15$0.65$0.075$0.275131K
Qwen3 Next 80B A3B ThinkingAlibaba$0.15$0.65$0.075$0.275131K
Qwen3.8 27BAlibaba$0.15$0.70$0.04$0.2875262K
Minimax/Minimax-M2MiniMax$0.17$1.53$0.085$0.51200K
Qwen3.6 FlashAlibaba$0.19$1.16$0.02$0.4325992K
Step 3.7 Flash—$0.19$1.14$0.03$0.4275262K
DeepSeek-V3DeepSeek$0.20$0.77$0.135$0.3425128K
DeepSeek-V3.1DeepSeek$0.20$0.70$0.10$0.325128K
GPT 5.4 NanoOpenAI$0.20$1.25$0.02$0.4625400K
Qwen3 Coder NextAlibaba$0.20$1.50$0.10$0.525262K
X-Ai/Grok 4.1 Fast Non ReasoningxAI$0.20$0.50$0.05$0.2752M
Z-Ai/GLM 4.7Zhipu$0.20$0.80$0.10$0.35200K
Qwen3.6 27B ThinkingAlibaba$0.203$2.24$0.1015$0.7123260K
DeepSeek V3.2DeepSeek$0.2174$0.326$0.06$0.2445128K
Qwen3.5 35B A3BAlibaba$0.225$1.80$0.1125$0.6188260K
GPT OSS 120BOpenAI$0.228$0.798$2.00$0.3705131K
Gemini 3.1 Flash LiteGoogle$0.25$1.50$0.025$0.56251M
GPT 5 MiniOpenAI$0.25$2.00$0.025$0.6875400K
GPT 5.1 Codex MiniOpenAI$0.25$2.00$0.025$0.6875400K
Qwen3 Coder 480B A35B InstructAlibaba$0.25$1.00$0.022$0.4375262K
DeepSeek V4.1 FlashDeepSeek$0.2556$1.2778$0.0128$0.51111M
Qwen3.5 27BAlibaba$0.27$2.16$0.135$0.7425260K
DeepSeek V3.2 ExpDeepSeek$0.28$0.42$0.14$0.315164K
Qwen3-Coder 30B-A3B InstructAlibaba$0.285$1.083$0.05$0.4845128K
Codestral 2508Mistral$0.30$0.90$0.15$0.45256K
Gemini 2.5 FlashGoogle$0.30$2.50$0.03$0.851M
Gemini 3.5 Flash LiteGoogle$0.30$2.50$0.03$0.851M
GLM 4.5Zhipu$0.30$1.30$0.15$0.55131K
MiniMax M3 ThinkingMiniMax$0.30$1.20$0.06$0.525512K
MiniMax-M2.5MiniMax$0.30$1.20$0.03$0.525205K
Moonshotai/Kimi-K2.5Alibaba$0.30$1.90$0.15$0.70256K
Qwen 3 235B A22BAlibaba$0.30$0.50$0.15$0.35128K
Qwen3 Coder FlashAlibaba$0.30$1.50$0.15$0.60128K
Qwen3 VL 235B A22B InstructAlibaba$0.30$1.20$0.15$0.525131K
MiniMax M2.7MiniMax$0.315$1.26$0.1575$0.5513205K
Qwen 3.6 PlusAlibaba$0.325$1.95$0.0325$0.7312992K
Minimax/Minimax-M2.1MiniMax$0.33$1.32$0.165$0.5775205K
Gemma 3 27BGoogle$0.342$0.684$0.1496$0.427540K
Qwen3.6 35B-A3BAlibaba$0.342$2.052$0.056$0.7695262K
Z-AI/GLM 4.6Zhipu$0.35$1.40$0.175$0.6125200K
Llama 4 Maverick 17B 128E Instruct FP8Meta$0.371$1.484$0.1275$0.6492131K
DeepSeek-R1DeepSeek$0.40$1.70$0.20$0.725128K
GPT 4.1 MiniOpenAI$0.40$1.60$0.10$0.701M
MiMo-V2.5—$0.40$2.00$0.08$0.801M
Qwen3.5 397B-A17BAlibaba$0.40$2.65$0.20$0.9625262K
Qwen3.5 Plus ThinkingAlibaba$0.40$2.40$0.04$0.90984K
DeepSeek V4 ProDeepSeek$0.435$0.87$0.04$0.54371M
Qwen3.5 122B A10B ThinkingAlibaba$0.437$3.496$0.1038$1.2018131K
DeepSeek V4 Flash Vision ExpDeepSeek$0.44$1.32$0.014$0.661M
Gemini 3 Flash (Preview)Google$0.50$3.00$0.05$1.1251M
GPT-3.5 TurboOpenAI$0.50$1.50free$0.7516K
Qwen3 VL 235B A22B ThinkingAlibaba$0.50$6.00$0.25$1.875131K
GLM 4.5V ThinkingZhipu$0.60$1.80$0.30$0.9066K
Kimi K2 ThinkingKimi$0.60$2.50$0.15$1.075256K
MiniMax-M2.7-highspeedMiniMax$0.60$2.40$0.06$1.05205K
Gemini 3.6 FlashGoogle$0.75$3.75$0.075$1.501M
Gemini 3.7 FlashGoogle$0.75$3.75$0.075$1.501M
Gemini 3.8 FlashGoogle$0.75$3.75$0.075$1.501M
GPT 5.4 MiniOpenAI$0.75$4.50$0.075$1.6875400K
Qwen3.7 PlusAlibaba$0.768$3.072$0.08$1.3441M
GLM-5Alibaba$0.89$3.2647$0.2226$1.4837205K
Kimi K2.7 CodeKimi$0.9006$4.389$0.1881$1.7727262K
Kimi K2.6Kimi$0.95$4.00$0.16$1.7125262K
DeepSeek R1 Distill Llama 70BDeepSeek$0.99$0.99—$0.9933K
Claude Haiku 4.5 ThinkingAnthropic$1.00$5.00$0.10$2.00200K
Grok Build 0.1xAI$1.00$2.00$0.20$1.25256K
Inkling ThinkingDatabricks$1.00$4.05$0.17$1.76251M
Qwen3 Coder PlusAlibaba$1.00$5.00$0.50$2.00128K
Qwen3 235B A22B Instruct 2507Alibaba$1.026$3.078$0.065$1.539262K
OpenAI o3-miniOpenAI$1.10$4.40$0.55$1.925200K
OpenAI o4-miniOpenAI$1.10$4.40$0.55$1.925200K
GLM 5 TurboZhipu$1.20$4.00$0.24$1.90203K
GLM 5V Turbo ThinkingZhipu$1.20$4.00$0.24$1.90203K
Qwen3 Max PreviewAlibaba$1.2002$6.001$0.6001$2.4004256K
Gemini 2.5 ProGoogle$1.25$10.00$0.125$3.43751M
GPT 5.1 CodexOpenAI$1.25$10.00$0.125$3.4375400K
GPT-5.1 (2025-11-13)OpenAI$1.25$10.00$0.125$3.4375400K
Grok 4.3xAI$1.25$2.50$0.20$1.56251M
OpenAI/GPT-5OpenAI$1.25$10.00$0.125$3.4375400K
Llama-3.3-70B-InstructMeta$1.254$1.254$0.025$1.254100K
GLM-5.1Zhipu$1.40$4.40$0.26$2.15200K
GLM-5.2Alibaba$1.40$4.40$0.26$2.151M
GLM-5.3Zhipu$1.40$4.40$0.26$2.151M
Gemini 3.5 FlashGoogle$1.50$9.00$0.15$3.3751M
Gemini-3-ProGoogle$1.60$9.60$0.16$3.601M
GPT 5.2 CodexOpenAI$1.75$14.00$0.175$4.8125400K
GPT 5.3 CodexOpenAI$1.75$14.00$0.175$4.8125400K
OpenAI/GPT-5.2OpenAI$1.75$14.00$0.175$4.8125400K
Claude Sonnet 5 ThinkingAnthropic$2.00$10.00$0.20$4.001M
Gemini 3 Pro ImageGoogle$2.00$12.00$0.20$4.5066K
Gemini 3.1 Pro (Preview)Google$2.00$12.00$0.20$4.501M
GPT 4.1OpenAI$2.00$8.00$0.50$3.501M
GPT 5.6 TerraOpenAI$2.00$12.00$0.20$4.501.1M
GPT-5.6 SolOpenAI$2.00$10.00$0.20$4.001.1M
Grok 4.5xAI$2.00$6.00$0.50$3.00500K
Grok 4.6xAI$2.00$6.00$0.50$3.00500K
OpenAI o3OpenAI$2.00$8.00$1.00$3.50200K
Qwen3.8 Max ThinkingAlibaba$2.00$6.00$0.25$3.00991K
Mistral Large 2411Mistral$2.006$6.001$0.20$3.0047128K
GPT 5.1 Codex MaxOpenAI$2.50$20.00$0.25$6.875400K
GPT 5.4OpenAI$2.50$15.00$0.25$5.6251.1M
GPT-4o (2024-08-06)OpenAI$2.50$10.00$1.25$4.375128K
Claude 3.7 SonnetAnthropic$3.00$15.00$0.30$6.00200K
Claude 4 Sonnet ThinkingAnthropic$3.00$15.00$0.30$6.001M
Claude Sonnet 4.5Anthropic$3.00$15.00$0.30$6.00200K
Claude Sonnet 4.6Anthropic$3.00$15.00$0.30$6.001M
Kimi K3Alibaba$3.00$15.00$0.30$6.001M
Qwen3.7 MaxAlibaba$3.00$9.00$0.50$4.501M
Claude 4.5 OpusAnthropic$5.00$25.00$0.50$10.00200K
Claude 4.6 Opus ThinkingAnthropic$5.00$25.00$0.50$10.001M
Claude 4.7 OpusAnthropic$5.00$25.00$0.50$10.001M
Claude Opus 4.8Anthropic$5.00$25.00$0.50$10.001M
Claude Opus 5Anthropic$5.00$25.00$0.50$10.001M
GPT 5.5OpenAI$5.00$30.00$0.50$11.251.1M
Claude Fable 5Anthropic$10.00$50.00$1.00$20.001M
Claude Fable 5.1Anthropic$10.00$50.00$0.25$20.001M
GPT 6 AstraOpenAI$10.00$50.00$1.00$20.001.1M
GPT-4 TurboOpenAI$10.00$30.00—$15.00128K
Claude 4 Opus ThinkingAnthropic$15.00$75.00$1.50$30.00200K
Claude 4.1 OpusAnthropic$15.00$75.00$1.50$30.00200K
GPT 5 ProOpenAI$15.00$120.00$1.50$41.25400K
OpenAI o1OpenAI$15.00$60.00$7.50$26.25200K
GPT-5.4 ProOpenAI$30.00$180.00$3.00$67.501.1M
GPT-5.5 ProOpenAI$30.00$180.00$3.00$67.501.1M
Show all 2,274

Common questions

How do you compare AI model prices?
Each row is one model. Input and output are US dollars per million tokens. Blended uses a 3:1 input to output mix. Cache-read is the listed prefix-cache price when a host publishes one.
What is a blended token price?
Blended is (3 × input + 1 × output) / 4. That mix matches a typical chat turn. It is a presentation choice. It is not a billed rate.
Why do two hosts list different prices for the same model?
A price belongs to a model and a host. This table shows the canonical listing. Open the model page to see every host.