Skip to content
API Pricing

11,193 prices on 4,854 listings · last collected 17 min 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 1–100 of 558

Per million output tokens100

PlatformModel · what it coversUSDPlatform’s own wordingSince
OpenRouterOfficialBaidu: ERNIE-5.5-Flash-Preview (free)$0/M outCheapestcompletion: 0 / token (endpoint baidu)
OpenRouterOfficialCohere: North Mini Code (free)$0/M outCheapestcompletion: 0 / token (endpoint cohere)
OpenRouterThird-partyDots Studio: Dots3-Note Preview (free)$0/M outCheapestcompletion: 0 / token (endpoint atlas-cloud/fp8)
OpenRouterOfficialGoogle: Gemma 4 26B A4B (free)$0/M outCheapestcompletion: 0 / token (endpoint google-ai-studio)
OpenRouterOfficialGoogle: Gemma 4 31B (free)$0/M outCheapestcompletion: 0 / token (endpoint google-ai-studio)
OpenRouterOfficialLiquidAI: LFM2.5-2.6B (free)$0/M outCheapestcompletion: 0 / token (endpoint liquid/fp8)
OpenRouterOfficialLiquidAI: LFM3-1.7B (free)$0/M outCheapestcompletion: 0 / token (endpoint liquid/fp8)
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)
OpenRouterOfficialNVIDIA: Nemotron 3.5 Lightning (free)$0/M outCheapestcompletion: 0 / token (endpoint nvidia/nvfp4)
OpenRouterOfficialNVIDIA: Nemotron 3.5 Super VL (free)$0/M outCheapestcompletion: 0 / token
OpenRouterNot disclosedFree Models Router$0/M outCheapestcompletion: 0 / token
OpenRouterOfficialRecursive: Flint (free)$0/M outCheapestcompletion: 0 / token (endpoint recursive/bf16)
OpenRouterOfficialScaleDown: Extract$0/M outCheapestcompletion: 0 / token (endpoint scaledown)
OpenRouterOfficialScaleDown: Summarize$0/M outCheapestcompletion: 0 / token (endpoint scaledown)
OpenRouterOfficialThinking Machines: Inkling 2 Small (free)$0/M outCheapestcompletion: 0 / token (endpoint thinkingmachines/nvfp4)
OpenRouterThird-partyMistral: Mistral Nemovia Io Net · fp16$0.022/M outcompletion: 0.0000000216 / token (endpoint io-net/fp16)
OpenRouterThird-partyOpenAI: gpt-oss-20bvia PrimeIntellect · fp4$0.032/M outcompletion: 0.000000032 / token (endpoint primeintellect/fp4)
OpenRouterThird-partyMeta: Llama 3.1 8B Instructvia DeepInfra · fp8$0.04/M outcompletion: 0.00000004 / token (endpoint deepinfra/fp8)
OpenRouterOfficialinclusionAI: Ling 3.0 Tiny$0.045/M outcompletion: 0.000000045 / token (endpoint antdigital/fp8)
OpenRouterThird-partyGoogle: Gemma 4 26B A4B via PrimeIntellect · bf16$0.049/M outcompletion: 0.000000049 / token (endpoint primeintellect/bf16)
OpenRouterThird-partyGoogle: Gemma 3 4Bvia Parasail · bf16$0.05/M outcompletion: 0.00000005 / token (endpoint parasail/bf16)
OpenRouterThird-partySao10K: Llama 3 8B Lunarisvia Parasail · bf16$0.05/M outcompletion: 0.00000005 / token (endpoint parasail/bf16)
OpenRouterThird-partyZ.ai: GLM 5.3 Flash (batch)via Morph · fp8$0.061/M outcompletion: 0.000000061 / token (endpoint morph/fp8)
OpenRouterThird-partyinclusionAI: Ling 3.0 Flashvia Novita$0.063/M outcompletion: 0.000000063 / token (endpoint novita)
OpenRouterThird-partyOpenAI: gpt-oss-120bvia PrimeIntellect · fp4$0.076/M outcompletion: 0.000000076 / token (endpoint primeintellect/fp4)
OpenRouterNot disclosedZ.ai: GLM 5.3 Flashvia Relace · fp4$0.078/M outcompletion: 0.0000000784 / token (endpoint relace/fp4)
OpenRouterNot disclosedZ.ai: GLM Flash Latest$0.078/M outcompletion: 0.0000000784 / token
OpenRouterThird-partyMistral: Mistral Small 3$0.08/M outcompletion: 0.00000008 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyDeepSeek: DeepSeek V4 Flash 0423via Baidu · fp8$0.1/M outcompletion: 0.00000009996 / token (endpoint baidu/fp8)
OpenRouterOfficialMistral: Ministral 3 3B 2512via Mistral · zdr$0.1/M outcompletion: 0.0000001 / token (endpoint mistral/zdr)
OpenRouterOfficialNex AGI: Nex-N2.5-Mini$0.1/M outcompletion: 0.0000001 / token
OpenRouterOfficialReka Edge$0.1/M outcompletion: 0.0000001 / token (endpoint reka)
OpenRouterThird-partyMythoMax 13Bvia Parasail · fp16$0.11/M outcompletion: 0.00000011 / token (endpoint parasail/fp16)
OpenRouterThird-partyOpenAI: gpt-oss-20b (batch)$0.112/M outcompletion: 0.000000112 / token (endpoint deepinfra/bf16)
OpenRouterThird-partyNVIDIA: Nemotron 3.5 Lightningvia Darkbloom · int4$0.12/M outcompletion: 0.00000012 / token (endpoint darkbloom/int4)
OpenRouterThird-partyPrismML: Ternary Bonsai 2 9B$0.13/M outcompletion: 0.00000013 / token (endpoint darkbloom/int4)
OpenRouterThird-partyQwen: Qwen3.5-9Bvia Darkbloom · fp4$0.13/M outcompletion: 0.00000013 / token (endpoint darkbloom/fp4)
OpenRouterOfficialQwen: Qwen3.7 Flashvia Alibaba$0.13/M outcompletion: 0.00000013 / token (endpoint alibaba)
OpenRouterThird-partyinclusionAI: Ling 3.1 Flash$0.135/M outcompletion: 0.000000135 / token (endpoint novita)
OpenRouterThird-partyOpenAI: gpt-oss-120b (batch)$0.136/M outcompletion: 0.000000136 / token (endpoint deepinfra/bf16)
OpenRouterOfficialAmazon: Nova Micro 1.0via Amazon Bedrock$0.14/M outcompletion: 0.00000014 / token (endpoint amazon-bedrock)
OpenRouterThird-partyDeepSeek: DeepSeek V4 Flash 0731via Relace · fp4$0.14/M outcompletion: 0.00000014 / token (endpoint relace/fp4)
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)