Skip to content
这个页面有中文版。
切换到中文
API Pricing

11,195 prices on 4,854 listings · last collected 2 h ago · 442 flagged changes in 30 days

Every price, as each platform publishes it

A collector reads every public price on ten platforms, daily by default, and keeps the page it read. Nothing is typed in by hand. Search a model to see who charges least, per unit, right now.

Showing 101–154 of 154

Per million output tokens54

PlatformModel · what it coversUSDPlatform’s own wordingSince
ReplicatePlatform-hostedmeta/llama-2-13b-chat$0.5/M out$0.50 per million output tokens
ReplicateOfficial partneropenai/gpt-4o-mini$0.6/M out$0.60 per million output tokens
ReplicatePlatform-hostedmeta/llama-4-scout-instruct$0.65/M out$0.65 per million output tokens
ReplicatePlatform-hostedopenai/gpt-oss-120b$0.72/M out$0.72 per million output tokens
ReplicatePlatform-hostedmeta/llama-4-maverick-instruct$0.95/M out$0.95 per million output tokens
ReplicatePlatform-hostedqwen/qwen3-235b-a22b-instruct-2507$1.06/M out$1.06 per million output tokens
ReplicateOfficial partnerqwen/qwen3-7-plus≤ 256 · 000$1.101/M out$1.101 per million output tokens (input token ≤ 256,000)
ReplicatePlatform-hosteddeepseek-ai/deepseek-v3$1.45/M out$1.45 per million output tokens
ReplicateOfficial partneropenai/gpt-4.1-mini$1.6/M out$1.60 per million output tokens
ReplicateOfficial partneropenai/gpt-5-mini$2/M out$2 per million output tokens
ReplicateOfficial partneropenai/gpt-5-structuredgpt-5-mini$2/M out$2 per million output tokens (gpt-5-mini)
ReplicateOfficial partnerdeepseek-ai/deepseek-v3.1$2.016/M out$2.016 per million output tokens
ReplicatePlatform-hostedperceptron-ai-inc/isaac-0.1$2.17/M out$2.17 per million output tokens
ReplicateOfficial partnergoogle/gemini-2.5-flash$2.5/M out$2.50 per million output tokens
ReplicateOfficial partnermoonshotai/kimi-k2-thinking$2.7/M out$2.70 per million output tokens
ReplicatePlatform-hostedmeta/llama-2-70b$2.75/M out$2.75 per million output tokens
ReplicatePlatform-hostedmeta/llama-2-70b-chat$2.75/M out$2.75 per million output tokens
ReplicatePlatform-hostedmeta/meta-llama-3-70b$2.75/M out$2.75 per million output tokens
ReplicatePlatform-hostedmeta/meta-llama-3-70b-instruct$2.75/M out$2.75 per million output tokens
ReplicateOfficial partnergoogle/gemini-3-flash$3/M out$3 per million output tokens
ReplicateOfficial partnerqwen/qwen3-7-plus> 256 · 000$3.301/M out$3.301 per million output tokens (input token > 256,000)
ReplicateOfficial partnermoonshotai/kimi-k2.5$3.6/M out$3.60 per million output tokens
ReplicateOfficial partnermoonshotai/kimi-k2.6$4/M out$4 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-speech-3.3-8b$4.9/M out$4.90 per million output tokens
ReplicateOfficial partneranthropic/claude-4.5-haiku$5/M out$5 per million output tokens
ReplicateOfficial partneropenai/gpt-4o-mini-transcribe$5/M out$5 per million output tokens
ReplicateOfficial partneropenai/gpt-5.6-luna$6/M out$6 per million output tokens
ReplicateOfficial partneropenai/gpt-4.1$8/M out$8 per million output tokens
ReplicateOfficial partnergoogle/gemini-3.5-flash$9/M out$9 per million output tokens
ReplicateOfficial partneranthropic/claude-sonnet-5$10/M out$0.01 per thousand output tokens
ReplicatePlatform-hosteddeepseek-ai/deepseek-r1$10/M out$0.01 per thousand output tokens
ReplicateOfficial partnergoogle/gemini-4-carbon$10/M out$0.01 per thousand output tokens
ReplicateOfficial partneropenai/gpt-4o$10/M out$0.01 per thousand output tokens
ReplicateOfficial partneropenai/gpt-4o-transcribe$10/M out$0.01 per thousand output tokens
ReplicateOfficial partneropenai/gpt-5$10/M out$0.01 per thousand output tokens
ReplicateOfficial partneropenai/gpt-5-structuredgpt-5$10/M out$0.01 per thousand output tokens (gpt-5)
ReplicateOfficial partneropenai/gpt-5.1$10/M out$0.01 per thousand output tokens
ReplicateOfficial partneropenai/gpt-5.6-sol$10/M out$0.01 per thousand output tokens
ReplicateOfficial partnergoogle/gemini-3-pro≤ 200 · 000$12/M out$0.012 per thousand output tokens (input token ≤ 200,000)
ReplicateOfficial partnergoogle/gemini-3.1-pro≤ 200 · 000$12/M out$0.012 per thousand output tokens (input token ≤ 200,000)
ReplicateOfficial partneropenai/gpt-5.2$14/M out$0.014 per thousand output tokens
ReplicateOfficial partneranthropic/claude-4.5-sonnet$15/M out$0.015 per thousand output tokens
ReplicateOfficial partneranthropic/claude-sonnet-4.6$15/M out$0.015 per thousand output tokens
ReplicateOfficial partneropenai/gpt-5.4$15/M out$0.015 per thousand output tokens
ReplicateOfficial partneropenai/gpt-5.6-terra$15/M out$0.015 per thousand output tokens
ReplicateOfficial partnergoogle/gemini-3-pro> 200 · 000$18/M out$0.018 per thousand output tokens (input token > 200,000)
ReplicateOfficial partnergoogle/gemini-3.1-pro> 200 · 000$18/M out$0.018 per thousand output tokens (input token > 200,000)
ReplicateOfficial partneranthropic/claude-opus-5.5$20/M out$0.02 per thousand output tokens
ReplicateOfficial partnersnowflake/snowflake-arctic-instruct$20/M out$0.02 per thousand output tokens
ReplicateOfficial partneranthropic/claude-opus-4.6$25/M out$0.025 per thousand output tokens
ReplicateOfficial partneranthropic/claude-opus-4.7$25/M out$0.025 per thousand output tokens
ReplicateOfficial partneranthropic/claude-fable-5.2$40/M out$0.04 per thousand output tokens
ReplicateOfficial partneranthropic/claude-fable-5$50/M out$0.05 per thousand output tokens
ReplicateOfficial partneropenai/gpt-5-pro$120/M out$0.12 per thousand output tokens