Skip to content
API Pricing

10,135 prices on 4,604 listings · last collected 5 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.

Showing 1–100 of 146

Per million output tokens100

PlatformModel · what it coversUSDPlatform’s own wordingSince
OpenRouterThird-partyDots Studio: Dots3-Note Preview (free)$0/M outCheapestcompletion: 0 / token
OpenRouterThird-partyMistral: Mistral Nemo$0.03/M outcompletion: 0.00000003 / token
OpenRouterThird-partyMeta: Llama 3.1 8B Instruct$0.04/M outcompletion: 0.00000004 / token
OpenRouterThird-partySao10K: Llama 3 8B Lunaris$0.05/M outcompletion: 0.00000005 / token
OpenRouterThird-partyZ.ai: GLM 5.3 Flash (batch)$0.061/M outcompletion: 0.000000061 / token
OpenRouterThird-partyinclusionAI: Ling 3.0 Flash$0.063/M outcompletion: 0.000000063 / token
OpenRouterThird-partyZ.ai: GLM 5.3 Flash$0.0784/M outcompletion: 0.0000000784 / token
OpenRouterThird-partyMistral: Mistral Small 3$0.08/M outcompletion: 0.00000008 / token
OpenRouterThird-partyGoogle: Gemma 3 4B$0.1/M outcompletion: 0.0000001 / token
OpenRouterThird-partyGoogle: Gemma 4 26B A4B $0.1/M outcompletion: 0.0000001 / token
OpenRouterThird-partyMythoMax 13B$0.11/M outcompletion: 0.00000011 / token
OpenRouterThird-partyOpenAI: gpt-oss-20b (batch)$0.112/M outcompletion: 0.000000112 / token
OpenRouterThird-partyOpenAI: gpt-oss-20b$0.13/M outcompletion: 0.00000013 / token
OpenRouterThird-partyPrismML: Ternary Bonsai 2 9B$0.13/M outcompletion: 0.00000013 / token
OpenRouterThird-partyinclusionAI: Ling 3.1 Flash$0.135/M outcompletion: 0.000000135 / token
OpenRouterThird-partyOpenAI: gpt-oss-120b (batch)$0.136/M outcompletion: 0.000000136 / token
OpenRouterThird-partyMicrosoft: Phi 4$0.14/M outcompletion: 0.00000014 / token
OpenRouterThird-partyDeepSeek: DeepSeek V4 Flash 0731 (batch)$0.144/M outcompletion: 0.000000144 / token
OpenRouterThird-partyGoogle: Gemma 3 12B$0.15/M outcompletion: 0.00000015 / token
OpenRouterThird-partyDeepSeek: DeepSeek V4 Flash 0423$0.18/M outcompletion: 0.00000018 / token
OpenRouterThird-partyinclusionAI: Ling 3.0 Flash VL$0.18/M outcompletion: 0.00000018 / token
OpenRouterThird-partyMeta: Llama Guard 4 12B$0.18/M outcompletion: 0.00000018 / token
OpenRouterThird-partyByteDance: UI-TARS 7B $0.2/M outcompletion: 0.0000002 / token
OpenRouterThird-partyDeepSeek: DeepSeek V4.1 Flash 1017 (batch)$0.2/M outcompletion: 0.0000002 / token
OpenRouterThird-partyNVIDIA: Nemotron 3.5 Content Safety$0.2/M outcompletion: 0.0000002 / token
OpenRouterThird-partyNVIDIA: Nemotron 3.5 Lightning$0.2/M outcompletion: 0.0000002 / token
OpenRouterThird-partyMeta: Llama 3.2 1B Instruct$0.201/M outcompletion: 0.000000201 / token
OpenRouterThird-partyQwen: Qwen3 14B$0.22/M outcompletion: 0.00000022 / token
OpenRouterThird-partyNVIDIA: Nemotron 3 Nano 30B A3B$0.24/M outcompletion: 0.00000024 / token
OpenRouterThird-partyIBM: Granite 4.2 8B$0.25/M outcompletion: 0.00000025 / token
OpenRouterThird-partyQwen: Qwen3.5-9B$0.25/M outcompletion: 0.00000025 / token
OpenRouterThird-partyQwen: Qwen3 32B$0.28/M outcompletion: 0.00000028 / token
OpenRouterThird-partyXiaomi: MiMo-V2.6-Flash$0.28/M outcompletion: 0.00000028 / token
OpenRouterThird-partyDeepSeek: DeepSeek V4 Flash 0731$0.3/M outcompletion: 0.0000003 / token
OpenRouterThird-partyMeta: Llama 4 Scout$0.3/M outcompletion: 0.0000003 / token
OpenRouterThird-partyMiniMax: MiniMax M3.1 Flashoff-peak 1500–0100 UTC$0.3/M outcompletion: 0.0000003 / token (utc_start 1500, utc_end 100)
OpenRouterThird-partyMistral: Mistral Small 3.2 24B$0.3/M outcompletion: 0.0000003 / token
OpenRouterThird-partyOpenAI: gpt-oss-safeguard-20b$0.3/M outcompletion: 0.0000003 / token
OpenRouterThird-partyQwen: Qwen3 30B A3B Instruct 2507$0.3/M outcompletion: 0.0000003 / token
OpenRouterThird-partyStepFun: Step 3.5 Flash$0.3/M outcompletion: 0.0000003 / token
OpenRouterThird-partyMeta: Llama 3.2 3B Instruct$0.33/M outcompletion: 0.00000033 / token
OpenRouterThird-partyTencent: Hy3off-peak 1600–0000 UTC$0.33/M outcompletion: 0.00000033 / token (utc_start 1600, utc_end 0)
OpenRouterThird-partyDeepSeek: DeepSeek V4.1 Flash (batch)$0.336/M outcompletion: 0.000000336 / token
OpenRouterThird-partyDeepSeek: DeepSeek V3.2$0.38/M outcompletion: 0.00000038 / token
OpenRouterThird-partyGoogle: Gemma 4 31B$0.4/M outcompletion: 0.0000004 / token
OpenRouterThird-partyNVIDIA: Nemotron 3 Super$0.4/M outcompletion: 0.0000004 / token
OpenRouterThird-partyQwen2.5 72B Instruct$0.4/M outcompletion: 0.0000004 / token
OpenRouterThird-partyTheDrummer: UnslopNemo 12B$0.4/M outcompletion: 0.0000004 / token
OpenRouterThird-partyZ.ai: GLM 4.7 Flash$0.4/M outcompletion: 0.0000004 / token
OpenRouterThird-partyDeepSeek: DeepSeek V3.2 Exp$0.41/M outcompletion: 0.00000041 / token
OpenRouterThird-partyGoogle: Gemma 3 27B$0.45/M outcompletion: 0.00000045 / token
OpenRouterThird-partyNVIDIA: Nemotron 3.5 Super VL$0.47/M outcompletion: 0.00000047 / token
OpenRouterThird-partyDeepSeek: DeepSeek V4.1 Flash 1017$0.5/M outcompletion: 0.0000005 / token
OpenRouterThird-partyPrismML: Ternary Bonsai 2 27B$0.5/M outcompletion: 0.0000005 / token
OpenRouterThird-partyQwen: Qwen3 30B A3B$0.5/M outcompletion: 0.0000005 / token
OpenRouterThird-partyTheDrummer: Cydonia 24B V4.1$0.5/M outcompletion: 0.0000005 / token
OpenRouterThird-partyReMM SLERP 13B$0.5/M outcompletion: 0.0000005 / token
OpenRouterThird-partyTencent: Hy3$0.528/M outcompletion: 0.000000528 / token (utc_start 0, utc_end 1600)
OpenRouterThird-partyMistral: Mistral Small 3.1 24B$0.555/M outcompletion: 0.000000555 / token
OpenRouterThird-partyDeepSeek: DeepSeek V4.1 Flash$0.567/M outcompletion: 0.000000567 / token
OpenRouterThird-partyTencent: Hunyuan A13B Instruct$0.57/M outcompletion: 0.00000057 / token
OpenRouterThird-partyMiniMax: MiniMax M3.1 Flash$0.6/M outcompletion: 0.0000006 / token (utc_start 100, utc_end 1500)
OpenRouterThird-partyOpenAI: gpt-oss-120b$0.6/M outcompletion: 0.0000006 / token
OpenRouterThird-partyQwen: Qwen3 Coder 30B A3B Instruct$0.6/M outcompletion: 0.0000006 / token
OpenRouterThird-partyQwen: Qwen3 VL 30B A3B Instruct$0.6/M outcompletion: 0.0000006 / token
OpenRouterThird-partyRicursive: Ripple 65B Preview$0.6/M outcompletion: 0.0000006 / token
OpenRouterThird-partyTencent: Hy3 preview$0.6/M outcompletion: 0.0000006 / token
OpenRouterThird-partyGoogle: Gemma 2 27B$0.65/M outcompletion: 0.00000065 / token
OpenRouterThird-partyMeta: Llama 3.3 70B Instruct$0.71/M outcompletion: 0.00000071 / token
OpenRouterThird-partyMeta: Llama 3.1 70B Instruct$0.72/M outcompletion: 0.00000072 / token
OpenRouterThird-partyQwen: Qwen3 VL 8B Instruct$0.75/M outcompletion: 0.00000075 / token
OpenRouterThird-partyQwen: Qwen3 235B A22B Instruct 2507$0.8/M outcompletion: 0.0000008 / token
OpenRouterThird-partyQwen: Qwen3 Coder Next$0.8/M outcompletion: 0.0000008 / token
OpenRouterThird-partyTheDrummer: Skyfall 36B V2$0.8/M outcompletion: 0.0000008 / token
OpenRouterThird-partyMiniMax: MiniMax M2.7$0.84/M outcompletion: 0.00000084 / token
OpenRouterThird-partySao10K: Llama 3.1 Euryale 70B v2.2$0.85/M outcompletion: 0.00000085 / token
OpenRouterThird-partyXiaomi: MiMo-V2.6-Pro$0.87/M outcompletion: 0.00000087 / token
OpenRouterThird-partyMiniMax: MiniMax M3 (batch)$0.88/M outcompletion: 0.00000088 / token
OpenRouterThird-partyDeepSeek: DeepSeek V3$0.89/M outcompletion: 0.00000089 / token
OpenRouterThird-partyVenice: Uncensored$0.9/M outcompletion: 0.0000009 / token
OpenRouterThird-partyQwen: Qwen3.6 35B A3B$0.9/M outcompletion: 0.0000009 / token
OpenRouterThird-partyZ.ai: GLM 4.6V$0.9/M outcompletion: 0.0000009 / token
OpenRouterThird-partyDeepSeek: DeepSeek V3.1$0.95/M outcompletion: 0.00000095 / token
OpenRouterThird-partyMeta: Muse Glimmer 30B (batch)$0.96/M outcompletion: 0.00000096 / token
OpenRouterThird-partyThinking Machines: Inkling Small (batch)$0.96/M outcompletion: 0.00000096 / token
OpenRouterThird-partyDeepSeek: DeepSeek V3.1 Terminus$1/M outcompletion: 0.000001 / token
OpenRouterThird-partyMeta: Llama 4 Maverick$1/M outcompletion: 0.000001 / token
OpenRouterThird-partyQwen2.5 Coder 32B Instruct$1/M outcompletion: 0.000001 / token
OpenRouterThird-partyQwen: Qwen2.5 VL 72B Instruct$1/M outcompletion: 0.000001 / token
OpenRouterThird-partyQwen: Qwen3 Coder 480B A35B$1/M outcompletion: 0.000001 / token
OpenRouterThird-partyQwen: Qwen3 VL 30B A3B Thinking$1/M outcompletion: 0.000001 / token
OpenRouterThird-partyQwen: Qwen3.5-35B-A3B$1/M outcompletion: 0.000001 / token
OpenRouterThird-partyReflection: Beam 1.0 501B A23B$1/M outcompletion: 0.000001 / token
OpenRouterThird-partyZ.ai: GLM 5.2 (batch)$1.075/M outcompletion: 0.000001075 / token
OpenRouterThird-partyMiniMax: MiniMax M2.5$1.08/M outcompletion: 0.00000108 / token
OpenRouterThird-partyQwen: Qwen3 Next 80B A3B Instruct$1.1/M outcompletion: 0.0000011 / token
OpenRouterThird-partyZ.ai: GLM 4.5 Air$1.1/M outcompletion: 0.0000011 / token
OpenRouterThird-partyDeepSeek: DeepSeek V3 0324$1.14/M outcompletion: 0.00000114 / token
OpenRouterThird-partyStepFun: Step 3.7 Flash$1.15/M outcompletion: 0.00000115 / token
OpenRouterThird-partyMeituan: LongCat 2.0$1.2/M outcompletion: 0.0000012 / token