Skip to content
API Pricing

10,549 prices on 4,760 listings · last collected 35 min ago · 383 flagged changes in 30 days

Every price, as each platform publishes it

A collector reads every public price on eight 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 43OpenRouter 34KIE 1Fal 0WaveSpeed 0Replicate 0APIMart 0Runware 6Aiberm 2
Kind
AllVideoImageTextAudioOtherExact prices only (hide “from”)
Route
All 43Official / partner 13Platform-hosted 0Third-party 20Not disclosed 10
Model
AllQwen 9Mistral 6Kimi 5Gemini 5GPT 4MiniMax 4Hunyuan 3Nemotron 2DeepSeek 1
Unit
All 294Per million input tokens 120Per million output tokens 117Per million tokens 1Per million cached input tokens (read) 43Per million cache-write tokens 4Per second of compute time 1Per run (default parameters) 7Other units (see the platform’s wording) 1

Showing 1–43 of 43

“Cheapest” is the lowest exact price in this unit for your search. Rows can differ in resolution, length or quality — read the label, or add it to the search (e.g. “1080”).

Per million cached input tokens (read)43

PlatformModel · what it coversUSDPlatform’s own wordingSince
OpenRouterOfficialMistral: Ministral 3 3B 2512$0.01/M cache readCheapestinput_cache_read: 0.00000001 / token
OpenRouterThird-partyNVIDIA: Nemotron 3 Nano 30B A3B$0.012/M cache readinput_cache_read: 0.000000012 / token
RunwareNot disclosedGemma 4 31BPer 1M$0.012/M cache read$1.2e-8 / cachedInputToken
OpenRouterOfficialMistral: Ministral 3 8B 2512$0.015/M cache readinput_cache_read: 0.000000015 / token
OpenRouterOfficialMistral: Ministral 3 14B 2512$0.02/M cache readinput_cache_read: 0.00000002 / token
OpenRouterThird-partyTencent: Hy3off-peak 1600–0000 UTC$0.020625/M cache readinput_cache_read: 0.000000020625 / token (utc_start 1600, utc_end 0)
OpenRouterThird-partyMeta: Muse Glimmer 30B (batch)$0.032/M cache readinput_cache_read: 0.000000032 / token
OpenRouterThird-partyTencent: Hy3$0.033/M cache readinput_cache_read: 0.000000033 / token (utc_start 0, utc_end 1600)
OpenRouterOfficialQwen: Qwen3 Coder Flash$0.039/M cache readinput_cache_read: 0.000000039 / token
OpenRouterThird-partyGoogle: Gemma 3 27B$0.04/M cache readinput_cache_read: 0.00000004 / token
OpenRouterThird-partyMeta: Muse Glimmer 30B$0.04/M cache readinput_cache_read: 0.00000004 / token
OpenRouterOfficialMistral: Mistral Medium 3$0.04/M cache readinput_cache_read: 0.00000004 / token
OpenRouterThird-partyMiniMax: MiniMax M3 (batch)$0.0448/M cache readinput_cache_read: 0.0000000448 / token
RunwareNot disclosedShieldstral 1.0 3BPer 1M$0.045/M cache read$4.5e-8 / cachedInputToken
OpenRouterOfficialGoogle: Gemini 3 Flash Preview$0.05/M cache readinput_cache_read: 0.00000005 / token
OpenRouterOfficialMistral: Mistral Large 3 2512$0.05/M cache readinput_cache_read: 0.00000005 / token
OpenRouterThird-partyQwen: Qwen3 235B A22B Instruct 2507$0.05/M cache readinput_cache_read: 0.00000005 / token
OpenRouterThird-partyMiniMax: MiniMax M3$0.06/M cache readinput_cache_read: 0.00000006 / token
OpenRouterNot disclosedMotif Technologies: Motif 3$0.06/M cache readinput_cache_read: 0.00000006 / token
OpenRouterThird-partyTencent: Hy3 preview$0.06/M cache readinput_cache_read: 0.00000006 / token
RunwareNot disclosedMiniMax M3≤ 512K context$0.06/M cache read$6e-8 / cachedInputToken · ≤ 512K context
OpenRouterOfficialQwen: Qwen3 Coder FlashPrompt > 32K$0.065/M cache readinput_cache_read: 0.000000065 / token (>32000)
OpenRouterThird-partyQwen: Qwen3 Coder Next$0.07/M cache readinput_cache_read: 0.00000007 / token
AibermNot disclosedo3 Mini$0.0759/M cache readmodel_ratio 0.55 × $2/M · group default ×0.23 · cache_ratio 0.3
OpenRouterOfficialGoogle: Gemini 3 Flash Preview$0.1/M cache readinput_audio_cache: 0.0000001 / token
OpenRouterThird-partyQwen: Qwen3 30B A3B Instruct 2507$0.1/M cache readinput_cache_read: 0.0000001 / token
OpenRouterThird-partyQwen: Qwen3 Coder 480B A35B$0.1/M cache readinput_cache_read: 0.0000001 / token
OpenRouterThird-partyQwen: Qwen3 VL 235B A22B Instruct$0.1/M cache readinput_cache_read: 0.0000001 / token
RunwareNot disclosedGemini 4 ArgonThrough Nov 30 · 2026$0.1/M cache read$1e-7 / cachedInputToken · Through Nov 30, 2026
OpenRouterOfficialQwen: Qwen3 Coder FlashPrompt > 128K$0.104/M cache readinput_cache_read: 0.000000104 / token (>128000)
AibermNot disclosedKimi K3$0.1058/M cache readmodel_ratio 2.3 × $2/M · group default ×0.23 · cache_ratio 0.1
OpenRouterThird-partyDeepSeek: DeepSeek V3 0324$0.11/M cache readinput_cache_read: 0.00000011 / token
OpenRouterThird-partyNVIDIA: Nemotron 3 Ultra$0.12/M cache readinput_cache_read: 0.00000012 / token
OpenRouterThird-partyQwen: Qwen3 VL 8B Instruct$0.12/M cache readinput_cache_read: 0.00000012 / token
RunwareNot disclosedMiniMax M3> 512K context$0.12/M cache read$1.2e-7 / cachedInputToken · > 512K context
OpenRouterThird-partyMoonshotAI: Kimi K3$0.182/M cache readinput_cache_read: 0.000000182 / token
OpenRouterThird-partyMoonshotAI: Kimi K3 (batch)$0.228/M cache readinput_cache_read: 0.000000228 / token
KIENot disclosedKimi K3$0.24/M cache read48 credits per million tokens ($0.24)Claims official or Fal price $0.3/M cache read
OpenRouterOfficialOpenAI: o3 (batch)$0.25/M cache readinput_cache_read: 0.00000025 / token
OpenRouterThird-partyTheDrummer: Skyfall 36B V2$0.25/M cache readinput_cache_read: 0.00000025 / token
OpenRouterOfficialOpenAI: o3 Mini (batch)$0.275/M cache readinput_cache_read: 0.000000275 / token
RunwareNot disclosedKimi K3Per 1M$0.3/M cache read$3e-7 / cachedInputToken
OpenRouterOfficialOpenAI: o3$0.5/M cache readinput_cache_read: 0.0000005 / token