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 2 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.

Showing 1–76 of 76

“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 output tokens76

PlatformModel · what it coversUSDPlatform’s own wordingSince
OpenRouterThird-partyDots Studio: Dots3-Note Preview (free)$0/M outCheapestcompletion: 0 / token (endpoint atlas-cloud/fp8)
OpenRouterOfficialGoogle: Gemma 4 31B (free)$0/M outCheapestcompletion: 0 / token (endpoint google-ai-studio)
OpenRouterOfficialNVIDIA: Nemotron 3 Nano Omni (free)$0/M outCheapestcompletion: 0 / token (endpoint nvidia)
OpenRouterOfficialNVIDIA: Nemotron 3 Ultra (free)$0/M outCheapestcompletion: 0 / token (endpoint nvidia)
OpenRouterThird-partySao10K: Llama 3 8B Lunarisvia Parasail · bf16$0.05/M outcompletion: 0.00000005 / token (endpoint parasail/bf16)
OpenRouterThird-partyMistral: Mistral Small 3$0.08/M outcompletion: 0.00000008 / token (endpoint deepinfra/fp8)
OpenRouterOfficialMistral: Ministral 3 3B 2512via Mistral · zdr$0.1/M outcompletion: 0.0000001 / token (endpoint mistral/zdr)
OpenRouterThird-partyGoogle: Gemma 3 12Bvia NextBit · int4$0.15/M outcompletion: 0.00000015 / token (endpoint nextbit/int4)
OpenRouterOfficialMistral: Ministral 3 8B 2512via Mistral · zdr$0.15/M outcompletion: 0.00000015 / token (endpoint mistral/zdr)
OpenRouterThird-partyGoogle: Gemma 3 27Bvia DeepInfra · fp8$0.16/M outcompletion: 0.00000016 / token (endpoint deepinfra/fp8)
OpenRouterOfficialMistral: Ministral 3 14B 2512via Mistral · zdr$0.2/M outcompletion: 0.0000002 / token (endpoint mistral/zdr)
OpenRouterOfficialReka Flash 3$0.2/M outcompletion: 0.0000002 / token (endpoint reka)
OpenRouterThird-partyQwen: Qwen3 14Bvia NextBit · int4$0.22/M outcompletion: 0.00000022 / token (endpoint nextbit/int4)
OpenRouterThird-partyNVIDIA: Nemotron 3 Nano 30B A3B$0.24/M outcompletion: 0.00000024 / token (endpoint nebius/fp8)
OpenRouterThird-partyQwen: Qwen3 32Bvia DeepInfra · fp8$0.28/M outcompletion: 0.00000028 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3 Coder 30B A3B Instructvia SiliconFlow · fp8$0.28/M outcompletion: 0.00000028 / token (endpoint siliconflow/fp8)
OpenRouterOfficialTencent: Hy-MT2-30B-A3B$0.295/M outcompletion: 0.000000295 / token (endpoint tencent/fp8)
OpenRouterThird-partyQwen: Qwen3 30B A3B Instruct 2507via DekaLLM$0.3/M outcompletion: 0.0000003 / token (endpoint dekallm)
OpenRouterThird-partyTencent: Hy3off-peak 1600–0000 UTC · via Tencent · fp8$0.33/M outcompletion: 0.00000033 / token (utc_start 1600, utc_end 0; endpoint tencent/fp8)
OpenRouterNot disclosedGoogle: Gemma 4 31Bvia KT$0.34/M outcompletion: 0.00000034 / token (endpoint kt)
OpenRouterThird-partyNVIDIA: Nemotron 3 Supervia DeepInfra · bf16$0.4/M outcompletion: 0.0000004 / token (endpoint deepinfra/bf16)
OpenRouterThird-partyQwen: Qwen3 30B A3B$0.5/M outcompletion: 0.0000005 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyTencent: Hy3peak 0000–1600 UTC · via Tencent · fp8$0.528/M outcompletion: 0.000000528 / token (utc_start 0, utc_end 1600; endpoint tencent/fp8)
OpenRouterThird-partyQwen: Qwen3 235B A22B Instruct 2507via DeepInfra · fp8$0.55/M outcompletion: 0.00000055 / token (endpoint deepinfra/fp8)
OpenRouterOfficialMorph: Morph V3 Fast (batch)$0.6/M outcompletion: 0.0000006 / token
OpenRouterThird-partyQwen: Qwen3 VL 30B A3B Instructvia DeepInfra · fp8$0.6/M outcompletion: 0.0000006 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyTencent: Hy3 preview$0.6/M outcompletion: 0.0000006 / token (endpoint gmicloud/bf16)
OpenRouterThird-partyQwen: Qwen3 VL 8B Instruct$0.75/M outcompletion: 0.00000075 / token (endpoint parasail/bf16)
OpenRouterThird-partyQwen: Qwen3 Coder Next$0.8/M outcompletion: 0.0000008 / token (endpoint parasail/bf16)
OpenRouterThird-partyTheDrummer: Skyfall 36B V2$0.8/M outcompletion: 0.0000008 / token (endpoint parasail/fp8)
OpenRouterThird-partyMiniMax: MiniMax M3 (batch)$0.88/M outcompletion: 0.00000088 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3 VL 235B A22B Instructvia DeepInfra · fp8$0.88/M outcompletion: 0.00000088 / token (endpoint deepinfra/fp8)
OpenRouterOfficialMorph: Morph V3 Large (batch)$0.95/M outcompletion: 0.00000095 / token (endpoint morph/fp8)
OpenRouterThird-partyMeta: Muse Glimmer 30B (batch)$0.96/M outcompletion: 0.00000096 / token (endpoint deepinfra/bf16)
OpenRouterThird-partyMiniMax: MiniMax M3via CoreWeave · fp4$0.96/M outcompletion: 0.00000096 / token (endpoint coreweave/fp4)
OpenRouterOfficialQwen: Qwen3 Coder Flash$0.975/M outcompletion: 0.000000975 / token (endpoint alibaba)
OpenRouterThird-partyDeepSeek: DeepSeek V3 0324via SiliconFlow · fp8$1/M outcompletion: 0.000001 / token (endpoint siliconflow/fp8)
OpenRouterThird-partyQwen2.5 Coder 32B Instruct$1/M outcompletion: 0.000001 / token (endpoint cloudflare)
OpenRouterThird-partyQwen: Qwen3 Coder 480B A35BTurbovia DeepInfra$1/M outcompletion: 0.000001 / token (endpoint deepinfra/turbo)
OpenRouterThird-partyQwen: Qwen3 VL 30B A3B Thinking$1/M outcompletion: 0.000001 / token (endpoint siliconflow/fp8)
OpenRouterThird-partyDeepSeek: DeepSeek V3via StreamLake$1.029/M outcompletion: 0.0000010287 / token (endpoint streamlake)
OpenRouterThird-partyQwen: Qwen3 Next 80B A3B Instructvia DeepInfra · fp8$1.1/M outcompletion: 0.0000011 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyMeta: Muse Glimmer 30B$1.2/M outcompletion: 0.0000012 / token (endpoint deepinfra/bf16)
OpenRouterOfficialMorph: Morph V3 Fast$1.2/M outcompletion: 0.0000012 / token (endpoint morph/fp8)
OpenRouterNot disclosedMotif Technologies: Motif 3$1.2/M outcompletion: 0.0000012 / token (endpoint kt)
OpenRouterOfficialRelace: Relace Apply 3$1.25/M outcompletion: 0.00000125 / token (endpoint relace/fp8)
OpenRouterOfficialGoogle: Gemini 3 Flash Preview (batch)$1.5/M outcompletion: 0.0000015 / token (endpoint google-vertex/global)
OpenRouterOfficialGoogle: Gemini 3 Flash Preview (batch)Reasoning$1.5/M outinternal_reasoning: 0.0000015 / token (endpoint google-vertex/global)
OpenRouterOfficialMistral: Mistral Large 3 2512via Mistral · zdr$1.5/M outcompletion: 0.0000015 / token (endpoint mistral/zdr)
OpenRouterOfficialQwen: Qwen3 Coder FlashPrompt > 32K$1.625/M outcompletion: 0.000001625 / token (>32000; endpoint alibaba)
OpenRouterOfficialMorph: Morph V3 Large$1.9/M outcompletion: 0.0000019 / token (endpoint morph/fp8)
OpenRouterOfficialMistral: Mistral Medium 3via Mistral · zdr$2/M outcompletion: 0.000002 / token (endpoint mistral/zdr)
OpenRouterNot disclosedNVIDIA: Nemotron 3 Ultravia KT$2.2/M outcompletion: 0.0000022 / token (endpoint kt)
OpenRouterOfficialOpenAI: o3 Mini (batch)$2.2/M outcompletion: 0.0000022 / token (endpoint openai)
OpenRouterThird-partyMoondream: Moondream 3 Preview$2.5/M outcompletion: 0.0000025 / token (endpoint primeintellect/fp8)
OpenRouterOfficialQwen: Qwen3 Coder FlashPrompt > 128K$2.6/M outcompletion: 0.0000026 / token (>128000; endpoint alibaba)
OpenRouterOfficialGoogle: Gemini 3 Flash Previewvia Google AI Studio$3/M outcompletion: 0.000003 / token (endpoint google-ai-studio)
OpenRouterOfficialGoogle: Gemini 3 Flash PreviewReasoningvia Google AI Studio$3/M outinternal_reasoning: 0.000003 / token (endpoint google-ai-studio)
OpenRouterThird-partyQwen: Qwen3 235B A22B Thinking 2507$3.5/M outcompletion: 0.0000035 / token (endpoint venice/fp8)
OpenRouterOfficialMiniMax: MiniMax H3 Image$3.8/M outoutput_image: 0.0000038 USD / token
OpenRouterOfficialOpenAI: o3 (batch)$4/M outcompletion: 0.000004 / token (endpoint openai)
OpenRouterOfficialMiniMax: MiniMax H3 Image Highspeed$7.6/M outoutput_image: 0.0000076 USD / token
OpenRouterOfficialOpenAI: o3$8/M outcompletion: 0.000008 / token (endpoint openai)
OpenRouterNot disclosedMoonshotAI: Kimi K3via Relace · fp4$11.006/M outcompletion: 0.0000110055 / token (endpoint relace/fp4)
OpenRouterThird-partyMoonshotAI: Kimi K3 (batch)$11.4/M outcompletion: 0.0000114 / token (endpoint deepinfra/bf16)
OpenRouterOfficialGoogle: Nano Banana Pro (Gemini 3 Pro Image)Text$12/M outcompletion: 0.000012 / token
OpenRouterOfficialGoogle: Nano Banana Pro (Gemini 3 Pro Image)Reasoning$12/M outinternal_reasoning: 0.000012 / token
OpenRouterOfficialGoogle: Nano Banana Pro (Gemini 3 Pro Image Preview)Text$12/M outcompletion: 0.000012 / token
OpenRouterOfficialGoogle: Nano Banana Pro (Gemini 3 Pro Image Preview)Reasoning$12/M outinternal_reasoning: 0.000012 / token
OpenRouterOfficialGoogle: Nano Banana Pro (Gemini 3 Pro Image Preview)via Google AI Studio · global/flex$60/M outoutput_image: 0.00006 USD / token
OpenRouterOfficialOpenAI: o3 Pro$80/M outcompletion: 0.00008 / token (endpoint openai)
OpenRouterOfficialGoogle: Nano Banana Pro (Gemini 3 Pro Image)via Google AI Studio$120/M outoutput_image: 0.00012 USD / token
OpenRouterOfficialGoogle: Nano Banana Pro (Gemini 3 Pro Image)via Google Vertex$120/M outoutput_image: 0.00012 USD / token
OpenRouterOfficialGoogle: Nano Banana Pro (Gemini 3 Pro Image)$120/M outimage_output: 0.00012 / token
OpenRouterOfficialGoogle: Nano Banana Pro (Gemini 3 Pro Image Preview)via Google AI Studio · global$120/M outoutput_image: 0.00012 USD / token
OpenRouterOfficialGoogle: Nano Banana Pro (Gemini 3 Pro Image Preview)$120/M outimage_output: 0.00012 / token