Skip to content

8,429 prices on 4,154 listings · last collected 4 h ago · 36 flagged changes in 30 days

Every price, as each platform publishes it

A collector reads every public price on six 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 1–82 of 82

Per million output tokens82

PlatformModel · what it coversUSDPlatform’s own wordingSince
Replicatemeta/llama-guard-4-12b$0.2/M outCheapest$0.20 per million output tokens
Replicateibm-granite/granite-3.0-2b-instruct$0.25/M out$0.25 per million output tokens
Replicateibm-granite/granite-3.0-8b-instruct$0.25/M out$0.25 per million output tokens
Replicateibm-granite/granite-3.1-2b-instruct$0.25/M out$0.25 per million output tokens
Replicateibm-granite/granite-3.1-8b-instruct$0.25/M out$0.25 per million output tokens
Replicateibm-granite/granite-3.2-8b-instruct$0.25/M out$0.25 per million output tokens
Replicateibm-granite/granite-3.3-8b-instruct$0.25/M out$0.25 per million output tokens
Replicateibm-granite/granite-4.0-h-small$0.25/M out$0.25 per million output tokens
Replicateibm-granite/granite-4.1-8b$0.25/M out$0.25 per million output tokens
Replicateibm-granite/granite-4.2-8b$0.25/M out$0.25 per million output tokens
Replicateibm-granite/granite-8b-code-instruct-128k$0.25/M out$0.25 per million output tokens
Replicateibm-granite/granite-speech-4.1-2b$0.25/M out$0.25 per million output tokens
Replicateibm-granite/granite-vision-3.3-2b$0.25/M out$0.25 per million output tokens
Replicateibm-granite/granite-vision-4.1-4b$0.25/M out$0.25 per million output tokens
Replicatemeta/llama-2-7b$0.25/M out$0.25 per million output tokens
Replicatemeta/llama-2-7b-chat$0.25/M out$0.25 per million output tokens
Replicatemeta/meta-llama-3-8b$0.25/M out$0.25 per million output tokens
Replicatemeta/meta-llama-3-8b-instruct$0.25/M out$0.25 per million output tokens
Replicatemistralai/mistral-7b-v0.1$0.25/M out$0.25 per million output tokens
Replicateopenai/gpt-oss-20b$0.36/M out$0.36 per million output tokens
Replicateopenai/gpt-5-nano$0.4/M out$0.40 per million output tokens
Replicateopenai/gpt-5-structuredgpt-5-nano$0.4/M out$0.40 per million output tokens (gpt-5-nano)
Replicateibm-granite/granite-20b-code-instruct-8k$0.5/M out$0.50 per million output tokens
Replicatemeta/llama-2-13b$0.5/M out$0.50 per million output tokens
Replicatemeta/llama-2-13b-chat$0.5/M out$0.50 per million output tokens
Replicateopenai/gpt-4o-mini$0.6/M out$0.60 per million output tokens
Replicatemeta/llama-4-scout-instruct$0.65/M out$0.65 per million output tokens
Replicateopenai/gpt-oss-120b$0.72/M out$0.72 per million output tokens
Replicatemeta/llama-4-maverick-instruct$0.95/M out$0.95 per million output tokens
Replicateqwen/qwen3-235b-a22b-instruct-2507$1.06/M out$1.06 per million output tokens
Replicateqwen/qwen3-7-plus256000$1.101/M out$1.101 per million output tokens (,256000)
Replicatedeepseek-ai/deepseek-v3$1.45/M out$1.45 per million output tokens
Replicateopenai/gpt-4.1-mini$1.6/M out$1.60 per million output tokens
Replicateopenai/gpt-5-mini$2/M out$2 per million output tokens
Replicateopenai/gpt-5-structuredgpt-5-mini$2/M out$2 per million output tokens (gpt-5-mini)
Replicatedeepseek-ai/deepseek-v3.1$2.016/M out$2.016 per million output tokens
Replicateperceptron-ai-inc/isaac-0.1$2.17/M out$2.17 per million output tokens
Replicategoogle/gemini-2.5-flash$2.5/M out$2.50 per million output tokens
Replicatemoonshotai/kimi-k2-thinking$2.7/M out$2.70 per million output tokens
Replicatemeta/llama-2-70b$2.75/M out$2.75 per million output tokens
Replicatemeta/llama-2-70b-chat$2.75/M out$2.75 per million output tokens
Replicatemeta/meta-llama-3-70b$2.75/M out$2.75 per million output tokens
Replicatemeta/meta-llama-3-70b-instruct$2.75/M out$2.75 per million output tokens
Replicategoogle/gemini-3-flash$3/M out$3 per million output tokens
Replicateqwen/qwen3-7-plus256000$3.301/M out$3.301 per million output tokens (256000,)
Replicatemoonshotai/kimi-k2.5$3.6/M out$3.60 per million output tokens
Replicatemoonshotai/kimi-k2.6$4/M out$4 per million output tokens
Replicateibm-granite/granite-speech-3.3-8b$4.9/M out$4.90 per million output tokens
Replicateanthropic/claude-3.5-haiku$5/M out$5 per million output tokens
Replicateanthropic/claude-4.5-haiku$5/M out$5 per million output tokens
Replicateopenai/gpt-4o-mini-transcribe$5/M out$5 per million output tokens
Replicategoogle/gemini-3.8-flash-lite-tts$6/M out$6 per million output tokens
Replicateopenai/gpt-5.6-luna$6/M out$6 per million output tokens
Replicateopenai/gpt-4.1$8/M out$8 per million output tokens
Replicategoogle/gemini-3.5-flash$9/M out$9 per million output tokens
Replicategoogle/gemini-3.8-flash-tts$9/M out$9 per million output tokens
Replicateanthropic/claude-sonnet-5$10/M out$0.01 per thousand output tokens
Replicatedeepseek-ai/deepseek-r1$10/M out$0.01 per thousand output tokens
Replicateopenai/gpt-4o$10/M out$0.01 per thousand output tokens
Replicateopenai/gpt-4o-transcribe$10/M out$0.01 per thousand output tokens
Replicateopenai/gpt-5$10/M out$0.01 per thousand output tokens
Replicateopenai/gpt-5-structuredgpt-5$10/M out$0.01 per thousand output tokens (gpt-5)
Replicateopenai/gpt-5.1$10/M out$0.01 per thousand output tokens
Replicateopenai/gpt-5.6-sol$10/M out$0.01 per thousand output tokens
Replicatesourceful/riverflow-v2.5-fast$10/M out$0.01 per thousand output tokens
Replicatesourceful/riverflow-v2.5-pro$10/M out$0.01 per thousand output tokens
Replicategoogle/gemini-3-pro200000$12/M out$0.012 per thousand output tokens (,200000)
Replicategoogle/gemini-3.1-pro200000$12/M out$0.012 per thousand output tokens (,200000)
Replicateopenai/gpt-5.2$14/M out$0.014 per thousand output tokens
Replicateanthropic/claude-4.5-sonnet$15/M out$0.015 per thousand output tokens
Replicateanthropic/claude-sonnet-4.6$15/M out$0.015 per thousand output tokens
Replicateopenai/gpt-5.4$15/M out$0.015 per thousand output tokens
Replicateopenai/gpt-5.6-terra$15/M out$0.015 per thousand output tokens
Replicategoogle/gemini-3-pro200000$18/M out$0.018 per thousand output tokens (200000,)
Replicategoogle/gemini-3.1-pro200000$18/M out$0.018 per thousand output tokens (200000,)
Replicateanthropic/claude-opus-5.5$20/M out$0.02 per thousand output tokens
Replicatesnowflake/snowflake-arctic-instruct$20/M out$0.02 per thousand output tokens
Replicateanthropic/claude-opus-4.6$25/M out$0.025 per thousand output tokens
Replicateanthropic/claude-opus-4.7$25/M out$0.025 per thousand output tokens
Replicategoogle/gemini-3.1-flash-tts$40/M out$0.04 per thousand output tokens
Replicateanthropic/claude-fable-5$50/M out$0.05 per thousand output tokens
Replicateopenai/gpt-5-pro$120/M out$0.12 per thousand output tokens