gpt-oss-120b pricing

gpt-oss-120b from OpenAI runs on 12 providers. The lowest price is $0.03 input and $0.17 output per 1M tokens, on CoreWeave. On Cerebras it costs 6.9× as much.

Updated

Lab
OpenAI
Context
131K
Input
Text
Providers
12
What each provider chargesBlended price per 1M tokens, 3 parts input to 1 part output. The highest is 6.9× the lowest.
  1. CoreWeave$0.065Lowest
  2. DeepInfra$0.07031.1×
  3. Crusoe$0.101.5×
  4. DigitalOcean$0.152.3×
  5. Google Vertex AI$0.1582.4×
  6. Baseten$0.203.1×
  7. Amazon Bedrock$0.2624.0×
  8. Nebius$0.2624.0×
  9. Together AI$0.2624.0×
  10. Groq$0.2624.0×
  11. SambaNova$0.3435.3×
  12. Cerebras$0.456.9×

Every price, by provider

gpt-oss-120b prices by provider, in US dollars per 1 million tokens
ProviderInputOutputCachedCache writeBatch inBatch outContextMax output
CoreWeavefp4$0.03$0.17$0.03–––131K118K
DeepInfrabf16$0.037$0.17––$0.0296$0.136131K118K
fp8Precision$0.20$0.95–
Crusoebf16$0.05$0.25$0.05–––131K118K
DigitalOcean$0.06$0.42$0.012–––128K4K
Google Vertex AI$0.09$0.36––––131K118K
Basetenfp4$0.10$0.50$0.10–––128K115K
Amazon Bedrock$0.15$0.60––––131K118K
eu-west-1Region$0.15$0.60–
Nebiusfp4$0.15$0.60$0.10–––131K118K
Together AI$0.15$0.60––––131K118K
Groq$0.15$0.60$0.075–$0.075$0.30131K66K
SambaNova$0.14$0.95––––131K118K
Cerebrasfp16$0.35$0.75$0.35–––131K41K

Prices in US dollars. Token prices are per 1 million tokens. abracadabra compiles them from each provider’s listing on OpenRouter, the LiteLLM price list and the providers’ own pricing pages, and refreshes them daily. The dataset is free to use: /api/ai-pricing.

See which tasks your agent finishes.

A price says what a call costs. abracadabra reads every conversation your agent has and shows the topics people bring, the tasks that get done and the turn where the rest stop.

Free to start, no card. Or open the playground (opens in a new tab).