{"i":12,"study":{"slug":"inference-provider-index","title":"Inference provider index: 27 models, 52 providers","seoTitle":"Inference provider prices: OpenRouter vs direct","description":"Price per million tokens for 27 models across 52 providers, the spread between them and OpenRouter’s markup over first-party prices.","question":"For the same model, how much do inference providers differ in price, and what does a gateway such as OpenRouter add over the first-party list price?","answer":"OpenRouter’s public API listed 265 endpoints from 52 providers for 27 models on 2026-10-06. For 10 of the 10 models with a first-party list price, OpenRouter’s per-token price was the same as the vendor’s; the cost of the gateway is the 5.5% credit-purchase fee (Standard plan, third-party-reported), so the effective markup is +5.5%. 15 of 15 closed models (Claude, GPT, Gemini) with 2 or more providers had one price across every standard-tier provider; their price differences come from named tiers (flex, priority, fast) and regional endpoints. Open-weight models differ by provider: DeepSeek V4 Flash 0423 12.6x (15 providers), DeepSeek V4 Pro 0423 11.2x (15 providers), gpt-oss-120b 6.9x (20 providers), Llama 3.3 70B Instruct 6.7x (10 providers) between the most expensive and the cheapest standard-tier provider (a calculation on reported prices). The cheapest endpoints often report lower precision or a shorter context. Latency and throughput were not in the keyless API (0 of 265 endpoints), and the gateway’s own delay is not measured: no key in the environment.","date":"2026-10-06","updated":"2026-10-06","tags":["inference","providers","openrouter","pricing","gateway","open-weight","third-party-reported"],"caveats":["Every price is third-party-reported by OpenRouter’s API at 2026-10-06. Prices change often; refetch before relying on them.","A provider listed on OpenRouter is reached through OpenRouter; its price there may differ from the price on the provider’s own site.","The cheapest endpoint may run lower precision (fp4 or fp8) or a shorter context. Price alone does not make two endpoints equal.","No latency or throughput figure: the keyless API returned none. A cheaper provider is not shown to be slower or faster.","First-party prices in the product table were verified on an earlier date than the snapshot; a vendor price change in between would show as a markup.","Comparison rows between providers name no winner: a price has no interval, so the rule for winners does not apply. The gap is stated."],"sourceIds":["openrouter-api-snapshot","openrouter-fees","price-anthropic","price-openai","price-google"],"stats":{"$k":["id","label","value","unit","display","n","note"],"$r":[["provider-index-endpoints","Provider endpoints in the snapshot",265,"count","265 endpoints, 52 providers, 27 models",27,"\u0001"],["provider-index-max-spread","Largest standard-tier price spread (DeepSeek V4 Flash 0423)",12.57,"ratio","12.6x (most expensive: Cloudflare; cheapest: StreamLake (fp8))",15,"Calculation on reported prices, blended 3:1."],["gateway-zero-markup-models","Models where OpenRouter’s per-token price equals the first-party list price",10,"count","10 of 10",10,"\u0001"],["gateway-credit-fee","Credit-purchase fee on OpenRouter’s Standard plan (third-party-reported)",5.5,"percent","5.5% ($0.80 minimum by card)","\u0001","\u0001"],["provider-index-latency-reported","Endpoints with a latency figure in the keyless API",0,"count","0 of 265",265,"\u0001"]]},"charts":{"$k":["id","title","subtitle","kind","unit","yLabel","series","note","sourceIds","factContext"],"$r":[["provider-index-spread","How much more the priciest provider charges than the cheapest","Standard tier, blended price (3 input : 1 output), most expensive provider ÷ cheapest provider","bar","ratio","Most expensive ÷ cheapest",[{"name":"Price spread","points":{"$k":["label","value","n","highlight"],"$r":[["DeepSeek V4 Flash 0423",12.57,15,true],["DeepSeek V4 Pro 0423",11.21,15,true],["gpt-oss-120b",6.92,20,true],["Llama 3.3 70B Instruct",6.71,10,true],["GLM 5.3",4.69,32,true],["Kimi K3",1.78,19,false],["Llama 4 Maverick",1.69,3,false],["Claude Haiku 4.5",1,4,false],["Claude Sonnet 5",1,5,false],["Claude Sonnet 5.5",1,5,false],["Claude Opus 4.8",1,5,false],["Claude Opus 5",1,5,false],["Claude Opus 5.5",1,5,false],["Claude Fable 5.1",1,4,false],["GPT-6 Sol",1,2,false],["GPT-6 Luna",1,2,false],["GPT-6 Astra",1,2,false],["GPT-5.5",1,2,false],["Gemini 3.8 Flash",1,2,false],["Gemini 3.5 Flash",1,2,false],["Gemini 3.5 Flash Lite",1,2,false],["Gemini 3.1 Pro Preview",1,2,false]]}}],"A calculation on prices reported by OpenRouter’s public API, snapshot 2026-10-06. n = providers with a standard-tier endpoint. 1x means every provider charges the same. Highlighted: a spread of 4x or more.",["openrouter-api-snapshot"],"\u0001"],["gateway-markup-vs-first-party","OpenRouter markup over the first-party list price","Per-token markup, and the markup after the Standard credit-purchase fee (calculation)","grouped-bar","percent","Markup (%)",{"$k":["name","points"],"$r":[["Per-token markup (input)",{"$k":["label","value"],"$r":[["Claude Haiku 4.5",0],["Claude Sonnet 5",0],["Claude Sonnet 5.5",0],["Claude Opus 4.8",0],["Claude Opus 5",0],["Claude Opus 5.5",0],["Claude Fable 5.1",0],["GPT-6 Luna",0],["Gemini 3.8 Flash",0],["Gemini 3.5 Flash",0]]}],["Per-token markup (output)",{"$k":["label","value"],"$r":[["Claude Haiku 4.5",0],["Claude Sonnet 5",0],["Claude Sonnet 5.5",0],["Claude Opus 4.8",0],["Claude Opus 5",0],["Claude Opus 5.5",0],["Claude Fable 5.1",0],["GPT-6 Luna",0],["Gemini 3.8 Flash",0],["Gemini 3.5 Flash",0]]}],["With the 5.5% card credit fee (input)",{"$k":["label","value"],"$r":[["Claude Haiku 4.5",5.5],["Claude Sonnet 5",5.5],["Claude Sonnet 5.5",5.5],["Claude Opus 4.8",5.5],["Claude Opus 5",5.5],["Claude Opus 5.5",5.5],["Claude Fable 5.1",5.5],["GPT-6 Luna",5.5],["Gemini 3.8 Flash",5.5],["Gemini 3.5 Flash",5.5]]}]]},"A calculation: OpenRouter list price ÷ first-party list price − 1, then × (1 + 5.5%) for credits bought by card on the Standard plan (purchases large enough that the minimum fee does not apply). Fees as published on 2026-10-06; first-party prices from the vendors’ list prices.",["openrouter-api-snapshot","openrouter-fees","price-anthropic","price-openai","price-google"],"\u0001"],["gateway-vs-direct-claude-haiku-4-5","Claude Haiku 4.5: OpenRouter vs Anthropic list price","USD per million tokens, before any credit-purchase fee","grouped-bar","usd","USD per million tokens",[{"name":"Input","points":[{"label":"OpenRouter","value":1},{"label":"Anthropic (first-party list price)","value":1}]},{"name":"Output","points":[{"label":"OpenRouter","value":5},{"label":"Anthropic (first-party list price)","value":5}]}],"OpenRouter price reported by OpenRouter’s public API, snapshot 2026-10-06. Anthropic price from the vendor’s published list price as recorded in the product price table. OpenRouter charges a 5.5% fee when credits are bought, not per request; the markup chart shows the price with that fee.",["openrouter-api-snapshot","price-anthropic"],"Claude Haiku 4.5 · list price, snapshot 2026-10-06"],["gateway-vs-direct-claude-sonnet-5","Claude Sonnet 5: OpenRouter vs Anthropic list price","USD per million tokens, before any credit-purchase fee","grouped-bar","usd","USD per million tokens",[{"name":"Input","points":[{"label":"OpenRouter","value":2},{"label":"Anthropic (first-party list price)","value":2}]},{"name":"Output","points":[{"label":"OpenRouter","value":10},{"label":"Anthropic (first-party list price)","value":10}]}],"OpenRouter price reported by OpenRouter’s public API, snapshot 2026-10-06. Anthropic price from the vendor’s published list price as recorded in the product price table. OpenRouter charges a 5.5% fee when credits are bought, not per request; the markup chart shows the price with that fee.",["openrouter-api-snapshot","price-anthropic"],"Claude Sonnet 5 · list price, snapshot 2026-10-06"],["gateway-vs-direct-claude-sonnet-5-5","Claude Sonnet 5.5: OpenRouter vs Anthropic list price","USD per million tokens, before any credit-purchase fee","grouped-bar","usd","USD per million tokens",[{"name":"Input","points":[{"label":"OpenRouter","value":2},{"label":"Anthropic (first-party list price)","value":2}]},{"name":"Output","points":[{"label":"OpenRouter","value":10},{"label":"Anthropic (first-party list price)","value":10}]}],"OpenRouter price reported by OpenRouter’s public API, snapshot 2026-10-06. Anthropic price from the vendor’s published list price as recorded in the product price table. OpenRouter charges a 5.5% fee when credits are bought, not per request; the markup chart shows the price with that fee.",["openrouter-api-snapshot","price-anthropic"],"Claude Sonnet 5.5 · list price, snapshot 2026-10-06"],["gateway-vs-direct-claude-opus-4-8","Claude Opus 4.8: OpenRouter vs Anthropic list price","USD per million tokens, before any credit-purchase fee","grouped-bar","usd","USD per million tokens",[{"name":"Input","points":[{"label":"OpenRouter","value":5},{"label":"Anthropic (first-party list price)","value":5}]},{"name":"Output","points":[{"label":"OpenRouter","value":25},{"label":"Anthropic (first-party list price)","value":25}]}],"OpenRouter price reported by OpenRouter’s public API, snapshot 2026-10-06. Anthropic price from the vendor’s published list price as recorded in the product price table. OpenRouter charges a 5.5% fee when credits are bought, not per request; the markup chart shows the price with that fee.",["openrouter-api-snapshot","price-anthropic"],"Claude Opus 4.8 · list price, snapshot 2026-10-06"],["gateway-vs-direct-claude-opus-5","Claude Opus 5: OpenRouter vs Anthropic list price","USD per million tokens, before any credit-purchase fee","grouped-bar","usd","USD per million tokens",[{"name":"Input","points":[{"label":"OpenRouter","value":5},{"label":"Anthropic (first-party list price)","value":5}]},{"name":"Output","points":[{"label":"OpenRouter","value":25},{"label":"Anthropic (first-party list price)","value":25}]}],"OpenRouter price reported by OpenRouter’s public API, snapshot 2026-10-06. Anthropic price from the vendor’s published list price as recorded in the product price table. OpenRouter charges a 5.5% fee when credits are bought, not per request; the markup chart shows the price with that fee.",["openrouter-api-snapshot","price-anthropic"],"Claude Opus 5 · list price, snapshot 2026-10-06"],["gateway-vs-direct-claude-opus-5-5","Claude Opus 5.5: OpenRouter vs Anthropic list price","USD per million tokens, before any credit-purchase fee","grouped-bar","usd","USD per million tokens",[{"name":"Input","points":[{"label":"OpenRouter","value":4},{"label":"Anthropic (first-party list price)","value":4}]},{"name":"Output","points":[{"label":"OpenRouter","value":20},{"label":"Anthropic (first-party list price)","value":20}]}],"OpenRouter price reported by OpenRouter’s public API, snapshot 2026-10-06. Anthropic price from the vendor’s published list price as recorded in the product price table. OpenRouter charges a 5.5% fee when credits are bought, not per request; the markup chart shows the price with that fee.",["openrouter-api-snapshot","price-anthropic"],"Claude Opus 5.5 · list price, snapshot 2026-10-06"],["gateway-vs-direct-claude-fable-5-1","Claude Fable 5.1: OpenRouter vs Anthropic list price","USD per million tokens, before any credit-purchase fee","grouped-bar","usd","USD per million tokens",[{"name":"Input","points":[{"label":"OpenRouter","value":10},{"label":"Anthropic (first-party list price)","value":10}]},{"name":"Output","points":[{"label":"OpenRouter","value":50},{"label":"Anthropic (first-party list price)","value":50}]}],"OpenRouter price reported by OpenRouter’s public API, snapshot 2026-10-06. Anthropic price from the vendor’s published list price as recorded in the product price table. OpenRouter charges a 5.5% fee when credits are bought, not per request; the markup chart shows the price with that fee.",["openrouter-api-snapshot","price-anthropic"],"Claude Fable 5.1 · list price, snapshot 2026-10-06"],["gateway-vs-direct-gpt-6-luna","GPT-6 Luna: OpenRouter vs OpenAI list price","USD per million tokens, before any credit-purchase fee","grouped-bar","usd","USD per million tokens",[{"name":"Input","points":[{"label":"OpenRouter","value":0.1},{"label":"OpenAI (first-party list price)","value":0.1}]},{"name":"Output","points":[{"label":"OpenRouter","value":0.5},{"label":"OpenAI (first-party list price)","value":0.5}]}],"OpenRouter price reported by OpenRouter’s public API, snapshot 2026-10-06. OpenAI price from the vendor’s published list price as recorded in the product price table. OpenRouter charges a 5.5% fee when credits are bought, not per request; the markup chart shows the price with that fee.",["openrouter-api-snapshot","price-openai"],"GPT-6 Luna · list price, snapshot 2026-10-06"],["gateway-vs-direct-gemini-3-8-flash","Gemini 3.8 Flash: OpenRouter vs Google list price","USD per million tokens, before any credit-purchase fee","grouped-bar","usd","USD per million tokens",[{"name":"Input","points":[{"label":"OpenRouter","value":0.75},{"label":"Google AI Studio (first-party list price)","value":0.75}]},{"name":"Output","points":[{"label":"OpenRouter","value":3.75},{"label":"Google AI Studio (first-party list price)","value":3.75}]}],"OpenRouter price reported by OpenRouter’s public API, snapshot 2026-10-06. Google price from the vendor’s published list price as recorded in the product price table. OpenRouter charges a 5.5% fee when credits are bought, not per request; the markup chart shows the price with that fee.",["openrouter-api-snapshot","price-google"],"Gemini 3.8 Flash · list price, snapshot 2026-10-06"],["gateway-vs-direct-gemini-3-5-flash","Gemini 3.5 Flash: OpenRouter vs Google list price","USD per million tokens, before any credit-purchase fee","grouped-bar","usd","USD per million tokens",[{"name":"Input","points":[{"label":"OpenRouter","value":1.5},{"label":"Google AI Studio (first-party list price)","value":1.5}]},{"name":"Output","points":[{"label":"OpenRouter","value":9},{"label":"Google AI Studio (first-party list price)","value":9}]}],"OpenRouter price reported by OpenRouter’s public API, snapshot 2026-10-06. Google price from the vendor’s published list price as recorded in the product price table. OpenRouter charges a 5.5% fee when credits are bought, not per request; the markup chart shows the price with that fee.",["openrouter-api-snapshot","price-google"],"Gemini 3.5 Flash · list price, snapshot 2026-10-06"],["provider-prices-claude-haiku-4-5","Claude Haiku 4.5: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",{"$k":["label","value"],"$r":[["Amazon Bedrock",1],["Anthropic",1],["Azure",1],["Google Vertex",1]]}],["Output",{"$k":["label","value"],"$r":[["Amazon Bedrock",5],["Anthropic",5],["Azure",5],["Google Vertex",5]]}],["Cache read",{"$k":["label","value"],"$r":[["Amazon Bedrock",0.1],["Anthropic",0.1],["Azure",0.1],["Google Vertex",0.1]]}]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"Claude Haiku 4.5 · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-claude-sonnet-5","Claude Sonnet 5: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",{"$k":["label","value"],"$r":[["Amazon Bedrock",2],["Anthropic",2],["Azure",2],["Claude Platform on AWS",2],["Google Vertex",2]]}],["Output",{"$k":["label","value"],"$r":[["Amazon Bedrock",10],["Anthropic",10],["Azure",10],["Claude Platform on AWS",10],["Google Vertex",10]]}],["Cache read",{"$k":["label","value"],"$r":[["Amazon Bedrock",0.2],["Anthropic",0.2],["Azure",0.2],["Claude Platform on AWS",0.2],["Google Vertex",0.2]]}]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"Claude Sonnet 5 · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-claude-sonnet-5-5","Claude Sonnet 5.5: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",{"$k":["label","value"],"$r":[["Amazon Bedrock",2],["Anthropic",2],["Azure",2],["Claude Platform on AWS",2],["Google Vertex",2]]}],["Output",{"$k":["label","value"],"$r":[["Amazon Bedrock",10],["Anthropic",10],["Azure",10],["Claude Platform on AWS",10],["Google Vertex",10]]}],["Cache read",{"$k":["label","value"],"$r":[["Amazon Bedrock",0.2],["Anthropic",0.2],["Azure",0.2],["Claude Platform on AWS",0.2],["Google Vertex",0.2]]}]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"Claude Sonnet 5.5 · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-claude-opus-4-8","Claude Opus 4.8: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",{"$k":["label","value"],"$r":[["Amazon Bedrock",5],["Anthropic",5],["Azure",5],["Claude Platform on AWS",5],["Google Vertex",5]]}],["Output",{"$k":["label","value"],"$r":[["Amazon Bedrock",25],["Anthropic",25],["Azure",25],["Claude Platform on AWS",25],["Google Vertex",25]]}],["Cache read",{"$k":["label","value"],"$r":[["Amazon Bedrock",0.5],["Anthropic",0.5],["Azure",0.5],["Claude Platform on AWS",0.5],["Google Vertex",0.5]]}]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"Claude Opus 4.8 · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-claude-opus-5","Claude Opus 5: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",{"$k":["label","value"],"$r":[["Amazon Bedrock",5],["Anthropic",5],["Azure",5],["Claude Platform on AWS",5],["Google Vertex",5]]}],["Output",{"$k":["label","value"],"$r":[["Amazon Bedrock",25],["Anthropic",25],["Azure",25],["Claude Platform on AWS",25],["Google Vertex",25]]}],["Cache read",{"$k":["label","value"],"$r":[["Amazon Bedrock",0.5],["Anthropic",0.5],["Azure",0.5],["Claude Platform on AWS",0.5],["Google Vertex",0.5]]}]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"Claude Opus 5 · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-claude-opus-5-5","Claude Opus 5.5: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",{"$k":["label","value"],"$r":[["Amazon Bedrock",4],["Anthropic",4],["Azure",4],["Claude Platform on AWS",4],["Google Vertex",4]]}],["Output",{"$k":["label","value"],"$r":[["Amazon Bedrock",20],["Anthropic",20],["Azure",20],["Claude Platform on AWS",20],["Google Vertex",20]]}],["Cache read",{"$k":["label","value"],"$r":[["Amazon Bedrock",0.2],["Anthropic",0.2],["Azure",0.2],["Claude Platform on AWS",0.2],["Google Vertex",0.2]]}]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"Claude Opus 5.5 · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-claude-fable-5-1","Claude Fable 5.1: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",{"$k":["label","value"],"$r":[["Amazon Bedrock",10],["Anthropic",10],["Azure",10],["Google Vertex",10]]}],["Output",{"$k":["label","value"],"$r":[["Amazon Bedrock",50],["Anthropic",50],["Azure",50],["Google Vertex",50]]}],["Cache read",{"$k":["label","value"],"$r":[["Amazon Bedrock",0.25],["Anthropic",0.25],["Azure",0.25],["Google Vertex",0.25]]}]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"Claude Fable 5.1 · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-gpt-6-sol","GPT-6 Sol: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",[{"label":"Azure","value":2},{"label":"OpenAI","value":2}]],["Output",[{"label":"Azure","value":10},{"label":"OpenAI","value":10}]],["Cache read",[{"label":"Azure","value":0.2},{"label":"OpenAI","value":0.2}]]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"GPT-6 Sol · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-gpt-6-luna","GPT-6 Luna: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",[{"label":"Azure","value":0.1},{"label":"OpenAI","value":0.1}]],["Output",[{"label":"Azure","value":0.5},{"label":"OpenAI","value":0.5}]],["Cache read",[{"label":"Azure","value":0.01},{"label":"OpenAI","value":0.01}]]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"GPT-6 Luna · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-gpt-6-astra","GPT-6 Astra: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",[{"label":"Azure","value":10},{"label":"OpenAI","value":10}]],["Output",[{"label":"Azure","value":50},{"label":"OpenAI","value":50}]],["Cache read",[{"label":"Azure","value":1},{"label":"OpenAI","value":1}]]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"GPT-6 Astra · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-gpt-5-5","GPT-5.5: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",[{"label":"Azure","value":5},{"label":"OpenAI","value":5}]],["Output",[{"label":"Azure","value":30},{"label":"OpenAI","value":30}]],["Cache read",[{"label":"Azure","value":0.5},{"label":"OpenAI","value":0.5}]]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"GPT-5.5 · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-gpt-oss-120b","gpt-oss-120b: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",{"$k":["label","value"],"$r":[["CoreWeave (fp4)",0.03],["DekaLLM (bf16)",0.03],["DeepInfra (bf16)",0.037],["AkashML (bf16)",0.037],["Mancer 2 (fp8)",0.045],["Crusoe (bf16)",0.05],["Novita (fp4)",0.05],["DigitalOcean",0.06],["Google Vertex",0.09],["BaseTen (fp4)",0.1],["Amazon Bedrock",0.15],["Groq",0.15],["Nebius (fp4)",0.15],["Phala",0.15],["SiliconFlow (fp8)",0.15],["Together",0.15],["Parasail (fp4)",0.1],["Mara",0.15],["SambaNova",0.14],["Cerebras (fp16)",0.35]]}],["Output",{"$k":["label","value"],"$r":[["CoreWeave (fp4)",0.17],["DekaLLM (bf16)",0.18],["DeepInfra (bf16)",0.17],["AkashML (bf16)",0.187],["Mancer 2 (fp8)",0.25],["Crusoe (bf16)",0.25],["Novita (fp4)",0.25],["DigitalOcean",0.42],["Google Vertex",0.36],["BaseTen (fp4)",0.5],["Amazon Bedrock",0.6],["Groq",0.6],["Nebius (fp4)",0.6],["Phala",0.6],["SiliconFlow (fp8)",0.6],["Together",0.6],["Parasail (fp4)",0.75],["Mara",0.75],["SambaNova",0.95],["Cerebras (fp16)",0.75]]}],["Cache read",{"$k":["label","value"],"$r":[["CoreWeave (fp4)",0.03],["DekaLLM (bf16)",0.03],["AkashML (bf16)",0.037],["Crusoe (bf16)",0.05],["DigitalOcean",0.012],["BaseTen (fp4)",0.1],["Groq",0.075],["SiliconFlow (fp8)",0.075],["Parasail (fp4)",0.055],["Cerebras (fp16)",0.35]]}]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"gpt-oss-120b · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-gemini-3-8-flash","Gemini 3.8 Flash: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",[{"label":"Google AI Studio","value":0.75},{"label":"Google Vertex","value":0.75}]],["Output",[{"label":"Google AI Studio","value":3.75},{"label":"Google Vertex","value":3.75}]],["Cache read",[{"label":"Google AI Studio","value":0.075},{"label":"Google Vertex","value":0.075}]]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"Gemini 3.8 Flash · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-gemini-3-5-flash","Gemini 3.5 Flash: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",[{"label":"Google AI Studio","value":1.5},{"label":"Google Vertex","value":1.5}]],["Output",[{"label":"Google AI Studio","value":9},{"label":"Google Vertex","value":9}]],["Cache read",[{"label":"Google AI Studio","value":0.15},{"label":"Google Vertex","value":0.15}]]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"Gemini 3.5 Flash · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-gemini-3-5-flash-lite","Gemini 3.5 Flash Lite: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",[{"label":"Google AI Studio","value":0.3},{"label":"Google Vertex","value":0.3}]],["Output",[{"label":"Google AI Studio","value":2.5},{"label":"Google Vertex","value":2.5}]],["Cache read",[{"label":"Google AI Studio","value":0.03},{"label":"Google Vertex","value":0.03}]]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"Gemini 3.5 Flash Lite · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-gemini-3-1-pro-preview","Gemini 3.1 Pro Preview: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",[{"label":"Google AI Studio","value":2},{"label":"Google Vertex","value":2}]],["Output",[{"label":"Google AI Studio","value":12},{"label":"Google Vertex","value":12}]],["Cache read",[{"label":"Google AI Studio","value":0.2},{"label":"Google Vertex","value":0.2}]]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"Gemini 3.1 Pro Preview · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-llama-4-maverick","Llama 4 Maverick: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",[{"name":"Input","points":{"$k":["label","value"],"$r":[["DigitalOcean",0.1875],["Novita (fp8)",0.27],["Parasail (fp8)",0.35]]}},{"name":"Output","points":{"$k":["label","value"],"$r":[["DigitalOcean",0.6525],["Novita (fp8)",0.85],["Parasail (fp8)",1]]}}],"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"Llama 4 Maverick · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-llama-3-3-70b-instruct","Llama 3.3 70B Instruct: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",{"$k":["label","value"],"$r":[["DeepInfra (fp8)",0.1],["Novita (bf16)",0.135],["AkashML (fp8)",0.2],["Parasail (fp8)",0.22],["SambaNova",0.45],["Groq",0.59],["CoreWeave (fp16)",0.71],["Google Vertex",0.72],["Cloudflare (fp8)",0.293],["Together",1.04]]}],["Output",{"$k":["label","value"],"$r":[["DeepInfra (fp8)",0.32],["Novita (bf16)",0.4],["AkashML (fp8)",0.52],["Parasail (fp8)",0.5],["SambaNova",0.9],["Groq",0.79],["CoreWeave (fp16)",0.71],["Google Vertex",0.72],["Cloudflare (fp8)",2.253],["Together",1.04]]}],["Cache read",{"$k":["label","value"],"$r":[["AkashML (fp8)",0.1],["Parasail (fp8)",0.11],["Groq",0.295],["CoreWeave (fp16)",0.71]]}]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"Llama 3.3 70B Instruct · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-deepseek-v4-pro","DeepSeek V4 Pro 0423: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",{"$k":["label","value"],"$r":[["StreamLake (fp8)",0.2088],["GMICloud (fp8)",0.957],["Relace (fp4)",0.2067],["Parasail (fp8)",0.45],["DigitalOcean",1.044],["Cloudflare",1.15],["DeepInfra (fp8)",1.3],["Alibaba (fp8)",1.416],["SiliconFlow (fp8)",1.50162],["Novita (fp8)",1.6],["Venice",1.65],["AtlasCloud (fp4)",1.68],["Baidu (fp8)",1.69],["NextBit (fp8)",1.74],["Reka",0.9]]}],["Output",{"$k":["label","value"],"$r":[["StreamLake (fp8)",0.4176],["GMICloud (fp8)",1.914],["Relace (fp4)",4.2],["Parasail (fp8)",3.48],["DigitalOcean",2.088],["Cloudflare",2.55],["DeepInfra (fp8)",2.6],["Alibaba (fp8)",2.832],["SiliconFlow (fp8)",3.135],["Novita (fp8)",3.2],["Venice",3.301],["AtlasCloud (fp4)",3.38],["Baidu (fp8)",3.38],["NextBit (fp8)",3.48],["Reka",9]]}],["Cache read",{"$k":["label","value"],"$r":[["StreamLake (fp8)",0.0174],["GMICloud (fp8)",0.07975],["Relace (fp4)",0.21],["Parasail (fp8)",0.1],["DigitalOcean",0.2088],["Cloudflare",0.2],["DeepInfra (fp8)",0.1],["Alibaba (fp8)",0.118],["SiliconFlow (fp8)",0.135],["Novita (fp8)",0.135],["Venice",0.33],["AtlasCloud (fp4)",0.13],["Baidu (fp8)",0.14],["NextBit (fp8)",0.145],["Reka",0.18]]}]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"DeepSeek V4 Pro 0423 · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-deepseek-v4-flash","DeepSeek V4 Flash 0423: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",{"$k":["label","value"],"$r":[["StreamLake (fp8)",0.042],["DeepInfra (fp8)",0.09],["GMICloud (fp8)",0.091],["Venice",0.0966],["DigitalOcean",0.098],["Alibaba (fp8)",0.134],["SiliconFlow (fp8)",0.13],["AtlasCloud (fp4)",0.14],["Baidu (fp8)",0.14],["Novita (fp8)",0.14],["Parasail (fp8)",0.14],["Mancer 2 (fp8)",0.19],["Relace (fp4)",0.012],["OpenInference (fp4)",0.0132],["Cloudflare",0.44]]}],["Output",{"$k":["label","value"],"$r":[["StreamLake (fp8)",0.084],["DeepInfra (fp8)",0.18],["GMICloud (fp8)",0.182],["Venice",0.1925],["DigitalOcean",0.196],["Alibaba (fp8)",0.268],["SiliconFlow (fp8)",0.28],["AtlasCloud (fp4)",0.28],["Baidu (fp8)",0.28],["Novita (fp8)",0.28],["Parasail (fp8)",0.28],["Mancer 2 (fp8)",0.5],["Relace (fp4)",1.28],["OpenInference (fp4)",1.408],["Cloudflare",1.32]]}],["Cache read",{"$k":["label","value"],"$r":[["StreamLake (fp8)",0.0084],["DeepInfra (fp8)",0.018],["GMICloud (fp8)",0.0182],["Venice",0.0196],["DigitalOcean",0.0196],["Alibaba (fp8)",0.0268],["SiliconFlow (fp8)",0.028],["AtlasCloud (fp4)",0.028],["Baidu (fp8)",0.028],["Novita (fp8)",0.028],["Parasail (fp8)",0.07],["Relace (fp4)",0.012],["OpenInference (fp4)",0.0132],["Cloudflare",0.014]]}]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"DeepSeek V4 Flash 0423 · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-kimi-k3","Kimi K3: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",{"$k":["label","value"],"$r":[["Relace (fp4)",0.83],["Phala",1.95],["Sail Research (fp4)",0.84],["Decart (mxfp4)",2.01],["InferenceNet (fp4)",0.95],["Wafer",0.95],["Morph (fp8)",1.274],["Makora",1.53],["AkashML (fp4)",1.3],["DigitalOcean",2.55],["Together",2.7],["DeepInfra (mxfp4)",2.85],["BaseTen (fp8)",3],["Chutes (mxfp4)",3],["Fireworks",3],["Modal (mxfp4)",3],["Moonshot AI (mxfp4)",3],["Parasail (fp4)",3],["Alibaba",3.45]]}],["Output",{"$k":["label","value"],"$r":[["Relace (fp4)",13],["Phala",9.75],["Sail Research (fp4)",13.5],["Decart (mxfp4)",10.05],["InferenceNet (fp4)",14],["Wafer",14],["Morph (fp8)",13.296],["Makora",12.75],["AkashML (fp4)",14],["DigitalOcean",12.95],["Together",13.5],["DeepInfra (mxfp4)",14.25],["BaseTen (fp8)",15],["Chutes (mxfp4)",15],["Fireworks",15],["Modal (mxfp4)",15],["Moonshot AI (mxfp4)",15],["Parasail (fp4)",15],["Alibaba",17.25]]}],["Cache read",{"$k":["label","value"],"$r":[["Relace (fp4)",0.45],["Phala",0.195],["Sail Research (fp4)",0.3],["Decart (mxfp4)",0.201],["InferenceNet (fp4)",0.31],["Wafer",0.4],["Morph (fp8)",0.278],["Makora",0.204],["AkashML (fp4)",1.3],["DigitalOcean",0.255],["Together",0.27],["DeepInfra (mxfp4)",0.285],["BaseTen (fp8)",0.3],["Chutes (mxfp4)",0.3],["Fireworks",0.3],["Modal (mxfp4)",0.3],["Moonshot AI (mxfp4)",0.3],["Parasail (fp4)",0.3],["Alibaba",0.345]]}]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06"],["provider-prices-glm-5-3","GLM 5.3: price per million tokens by provider","Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","grouped-bar","usd","USD per million tokens",{"$k":["name","points"],"$r":[["Input",{"$k":["label","value"],"$r":[["Novita (fp8)",0.42],["Reka",0.17],["Sail Research (fp8)",0.2],["Morph (fp8)",0.179],["DeepInfra (fp4)",0.5625],["SiliconFlow (fp8)",0.7],["InferenceNet",0.14],["Makora (fp4)",0.18],["AkashML (fp8)",0.19],["Phala",0.84],["Inceptron (fp4)",0.6],["DigitalOcean",0.91],["GMICloud (fp8)",0.98],["Alibaba",1.19],["Decart (fp4)",1.19],["Wafer",0.15],["Friendli",1.26],["AtlasCloud (fp8)",1.4],["Baidu (fp8)",1.4],["BaseTen (fp4)",1.4],["Cloudflare",1.4],["Crusoe (fp4)",1.4],["Fireworks",1.4],["Mistral (nvfp4)",1.4],["Modal",1.4],["Nebius (fp4)",1.4],["Parasail (fp8)",1.4],["PrimeIntellect",1.4],["Together",1.4],["Venice",1.4],["Z.AI (fp8)",1.4],["Relace",0.03]]}],["Output",{"$k":["label","value"],"$r":[["Novita (fp8)",1.32],["Reka",3],["Sail Research (fp8)",3.4],["Morph (fp8)",3.553],["DeepInfra (fp4)",2.5],["SiliconFlow (fp8)",2.2],["InferenceNet",4.4],["Makora (fp4)",4.4],["AkashML (fp8)",4.4],["Phala",2.64],["Inceptron (fp4)",3.39],["DigitalOcean",2.86],["GMICloud (fp8)",3.08],["Alibaba",3.74],["Decart (fp4)",3.74],["Wafer",7],["Friendli",3.96],["AtlasCloud (fp8)",4.4],["Baidu (fp8)",4.4],["BaseTen (fp4)",4.4],["Cloudflare",4.4],["Crusoe (fp4)",4.4],["Fireworks",4.4],["Mistral (nvfp4)",4.4],["Modal",4.4],["Nebius (fp4)",4.4],["Parasail (fp8)",4.4],["PrimeIntellect",4.4],["Together",4.4],["Venice",4.4],["Z.AI (fp8)",4.4],["Relace",12]]}],["Cache read",{"$k":["label","value"],"$r":[["Novita (fp8)",0.078],["Reka",0.169],["Sail Research (fp8)",0.15],["Morph (fp8)",0.137],["DeepInfra (fp4)",0.125],["SiliconFlow (fp8)",0.13],["InferenceNet",0.07],["Makora (fp4)",0.19],["AkashML (fp8)",0.19],["Phala",0.156],["Inceptron (fp4)",0.2],["DigitalOcean",0.169],["GMICloud (fp8)",0.182],["Alibaba",0.238],["Decart (fp4)",0.1955],["Wafer",0.14],["Friendli",0.234],["AtlasCloud (fp8)",0.26],["Baidu (fp8)",0.26],["BaseTen (fp4)",0.14],["Cloudflare",0.26],["Crusoe (fp4)",0.26],["Fireworks",0.26],["Mistral (nvfp4)",0.14],["Modal",0.26],["Parasail (fp8)",0.26],["PrimeIntellect",0.26],["Together",0.26],["Venice",0.26],["Z.AI (fp8)",0.26],["Relace",0.03]]}]]},"Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.",["openrouter-api-snapshot"],"GLM 5.3 · reported by OpenRouter’s public API, snapshot 2026-10-06"]]},"related":["routing-overhead","cost-thought-experiments"]}}