GPT OSS 120B
OpenAI's open-weight 120B model for production and high reasoning use cases.
- Input price
- $0.165–$0.385
- Output price
- $0.66–$0.825
- Context
- 128K
- Max output
- 16K
- Capability
- 140 (#75 of 82)
- Human preference
- 1366
- 30-day uptime
- —
- Released
- 2025-08-30
InputTextOutputText
Providers
Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.
Pricing
Prices vary by provider. Showing Groq, the lowest. Pick a provider above to see its prices.
- Input
- $0.165
- per 1M tokens
- Output
- $0.66
- per 1M tokens
- Cache read
- $0.0825
- per 1M tokens
Estimated cost of common use (500 output tokens each)
- One chat message
- $0.000828
- 3K input tokens
- Agent first turn
- $0.0168
- 100K tokens of context, none cached
- Each later agent turn
- $0.00892
- context read from cache, plus 2K new tokens
- 20-turn agent task
- $0.186
- first turn plus 19 more
Try it
Runs on your balance and is billed like any API request.
Similar models
Other models with the same output types at a similar price.
Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-18): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text