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 3 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.

Platform
All 1,178OpenRouter 0KIE 0Fal 904WaveSpeed 0Replicate 274APIMart 0Runware 0Aiberm 0Tripo 0Meshy 0
Kind
AllVideoImageText3DAudioOtherExact prices only (hide “from”)
Route
All 982Official / partner 707Platform-hosted 274Third-party 0Not disclosed 1
Unit price
All 274Per second of output 94Per video 4Per image 80Per megapixel 20Per million input tokens 32Per million output tokens 34Per thousand characters 3Per second of compute time 4Per run (default parameters) 3

Showing 201–274 of 274

Per million input tokens30

PlatformModel · what it coversUSDPlatform’s own wordingSince
ReplicatePlatform-hostedibm-granite/granite-3.1-8b-instruct$0.03/M inCheapest$0.03 per million input tokens
ReplicatePlatform-hostedibm-granite/granite-3.2-8b-instruct$0.03/M inCheapest$0.03 per million input tokens
ReplicatePlatform-hostedibm-granite/granite-3.3-8b-instruct$0.03/M inCheapest$0.03 per million input tokens
ReplicatePlatform-hostedibm-granite/granite-speech-4.1-2b$0.03/M inCheapest$0.03 per million input tokens
ReplicatePlatform-hostedibm-granite/granite-3.0-8b-instruct$0.05/M in$0.05 per million input tokens
ReplicatePlatform-hostedibm-granite/granite-8b-code-instruct-128k$0.05/M in$0.05 per million input tokens
ReplicatePlatform-hostedmeta/llama-2-7b$0.05/M in$0.05 per million input tokens
ReplicatePlatform-hostedmeta/llama-2-7b-chat$0.05/M in$0.05 per million input tokens
ReplicatePlatform-hostedmeta/meta-llama-3-8b$0.05/M in$0.05 per million input tokens
ReplicatePlatform-hostedmeta/meta-llama-3-8b-instruct$0.05/M in$0.05 per million input tokens
ReplicatePlatform-hostedmistralai/mistral-7b-v0.1$0.05/M in$0.05 per million input tokens
ReplicatePlatform-hostedibm-granite/granite-4.0-h-small$0.06/M in$0.06 per million input tokens
ReplicatePlatform-hostedibm-granite/granite-4.1-8b$0.06/M in$0.06 per million input tokens
ReplicatePlatform-hostedibm-granite/granite-4.2-8b$0.06/M in$0.06 per million input tokens
ReplicatePlatform-hostedibm-granite/granite-vision-4.1-4b$0.06/M in$0.06 per million input tokens
ReplicatePlatform-hostedibm-granite/granite-20b-code-instruct-8k$0.1/M in$0.10 per million input tokens
ReplicatePlatform-hostedmeta/llama-2-13b$0.1/M in$0.10 per million input tokens
ReplicatePlatform-hostedmeta/llama-2-13b-chat$0.1/M in$0.10 per million input tokens
ReplicatePlatform-hostedmeta/llama-4-scout-instruct$0.17/M in$0.17 per million input tokens
ReplicatePlatform-hostedopenai/gpt-oss-120b$0.18/M in$0.18 per million input tokens
ReplicatePlatform-hostedmeta/llama-guard-4-12b$0.2/M in$0.20 per million input tokens
ReplicatePlatform-hostedmeta/llama-4-maverick-instruct$0.25/M in$0.25 per million input tokens
ReplicatePlatform-hostedperceptron-ai-inc/isaac-0.1$0.26/M in$0.26 per million input tokens
ReplicatePlatform-hostedqwen/qwen3-235b-a22b-instruct-2507$0.264/M in$0.264 per million input tokens
ReplicatePlatform-hostedmeta/llama-2-70b$0.65/M in$0.65 per million input tokens
ReplicatePlatform-hostedmeta/llama-2-70b-chat$0.65/M in$0.65 per million input tokens
ReplicatePlatform-hostedmeta/meta-llama-3-70b$0.65/M in$0.65 per million input tokens
ReplicatePlatform-hostedmeta/meta-llama-3-70b-instruct$0.65/M in$0.65 per million input tokens
ReplicatePlatform-hosteddeepseek-ai/deepseek-v3$1.45/M in$1.45 per million input tokens
ReplicatePlatform-hosteddeepseek-ai/deepseek-r1$3.75/M in$3.75 per million input tokens

Per million output tokens34

PlatformModel · what it coversUSDPlatform’s own wordingSince
ReplicatePlatform-hostedmeta/llama-guard-4-12b$0.2/M outCheapest$0.20 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-3.0-2b-instruct$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-3.0-8b-instruct$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-3.1-2b-instruct$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-3.1-8b-instruct$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-3.2-8b-instruct$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-3.3-8b-instruct$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-4.0-h-small$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-4.1-8b$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-4.2-8b$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-8b-code-instruct-128k$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-speech-4.1-2b$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-vision-3.3-2b$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-vision-4.1-4b$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedmeta/llama-2-7b$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedmeta/llama-2-7b-chat$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedmeta/meta-llama-3-8b$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedmeta/meta-llama-3-8b-instruct$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedmistralai/mistral-7b-v0.1$0.25/M out$0.25 per million output tokens
ReplicatePlatform-hostedibm-granite/granite-20b-code-instruct-8k$0.5/M out$0.50 per million output tokens
ReplicatePlatform-hostedmeta/llama-2-13b$0.5/M out$0.50 per million output tokens
ReplicatePlatform-hostedmeta/llama-2-13b-chat$0.5/M out$0.50 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
ReplicatePlatform-hosteddeepseek-ai/deepseek-v3$1.45/M out$1.45 per million output tokens
ReplicatePlatform-hostedperceptron-ai-inc/isaac-0.1$2.17/M out$2.17 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
ReplicatePlatform-hostedibm-granite/granite-speech-3.3-8b$4.9/M out$4.90 per million output tokens
ReplicatePlatform-hosteddeepseek-ai/deepseek-r1$10/M out$0.01 per thousand output tokens

Per thousand characters3

PlatformModel · what it coversUSDPlatform’s own wordingSince
ReplicatePlatform-hostedqwen/qwen3-ttsthousand input characters$0.02/1K charsCheapest$0.02 per thousand input characters
ReplicatePlatform-hostedresemble-ai/chatterboxthousand input characters$0.025/1K chars$0.025 per thousand input characters
ReplicatePlatform-hostedresemble-ai/chatterbox-turbothousand input characters$0.025/1K chars$0.025 per thousand input characters

Per second of compute time4

PlatformModel · what it coversUSDPlatform’s own wordingSince
ReplicatePlatform-hostedfalcons-ai/nsfw_image_detectionsecond of run time$0.00023/compute sCheapest$0.225 per thousand seconds of run time
ReplicatePlatform-hostedibm-granite/granite-embedding-small-english-r2second of run time$0.00023/compute sCheapest$0.225 per thousand seconds of run time
ReplicatePlatform-hostedopenai/clipsecond of run time$0.00098/compute s$0.975 per thousand seconds of run time
ReplicatePlatform-hostedwan-video/wan-2.2-animate-animationVideo to video & editingsecond of run time$0.003/compute s$3 per thousand seconds of run time

Per run (default parameters)3

PlatformModel · what it coversUSDPlatform’s own wordingSince
ReplicatePlatform-hostedibm-granite/granite-embedding-278m-multilingualrun$0.001/runCheapest$1 per thousand runs
ReplicatePlatform-hostedprunaai/p-image-try-onImage to image & editingrun$0.007/run$7 per thousand runs
ReplicatePlatform-hostedstability-ai/stable-audio-2.5$0.2/run$0.20 per output audio file