Same open weights, served by 8 providers. Weights: openai/gpt-oss-120b.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | openai/gpt-oss-120b | standardFull precision | $0.037 | $0.17 | — | $0.07 | Verified 5h ago · Changed 7h ago | |
Google Vertex AI | openai/gpt-oss-120b-maas | standardQuantization not disclosed | $0.09 | $0.36 | — | $0.158 | Verified 7h ago · Changed 7h ago | |
DeepInfra | openai/gpt-oss-120b-Turbo | flexFull precision0.8× standard | $0.12 | $0.48 | — | $0.21 | Verified 5h ago · Changed 7h ago | |
DeepInfra | openai/gpt-oss-120b-Turbo | standardFull precision | $0.15 | $0.60 | — | $0.262 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | gpt-oss-120b | standardglobal endpointQuantization not disclosed | $0.15 | $0.60 | — | $0.262 | Verified 5h ago · Changed 7h ago | |
Together AI | openai/gpt-oss-120b | standardQuantization not disclosed | $0.15 | $0.60 | — | $0.262 | Verified 7h ago · Changed 7h ago | |
Fireworks AI | accounts/fireworks/models/gpt-oss-120b | standardQuantization not disclosed | $0.15 | $0.60 | $0.015 | $0.262 | Verified 7h ago · Changed 7h ago | |
Groq | openai/gpt-oss-120b | standardQuantization not disclosed | $0.15 | $0.60 | $0.075 | $0.262 | Verified 7h ago · Changed 7h ago | |
AWS Bedrock | openai.gpt-oss-120b | standardQuantization not disclosed | $0.15 | $0.60 | — | $0.262 | Verified 7h ago · Changed 7h ago | |
AWS Bedrock | openai.gpt-oss-120b-1:0 | standardQuantization not disclosed | $0.15 | $0.60 | — | $0.262 | Verified 7h ago · Changed 7h ago | |
Azure AI Foundry Fireworks on Azure | gpt-oss-120b | standarddata zone (US)Quantization not disclosed | $0.165 | $0.66 | $0.082 | $0.289 | Verified 5h ago · Changed 7h ago | |
AWS Bedrock | us-gov.openai.gpt-oss-120b-1:0 | standardQuantization not disclosedReduced context (128k of 131k) | $0.18 | $0.72 | — | $0.315 | Verified 7h ago · Changed 7h ago | |
Cerebras | gpt-oss-120b | standardQuantization not disclosed | $0.35 | $0.75 | — | $0.45 | Verified 7h ago · Changed 7h ago |
Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.
| DeepInfra bfloat16 | $7.1/mo |
| Google Vertex AI | $16.2/mo |
| DeepInfra bfloat16 | $27/mo |
| Azure AI Foundry global endpoint | $27/mo |
| Together AI | $27/mo |
| Fireworks AI | $27/mo |
| Groq | $27/mo |
| AWS Bedrock | $27/mo |
| AWS Bedrock | $27/mo |
| Azure AI Foundry data zone (US) | $29.7/mo |
| AWS Bedrock | $32.4/mo |
| Cerebras | $50/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.