OpenAI (via Together) · 2026-11-19
gpt-oss-120B API pricing
gpt-oss-120B costs $0.15 per 1M input tokens and $0.6 per 1M output tokens (list price, source linked below). It ranks #26 of 36 on our board by editorial tier, then price.
| Provider | OpenAI (via Together) |
| Region | 🇺🇸 US |
| Editorial tier | Strong |
| Input / 1M tokens | $0.15 |
| Output / 1M tokens | $0.6 |
| Blended / 1M (3:1) | $0.26 |
| Context | 131K |
| Open weights | Yes |
| Strengths | Open-weights OpenAI model |
| Best for | Self-host, private deployments |
| Our picks | — |
| Price source | PromptCost LLM API pricing (Oct 2026) |
What would gpt-oss-120B cost me?
Estimates at list price, before any caching or batch discounts.
| Monthly usage | Estimated list cost |
|---|---|
| 1M input + 250K output tokens | $0.30 |
| 10M input + 2M output tokens | $2.70 |
| 100M input + 25M output tokens | $30.00 |
How much does the gpt-oss-120B API cost?
gpt-oss-120B lists at $0.15 per 1M input tokens and $0.6 per 1M output tokens, per PromptCost LLM API pricing (Oct 2026) as of 2026-11-19.
What is gpt-oss-120B best for?
Self-host, private deployments. AIRaceBoard places it in the Strong tier (editorial, not a benchmark score).
Is there a cheaper alternative to gpt-oss-120B?
Among models in the same or a higher tier, Claude Haiku 5.5 has a lower blended list price ($0.20 vs $0.26 per 1M tokens).
Similar models
- Claude Haiku 5.5 — $0.1/$0.5 per 1M
- Muse Ember — $0.1/$0.5 per 1M
- GPT-6 Luna — $0.1/$0.5 per 1M
- Nemotron 3.5 Super VL — $0.15/$0.5 per 1M
- MiniMax-M3.1-Flash — $0.15/$0.6 per 1M
- Mistral Small 4 vs gpt-oss-120B
- All comparisons and model pages
See all 36 models on the leaderboard → Estimate your bill Advertise here