Polarison

OpenAI · open weights

gpt-oss-120b API pricing by provider

gpt-oss-120b is available from 16 providers. The cheapest is AkashML at $0.03 input / $0.17 output per 1M tokens (BF16). The priciest host, Cerebras, charges 6.9x the cheapest.

Prices from the OpenRouter API, retrieved September 15, 2026. Weights: openai/gpt-oss-120b.

ProviderPrecisionInput / 1MOutput / 1MDocument Q&A / monthContextMax output
AkashMLbf16$0.03$0.17$17.10131K118K
CoreWeavefp4$0.03$0.17$17.10131K118K
DekaLLMbf16$0.03$0.18$17.40131K118K
DeepInfrabf16$0.037$0.17$19.90131K118K
Crusoebf16$0.05$0.25$27.50131K118K
DigitalOcean$0.06$0.42$36.60128K4K
Google$0.09$0.36$46.80131K118K
Mancer 2fp8$0.055$0.50$37.00131K118K
BaseTenfp4$0.10$0.50$55.00128K115K
Amazon Bedrock$0.15$0.60$78.00131K118K
Nebiusfp4$0.15$0.60$78.00131K118K
DeepInfrabf16$0.15$0.60$78.00131K16K
SiliconFlowfp8$0.15$0.60$78.00131K8K
Groq$0.15$0.60$78.00131K66K
Parasailfp4$0.10$0.75$62.50131K118K
SambaNova$0.14$0.95$84.50131K118K
DeepInfrafp8$0.20$0.95$108.50131K118K
Cerebrasfp16$0.35$0.75$162.50131K41K

Sorted by blended price (3 input : 1 output). Document Q&A assumes 50,000 questions a month with 8,000 input and 600 output tokens each. Precision is reported by the provider; “—” means not disclosed.

Frequently asked questions

What is the cheapest gpt-oss-120b API provider?
AkashML is the cheapest healthy provider we track at $0.03 per 1M input tokens and $0.17 per 1M output tokens.
How much does gpt-oss-120b cost?
Across 16 providers, input prices range from $0.03 to $0.35 per 1M tokens and output prices from $0.17 to $0.95.
What is gpt-oss-120b’s context window?
gpt-oss-120b supports up to 131K tokens, but some providers serve a smaller context window — check the table before choosing.

Other open-weight models