OpenAI · Model
gpt-oss-120b pricing, context window and specs
gpt-oss-120b costs $0.037 per million input tokens and $0.17 per million output tokens, and reads up to 131,072 tokens per request. By blended price it is number 2 of 60 from cheapest in OpenAI's current line-up.
- Input / 1M
- $0.037
- Output / 1M
- $0.17
- Cached / 1M
- –
- Context
- 131,072
- Max output
- Not published
- Released
- 2025-08-05
Estimate your cost with gpt-oss-120bCompare all OpenAI modelsCount tokens for gpt-oss-120b
Pricing
gpt-oss-120b API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.037 | $0.17 |
| Batch API | $0.0296 | $0.136 |
Output costs 4.6× the input price, so long replies drive the bill more than long prompts. No cached-input price is published, so repeated prompt prefixes are billed at the full input price.
Examples
What gpt-oss-120b costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot | 1,500 / 400 | 1,000 | $0.000124 | $3.76 |
| RAG app | 6,000 / 500 | 500 | $0.000307 | $4.67 |
| Coding agent | 40,000 / 2,000 | 200 | $0.00182 | $11.07 |
| Document summariserbatch | 8,000 / 600 | 300 | $0.000318 | $2.91 |
Change any number in the cost calculator.
Context
Context window
gpt-oss-120b accepts up to 131,072 tokens per request, roughly 98,304 English words or 197 pages. That budget is shared between your prompt and the reply, and no separate cap on the reply is published.
Filling the whole window with one prompt costs about $0.00485 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
Capabilities
- Image input
- No
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- No
- Structured output
- Yes
- Open weights
- Yes
- Accepts
- text
- Knowledge cutoff
- 2024-06-30
As declared by the provider’s API. It shows a feature exists, not how well it works.
OpenAI
Where gpt-oss-120b sits in OpenAI’s line-up
Ranked by blended price (three parts input to one part output, $0.0703 per 1M for gpt-oss-120b), it is number 2 of 60 from cheapest of OpenAI’s 60 priced models. See every OpenAI model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| GPT-6.1 Sol | $2 | $10 | 1,050,000 | 2026-09-29 |
| GPT-6.1 Sol Pro | $2 | $10 | 1,050,000 | 2026-09-29 |
| GPT-6 Luna | $0.10 | $0.50 | 1,050,000 | 2026-09-22 |
| GPT-6 Luna Pro | $0.10 | $0.50 | 1,050,000 | 2026-09-22 |
| GPT-6 Sol | $2 | $10 | 1,050,000 | 2026-09-22 |
| GPT-6 Sol Pro | $2 | $10 | 1,050,000 | 2026-09-22 |
| GPT-6 Astra | $10 | $50 | 1,050,000 | 2026-09-04 |
| GPT-6 Astra Pro | $10 | $50 | 1,050,000 | 2026-09-04 |
Save
Cheaper alternatives
- Qwen3.7 FlashQwen22% cheaper
- Nemotron 3.5 LightningNVIDIA2% cheaper
Current models from major providers, one per provider, that keep tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Similarly priced models
- Nemotron 3.5 LightningNVIDIA$0.0469 / $0.134
- Qwen3.7 FlashQwen$0.03 / $0.13
- Ministral 3 3B 2512Mistral$0.10 / $0.10
- Gemma 4 26B A4BGoogle$0.0765 / $0.255
- Muse Spark 1.2 ContributorMeta$0.10 / $0.20
Current models from other major providers, closest blended price.
FAQ
gpt-oss-120b questions
How much does gpt-oss-120b cost?
gpt-oss-120b costs $0.037 per million input tokens and $0.17 per million output tokens. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.000124. Use the LLM cost calculator for your own workload.
What is gpt-oss-120b's context window?
131,072 tokens, about 98,304 English words or 197 printed pages, shared between your prompt and the reply. No separate limit on the reply is published, so the window is the limit.
Does gpt-oss-120b support prompt caching and batch requests?
No cached-input price is published for it. A batch API is available at $0.0296 input and $0.136 output per million tokens.
What are cheaper alternatives to gpt-oss-120b?
With the same essentials (tool calling), the cheapest options are Qwen3.7 Flash (22% cheaper), Nemotron 3.5 Lightning (2% cheaper). Cheaper doesn't mean equivalent, so test them on your own prompts.
Is gpt-oss-120b open source?
Yes, gpt-oss-120b has open weights, so you can run it yourself or choose between several hosting providers. The prices here are a typical hosted price.