OpenAI: gpt-oss-120b (batch) API Pricing
OpenAI: gpt-oss-120b (batch) costs $0.030 per 1M input tokens and $0.136 per 1M output tokens. Context window: 131K. Prices verified 2026-10-21 · source
Alternatives to consider
44% cheaper with nearly identical quality (20.1 vs 11.6)
Cheapest openai model — 36% less per month
Rebuilt daily from our snapshot archive — the chart appears once a model has 5+ snapshots of history.
High adoption means battle-tested weights, more fine-tunes/quants, and faster bug fixes. View on HuggingFace →
From our own daily snapshot archive — independent of provider announcements.
Intelligence measures reasoning/knowledge/coding benchmarks. A high score with a low blended price = value pick; check the value chart to see where this model lands.
Higher effort = deeper thinking = more reasoning tokens billed as output.
Training data ends here — newer events require retrieval or web search.
What would OpenAI: gpt-oss-120b (batch) cost you per month?
| Workload | Requests/mo | Avg tokens (in/out) | Est. monthly cost |
|---|---|---|---|
| Light chatbot | 10,000 | 800 / 400 | $0.78 |
| Coding agent | 5,000 | 8,000 / 2,000 | $2.54 |
| RAG pipeline | 30,000 | 4,000 / 500 | $5.59 |
| Doc summarizer | 2,000 | 20,000 / 1,000 | $1.46 |
Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.
About OpenAI: gpt-oss-120b (batch)
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
Compare OpenAI: gpt-oss-120b (batch) with
- gpt-oss-120b (batch) vs OpenAI: GPT-5.6 Terra Pro
- gpt-oss-120b (batch) vs Anthropic: Claude Fable 5
- gpt-oss-120b (batch) vs Anthropic: Claude Opus 5
- gpt-oss-120b (batch) vs OpenAI: GPT-5.6 Sol
Popular head-to-heads — see all on the comparisons index.
Frequently asked questions
How much does OpenAI: gpt-oss-120b (batch) cost?
OpenAI: gpt-oss-120b (batch) costs $0.030 per 1M input tokens and $0.136 per 1M output tokens. Verified 2026-10-21 — provider source.
What is the context window?
131K tokens, with up to 118K output tokens per response. That's roughly 164 pages of text in a single request.
Does it support prompt caching?
Prompt-caching pricing is not published for this model via OpenRouter.
What's a cheaper alternative?
Check the value chart for models with similar intelligence at lower cost.
Official resources
- OpenAI: gpt-oss-120b (batch) on OpenRouter — live endpoint, pricing source of record.
- Artificial Analysis leaderboard → — independent intelligence and performance rankings.
- OpenAI pricing → — first-party pricing and billing details.
- LMArena leaderboard → — independent human-preference rankings.
- Shred your current bill — paste a CSV and see if switching saves money.