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 8 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 901–1000 of 2,299

Per million output tokens100

PlatformModel · what it coversUSDPlatform’s own wordingSince
OpenRouterThird-partyMicrosoft: Phi 4via DeepInfra · bf16$0.14/M outcompletion: 0.00000014 / token (endpoint deepinfra/bf16)
OpenRouterThird-partyDeepSeek: DeepSeek V4 Flash 0731 (batch)$0.144/M outcompletion: 0.000000144 / token (endpoint deepinfra/fp8)
OpenRouterOfficialCohere: Command R7B (12-2024)$0.15/M outcompletion: 0.00000015 / token (endpoint cohere)
OpenRouterThird-partyGoogle: Gemma 3 12Bvia NextBit · int4$0.15/M outcompletion: 0.00000015 / token (endpoint nextbit/int4)
OpenRouterThird-partyIBM: Granite 4.2 8Bvia CoreWeave · bf16$0.15/M outcompletion: 0.00000015 / token (endpoint coreweave/bf16)
OpenRouterOfficialInference.net: Schematron V2 Turbovia InferenceNet · bf16$0.15/M outcompletion: 0.00000015 / token (endpoint inference-net/bf16)
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)
OpenRouterOfficialTencent: Hy-MT2-1.8B$0.177/M outcompletion: 0.000000177 / token (endpoint tencent/fp8)
OpenRouterThird-partyinclusionAI: Ling 3.0 Flash VL$0.18/M outcompletion: 0.00000018 / token (endpoint deepinfra/fp16)
OpenRouterThird-partyMeta: Llama Guard 4 12Bvia DeepInfra · bf16$0.18/M outcompletion: 0.00000018 / token (endpoint deepinfra/bf16)
OpenRouterThird-partyByteDance: UI-TARS 7B $0.2/M outcompletion: 0.0000002 / token (endpoint parasail/bf16)
OpenRouterThird-partyDeepSeek: DeepSeek V4.1 Flash 1017 (batch)$0.2/M outcompletion: 0.0000002 / token (endpoint morph/fp8)
OpenRouterOfficialLiquidAI: LFM3-1.7B$0.2/M outcompletion: 0.0000002 / token (endpoint liquid/fp8)
OpenRouterOfficialMeta: Muse Spark 1.2 Contributor$0.2/M outcompletion: 0.0000002 / token (endpoint meta)
OpenRouterOfficialMeta: Muse Spark 1.3 Contributor$0.2/M outcompletion: 0.0000002 / token (endpoint meta)
OpenRouterOfficialMistral: Ministral 3 14B 2512via Mistral · zdr$0.2/M outcompletion: 0.0000002 / token (endpoint mistral/zdr)
OpenRouterThird-partyMistral: Mistral Small 3.2 24Bvia DeepInfra · fp8$0.2/M outcompletion: 0.0000002 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyNVIDIA: Nemotron 3.5 Content Safety$0.2/M outcompletion: 0.0000002 / token (endpoint deepinfra/bf16)
OpenRouterOfficialOpenAI: GPT-4.1 Nano (batch)$0.2/M outcompletion: 0.0000002 / token (endpoint openai)
OpenRouterOfficialOpenAI: GPT-5 Nano (batch)$0.2/M outcompletion: 0.0000002 / token (endpoint openai)
OpenRouterOfficialReka Flash 3$0.2/M outcompletion: 0.0000002 / token (endpoint reka)
OpenRouterOfficialUpstage: Solar Mini 4via Upstage · zdr$0.2/M outcompletion: 0.0000002 / token (endpoint upstage/zdr)
OpenRouterThird-partyMeta: Llama 3.2 1B Instruct$0.201/M outcompletion: 0.000000201 / token (endpoint cloudflare)
OpenRouterThird-partyQwen: Qwen3.6 35B A3Bvia PrimeIntellect · fp8$0.213/M outcompletion: 0.000000213 / token (endpoint primeintellect/fp8)
OpenRouterThird-partyQwen: Qwen3 14Bvia NextBit · int4$0.22/M outcompletion: 0.00000022 / token (endpoint nextbit/int4)
OpenRouterOfficialInference.net: Schematron V2 Smallvia InferenceNet · bf16$0.23/M outcompletion: 0.00000023 / token (endpoint inference-net/bf16)
OpenRouterOfficialAmazon: Nova Lite 1.0via Amazon Bedrock$0.24/M outcompletion: 0.00000024 / token (endpoint amazon-bedrock)
OpenRouterThird-partyNVIDIA: Nemotron 3 Nano 30B A3B$0.24/M outcompletion: 0.00000024 / token (endpoint nebius/fp8)
OpenRouterOfficialAnthropic: Claude Haiku 5.5 (batch)$0.25/M outcompletion: 0.00000025 / token (endpoint anthropic)
OpenRouterOfficialNex AGI: Nex-N2.5-Pro$0.25/M outcompletion: 0.00000025 / token (endpoint nex-agi/fp8)
OpenRouterOfficialOpenAI: GPT-6 Luna Pro (batch)$0.25/M outcompletion: 0.00000025 / token (endpoint openai)
OpenRouterOfficialOpenAI: GPT-6 Luna (batch)$0.25/M outcompletion: 0.00000025 / token (endpoint openai)
OpenRouterOfficialQwen: Qwen3.5-Flash$0.26/M outcompletion: 0.00000026 / token (endpoint alibaba)
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)
OpenRouterThird-partyXiaomi: MiMo-V2.6-Flashvia Darkbloom · fp4$0.28/M outcompletion: 0.00000028 / token (endpoint darkbloom/fp4)
OpenRouterOfficialTencent: Hy-MT2-30B-A3B$0.295/M outcompletion: 0.000000295 / token (endpoint tencent/fp8)
OpenRouterOfficialTencent: Hy-MT2-7B$0.295/M outcompletion: 0.000000295 / token (endpoint tencent/fp8)
OpenRouterThird-partyMeta: Llama 4 Scoutvia DeepInfra · fp8$0.3/M outcompletion: 0.0000003 / token (endpoint deepinfra/fp8)
OpenRouterOfficialMistral: Voxtral Small 24B 2507$0.3/M outcompletion: 0.0000003 / token
OpenRouterOfficialOpenAI: GPT-4o-mini (batch)$0.3/M outcompletion: 0.0000003 / token (endpoint openai)
OpenRouterThird-partyOpenAI: gpt-oss-safeguard-20b$0.3/M outcompletion: 0.0000003 / token
OpenRouterThird-partyQwen: Qwen3 30B A3B Instruct 2507via DekaLLM$0.3/M outcompletion: 0.0000003 / token (endpoint dekallm)
OpenRouterThird-partyRicursive: Ripple 65B Previewvia PrimeIntellect · bf16$0.3/M outcompletion: 0.0000003 / token (endpoint primeintellect/bf16)
OpenRouterThird-partyStepFun: Step 3.5 Flash$0.3/M outcompletion: 0.0000003 / token (endpoint siliconflow/fp8)
OpenRouterNot disclosedDeepSeek: DeepSeek V4 Flash Latest$0.3/M outcompletion: 0.0000003 / token
OpenRouterThird-partyDeepSeek: DeepSeek V3.2via GMICloud · fp8$0.31/M outcompletion: 0.0000003096 / token (endpoint gmicloud/fp8)
OpenRouterThird-partyMeta: Llama 3.3 70B InstructTurbovia DeepInfra$0.32/M outcompletion: 0.00000032 / token (endpoint deepinfra/turbo)
OpenRouterThird-partyMeta: Llama 3.2 3B Instructvia Parasail · bf16$0.33/M outcompletion: 0.00000033 / token (endpoint parasail/bf16)
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)
OpenRouterThird-partyDeepSeek: DeepSeek V4.1 Flash (batch)$0.336/M outcompletion: 0.000000336 / token (endpoint deepinfra/fp8)
OpenRouterNot disclosedGoogle: Gemma 4 31Bvia KT$0.34/M outcompletion: 0.00000034 / token (endpoint kt)
OpenRouterThird-partyNVIDIA: Nemotron 3.5 Super VLvia Darkbloom · nvfp4$0.35/M outcompletion: 0.00000035 / token (endpoint darkbloom/nvfp4)
OpenRouterOfficialOpenAI: GPT-6 Luna Pro (batch)Prompt > 272K$0.375/M outcompletion: 0.000000375 / token (>272000; endpoint openai)
OpenRouterOfficialOpenAI: GPT-6 Luna (batch)Prompt > 272K$0.375/M outcompletion: 0.000000375 / token (>272000; endpoint openai)
OpenRouterOfficialByteDance Seed: Seed-2.0-Mini$0.4/M outcompletion: 0.0000004 / token (endpoint seed/fp8)
OpenRouterThird-partyDeepSeek: DeepSeek V4.1 Flashvia Morph · fp8$0.4/M outcompletion: 0.0000004 / token (endpoint morph/fp8)
OpenRouterThird-partyDeepSeek: DeepSeek V4.1 Flash 1017via Morph · fp8$0.4/M outcompletion: 0.0000004 / token (endpoint morph/fp8)
OpenRouterOfficialGoogle: Gemini 2.5 Flash Litevia Google AI Studio$0.4/M outcompletion: 0.0000004 / token (endpoint google-ai-studio)
OpenRouterOfficialGoogle: Gemini 2.5 Flash LiteReasoningvia Google AI Studio$0.4/M outinternal_reasoning: 0.0000004 / token (endpoint google-ai-studio)
OpenRouterOfficialNex AGI: Nex-N2.6$0.4/M outcompletion: 0.0000004 / token (endpoint nex-agi/fp8)
OpenRouterThird-partyNVIDIA: Nemotron 3 Supervia DeepInfra · bf16$0.4/M outcompletion: 0.0000004 / token (endpoint deepinfra/bf16)
OpenRouterOfficial partnerOpenAI: GPT-4.1 Nanovia Azure$0.4/M outcompletion: 0.0000004 / token (endpoint azure)
OpenRouterOfficial partnerOpenAI: GPT-5 Nanovia Azure$0.4/M outcompletion: 0.0000004 / token (endpoint azure)
OpenRouterThird-partyQwen2.5 72B Instruct$0.4/M outcompletion: 0.0000004 / token (endpoint deepinfra/fp8)
OpenRouterOfficialQwen: Qwen3.7 FlashPrompt > 32Kvia Alibaba$0.4/M outcompletion: 0.0000004 / token (>32000; endpoint alibaba)
OpenRouterThird-partyTheDrummer: UnslopNemo 12B$0.4/M outcompletion: 0.0000004 / token (endpoint parasail/bf16)
OpenRouterThird-partyZ.ai: GLM 4.7 Flashvia Cloudflare$0.4/M outcompletion: 0.0000004 / token (endpoint cloudflare)
OpenRouterThird-partyDeepSeek: DeepSeek V3.2 Exp$0.41/M outcompletion: 0.00000041 / token (endpoint siliconflow/fp8)
OpenRouterThird-partyQwen: Qwen3.8 27Bvia PrimeIntellect · fp8$0.44/M outcompletion: 0.00000044 / token (endpoint primeintellect/fp8)
OpenRouterThird-partyMiniMax: MiniMax M3.1 Flashvia GMICloud · fp8$0.45/M outcompletion: 0.00000045 / token (endpoint gmicloud/fp8)
OpenRouterOfficialQwen: Qwen3.8 Flashvia Alibaba$0.47/M outcompletion: 0.00000047 / token (endpoint alibaba)
OpenRouterOfficialQwen: Qwen3.8 Omni Flash$0.47/M outcompletion: 0.00000047 / token (endpoint alibaba)
OpenRouterOfficial partnerAnthropic: Claude Haiku 5.5via Google · global$0.5/M outcompletion: 0.0000005 / token (endpoint google-vertex/global)
OpenRouterOfficialLiquidAI: LFM2.5-2.6B$0.5/M outcompletion: 0.0000005 / token (endpoint liquid/fp8)
OpenRouterOfficialMancer: Weaver (alpha)$0.5/M outcompletion: 0.0000005 / token (endpoint mancer/fp8)
OpenRouterThird-partyMeta: Muse Embervia Google · global$0.5/M outcompletion: 0.0000005 / token (endpoint google-vertex/global)
OpenRouterOfficial partnerOpenAI: GPT-6 Lunavia Amazon Bedrock · global$0.5/M outcompletion: 0.0000005 / token (endpoint amazon-bedrock/global)
OpenRouterOfficial partnerOpenAI: GPT-6 Luna Provia OpenAI$0.5/M outcompletion: 0.0000005 / token (endpoint openai)
OpenRouterOfficialParticle AI: Particle-1$0.5/M outcompletion: 0.0000005 / token
OpenRouterThird-partyPrismML: Ternary Bonsai 2 27B$0.5/M outcompletion: 0.0000005 / token (endpoint darkbloom/int4)
OpenRouterThird-partyQwen: Qwen3 30B A3B$0.5/M outcompletion: 0.0000005 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyTheDrummer: Cydonia 24B V4.1$0.5/M outcompletion: 0.0000005 / token (endpoint parasail/bf16)
OpenRouterThird-partyReMM SLERP 13B$0.5/M outcompletion: 0.0000005 / token (endpoint mancer/fp8)
OpenRouterNot disclosedAnthropic: Claude Haiku Latest$0.5/M outcompletion: 0.0000005 / token
OpenRouterNot disclosedDeepSeek: DeepSeek Flash Latest$0.5/M outcompletion: 0.0000005 / token
OpenRouterNot disclosedOpenAI: GPT Luna Latest$0.5/M outcompletion: 0.0000005 / token
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)
OpenRouterThird-partyMistral: Mistral Small 3.1 24B$0.555/M outcompletion: 0.000000555 / token (endpoint cloudflare)
OpenRouterThird-partyTencent: Hunyuan A13B Instruct$0.57/M outcompletion: 0.00000057 / token (endpoint siliconflow/fp8)
OpenRouterOfficialCohere: Command R (08-2024)$0.6/M outcompletion: 0.0000006 / token (endpoint cohere)
OpenRouterOfficialMistral: Sabavia Mistral · zdr$0.6/M outcompletion: 0.0000006 / token (endpoint mistral/zdr)
OpenRouterOfficialMistral: Mistral Small 4via Mistral · zdr$0.6/M outcompletion: 0.0000006 / token (endpoint mistral/zdr)
OpenRouterOfficialMorph: Morph V3 Fast (batch)$0.6/M outcompletion: 0.0000006 / token
OpenRouterOfficial partnerOpenAI: GPT-4o-minivia Azure$0.6/M outcompletion: 0.0000006 / token (endpoint azure)
OpenRouterOfficialOpenAI: GPT-4o-mini (2024-07-18)$0.6/M outcompletion: 0.0000006 / token (endpoint openai)
OpenRouterOfficialOpenAI: GPT-5.6 Luna Pro (batch)$0.6/M outcompletion: 0.0000006 / token (endpoint openai)
OpenRouterOfficialOpenAI: GPT-5.6 Luna (batch)$0.6/M outcompletion: 0.0000006 / token (endpoint openai)