[{"slug":"inference-provider-index","chart":{"id":"provider-prices-gpt-oss-120b","title":"gpt-oss-120b: price per million tokens by provider","subtitle":"Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","kind":"grouped-bar","unit":"usd","yLabel":"USD per million tokens","series":{"$k":["name","points"],"$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]]}]]},"note":"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.","factContext":"gpt-oss-120b · reported by OpenRouter’s public API, snapshot 2026-10-06","sourceIds":["openrouter-api-snapshot"]}},{"slug":"inference-provider-index","chart":{"id":"provider-prices-llama-3-3-70b-instruct","title":"Llama 3.3 70B Instruct: price per million tokens by provider","subtitle":"Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06","kind":"grouped-bar","unit":"usd","yLabel":"USD per million tokens","series":{"$k":["name","points"],"$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]]}]]},"note":"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.","factContext":"Llama 3.3 70B Instruct · reported by OpenRouter’s public API, snapshot 2026-10-06","sourceIds":["openrouter-api-snapshot"]}}]