Skip to content
API Pricing

10,135 prices on 4,604 listings · last collected 22 min ago · 383 flagged changes in 30 days

Every price, as each platform publishes it

A collector reads every public price on seven 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 538OpenRouter 433KIE 19Fal 20WaveSpeed 0Replicate 0APIMart 14Runware 52
Kind
AllVideoImageTextAudioOtherExact prices only (hide “from”)
Route
All 52Official / partner 0Platform-hosted 0Third-party 0Not disclosed 52
Unit
All 1,037Per second of output 283Per video 27Per image 224Per megapixel 20Per million input tokens 97Per million output tokens 88Per million cached input tokens (read) 52Per million cache-write tokens 23Per thousand characters 11Per run (default parameters) 191Other units (see the platform’s wording) 21

Showing 1–52 of 52

Per million cached input tokens (read)52

PlatformModel · what it coversUSDPlatform’s own wordingSince
RunwareNot disclosedClaude Haiku 5.5≤ 100K context$0.01/M cache readCheapest$1e-8 / cachedInputToken · ≤ 100K context
RunwareNot disclosedDeepSeek-V4.1-FlashPer 1M$0.01/M cache readCheapest$1e-8 / cachedInputToken
RunwareNot disclosedDeepSeek-V4.1-Flash-1017Per 1M$0.01/M cache readCheapest$1e-8 / cachedInputToken
RunwareNot disclosedGPT-6 Luna≤ 272K context$0.01/M cache readCheapest$1e-8 / cachedInputToken · ≤ 272K context
RunwareNot disclosedGemma 4 31BPer 1M$0.012/M cache read$1.2e-8 / cachedInputToken
RunwareNot disclosedDeepSeek-V4-Flash-0731Per 1M$0.014/M cache read$1.4e-8 / cachedInputToken
RunwareNot disclosedMiniMax M3.1 FlashPer 1M$0.015/M cache read$1.5e-8 / cachedInputToken
RunwareNot disclosedGPT-5.6 LunaPer 1M$0.02/M cache read$2e-8 / cachedInputToken
RunwareNot disclosedGPT-6 Luna> 272K context$0.02/M cache read$2e-8 / cachedInputToken · > 272K context
RunwareNot disclosedGemini 3.5 Flash-LitePer 1M$0.03/M cache read$3e-8 / cachedInputToken
RunwareNot disclosedGLM-5.3-FlashPer 1M$0.03/M cache read$3e-8 / cachedInputToken
RunwareNot disclosedgpt-oss-safeguard-20bPer 1M$0.035/M cache read$3.5e-8 / cachedInputToken
RunwareNot disclosedShieldstral 1.0 3BPer 1M$0.045/M cache read$4.5e-8 / cachedInputToken
RunwareNot disclosedClaude Haiku 5.5> 100K context$0.05/M cache read$5e-8 / cachedInputToken · > 100K context
RunwareNot disclosedGPT-6.1 Terra≤ 272K context$0.05/M cache read$5e-8 / cachedInputToken · ≤ 272K context
RunwareNot disclosedMiniMax M3≤ 512K context$0.06/M cache read$6e-8 / cachedInputToken · ≤ 512K context
RunwareNot disclosedGemini 3.7 FlashPer 1M$0.075/M cache read$7.5e-8 / cachedInputToken
RunwareNot disclosedGemini 3.8 FlashPer 1M$0.075/M cache read$7.5e-8 / cachedInputToken
RunwareNot disclosedDeepSeek-V4-Pro-0813Per 1M$0.079/M cache read$7.9e-8 / cachedInputToken
RunwareNot disclosedClaude Haiku 4.5Per 1M$0.1/M cache read$1e-7 / cachedInputToken
RunwareNot disclosedGemini 4 ArgonThrough Nov 30 · 2026$0.1/M cache read$1e-7 / cachedInputToken · Through Nov 30, 2026
RunwareNot disclosedGPT-6.1 Sol≤ 272K context$0.1/M cache read$1e-7 / cachedInputToken · ≤ 272K context
RunwareNot disclosedGPT-6.1 Terra> 272K context$0.1/M cache read$1e-7 / cachedInputToken · > 272K context
RunwareNot disclosedMiniMax M3> 512K context$0.12/M cache read$1.2e-7 / cachedInputToken · > 512K context
RunwareNot disclosedGemini 3.5 FlashPer 1M$0.15/M cache read$1.5e-7 / cachedInputToken
RunwareNot disclosedGemini 3.6 FlashPer 1M$0.15/M cache read$1.5e-7 / cachedInputToken
RunwareNot disclosedGLM-5.2Per 1M$0.16/M cache read$1.6e-7 / cachedInputToken
RunwareNot disclosedClaude Fable 5.2Per 1M$0.2/M cache read$2e-7 / cachedInputToken
RunwareNot disclosedClaude Opus 5.5Per 1M$0.2/M cache read$2e-7 / cachedInputToken
RunwareNot disclosedClaude Sonnet 5Per 1M$0.2/M cache read$2e-7 / cachedInputToken
RunwareNot disclosedClaude Sonnet 5.5Per 1M$0.2/M cache read$2e-7 / cachedInputToken
RunwareNot disclosedGemini 4 ArgonFrom Dec 1 · 2026$0.2/M cache read$2e-7 / cachedInputToken · From Dec 1, 2026
RunwareNot disclosedKimi K3.1 ProPer 1M$0.2/M cache read$2e-7 / cachedInputToken
RunwareNot disclosedGPT-5.6 TerraPer 1M$0.2/M cache read$2e-7 / cachedInputToken
RunwareNot disclosedGPT-6.1 Sol> 272K context$0.2/M cache read$2e-7 / cachedInputToken · > 272K context
RunwareNot disclosedGPT-6 Sol≤ 272K context$0.2/M cache read$2e-7 / cachedInputToken · ≤ 272K context
RunwareNot disclosedGrok 4.3Per 1M$0.2/M cache read$2e-7 / cachedInputToken
RunwareNot disclosedGLM-5.3Per 1M$0.2/M cache read$2e-7 / cachedInputToken
RunwareNot disclosedClaude Fable 5.1Per 1M$0.25/M cache read$2.5e-7 / cachedInputToken
RunwareNot disclosedClaude Sonnet 4.6Per 1M$0.3/M cache read$3e-7 / cachedInputToken
RunwareNot disclosedKimi K3Per 1M$0.3/M cache read$3e-7 / cachedInputToken
RunwareNot disclosedGPT-5.6 SolPer 1M$0.4/M cache read$4.0000000000000003e-7 / cachedInputToken
RunwareNot disclosedGPT-6 Sol> 272K context$0.4/M cache read$4e-7 / cachedInputToken · > 272K context
RunwareNot disclosedClaude Opus 4.7Per 1M$0.5/M cache read$5e-7 / cachedInputToken
RunwareNot disclosedClaude Opus 4.8Per 1M$0.5/M cache read$5e-7 / cachedInputToken
RunwareNot disclosedClaude Opus 5Per 1M$0.5/M cache read$5e-7 / cachedInputToken
RunwareNot disclosedGPT-5.5Per 1M$0.5/M cache read$5e-7 / cachedInputToken
RunwareNot disclosedGrok 4.7< 200K context$0.5/M cache read$5e-7 / cachedInputToken · < 200K context
RunwareNot disclosedClaude Fable 5Per 1M$1/M cache read$0.000001 / cachedInputToken
RunwareNot disclosedGPT-6 Astra≤ 272K context$1/M cache read$0.000001 / cachedInputToken · ≤ 272K context
RunwareNot disclosedGrok 4.7≥ 200K context$1/M cache read$0.000001 / cachedInputToken · ≥ 200K context
RunwareNot disclosedGPT-6 Astra> 272K context$2/M cache read$0.000002 / cachedInputToken · > 272K context