# GPT: OSS 120B API

OpenAI's GPT: OSS 120B, through an OpenAI-compatible API. 3 providers quote it now, and each request goes to the offer with the lowest estimated charge that meets your rules.

- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send gpt-oss-120b as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

## Facts

- Model name: gpt-oss-120b
- Maker: OpenAI
- Context window: 122.9K · 131.1K tokens
- Input price: $0.037 to $0.090 per million tokens
- Output price: $0.0034 to $0.460 per million tokens
- Providers: 3 independent providers
- Regions: eu, us, us-west

## Providers

- [akash](https://liquidinference.ai/providers/2249261a-b9e8-449c-8c79-abf2dc02dd91.md): us-west, $0.037 input and $0.187 output per million tokens, $0.037 cache read per million tokens, 131.1K tokens of context
- [Pera](https://liquidinference.ai/providers/f651491e-f85b-4f03-b80c-32876aeb80ce.md): us, $0.037 input and $0.0034 output per million tokens, $0.037 cache read per million tokens, $0.00017 fee for each request, 122.9K tokens of context
- [SOKKAN](https://liquidinference.ai/providers/65502412-bcc7-4baa-9a9a-e20ea20a38d4.md): eu, $0.090 input and $0.460 output per million tokens, $0.090 cache read per million tokens, 131.1K tokens of context

## Scores

- HLE: 19.6, #118 of 273
- GPQA: 78.2, #109 of 250
- AA-LCR: 52.0, #157 of 237
- SciCode: 34.0, #111 of 123
- Terminal-Bench Hard: 23.5, #82 of 166
- LiveCodeBench: 87.8, #4 of 130
- AIME 2025: 93.4, #7 of 100
- MMLU-Pro: 80.8, #44 of 133
- τ²-Bench: 65.8, #83 of 169
- IFBench: 69.0, #44 of 178

Scores: Artificial Analysis (https://artificialanalysis.ai/)

## Request

```sh
curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-oss-120b",
    "messages": [{"role":"user","content":"Say hello."}]
  }'
```

## Questions

### What is GPT: OSS 120B?

GPT: OSS 120B is a model from OpenAI.

### How much does GPT: OSS 120B cost?

Offers now ask $0.037 to $0.090 per million input tokens and $0.0034 to $0.460 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.

### What is the context length of GPT: OSS 120B?

The largest offer takes 131,072 input tokens. One job can generate up to 131,072 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.

### What can GPT: OSS 120B do?

Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Presence penalty, Seed, Stop sequences, Top-p sampling, Text, Tools.

### What inputs and outputs does GPT: OSS 120B support?

Text → Text.

### Which providers serve GPT: OSS 120B?

3 independent providers quote it now, with 3 offers. The table above ranks them by the cost of a typical job.

### How do I call GPT: OSS 120B?

Send "gpt-oss-120b" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.

### When was GPT: OSS 120B listed?

The exchange first listed it on 9/29/2026. This is not its release date.

## Related pages

- [This page in a browser](https://liquidinference.ai/models/gpt-oss-120b)
- [GPT: OSS 20B](https://liquidinference.ai/models/gpt-oss-20b.md)
- [GPT: OSS Safeguard 20B](https://liquidinference.ai/models/gpt-oss-safeguard-20b.md)
- [GPT 5 Nano 2025 08 07](https://liquidinference.ai/models/gpt-5-nano-2025-08-07.md)
- [GPT 5 Nano](https://liquidinference.ai/models/gpt-5-nano.md)
- [GPT 4.1 Nano](https://liquidinference.ai/models/gpt-4.1-nano.md)
- [GPT: Luna Latest](https://liquidinference.ai/models/gpt-luna-latest.md)
- [Set up a client](https://liquidinference.ai/connect/gpt-oss-120b)
- [All models](https://liquidinference.ai/models)
- [Providers](https://liquidinference.ai/providers.md)
- [Discover the best model for your budget](https://liquidinference.ai/discover)
- [Quickstart](https://liquidinference.ai/docs/quickstart.md)
- [llms.txt: the index of every page, as Markdown](https://liquidinference.ai/llms.txt)
- [llms-full.txt: every page in one file](https://liquidinference.ai/llms-full.txt)