# GPT 5.4 Mini API

OpenAI's GPT 5.4 Mini, through an OpenAI-compatible API. Providers quote it on an open exchange, 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-5.4-mini 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-5.4-mini
- Maker: OpenAI
- Context window: 272K tokens
- Input price: $0.750 per million tokens
- Output price: $4.500 per million tokens
- Providers: 1 independent provider
- Regions: global

## Providers

- [RelayGPU](https://liquidinference.ai/providers/42a59421-ba42-47c5-9e79-b05429ad3b59.md): global, $0.750 input and $4.500 output per million tokens, $0.750 cache read per million tokens, 272K tokens of context

## Scores

- HLE: 5.9, #192 of 273
- GPQA: 60.6, #174 of 250
- AA-LCR: 37.0, #188 of 237
- Terminal-Bench Hard: 18.2, #97 of 166
- τ²-Bench: 23.4, #146 of 169
- IFBench: 38.8, #128 of 178
- SimpleQA Verified: 29.4, #83 of 126

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

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

## 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-5.4-mini",
    "messages": [{"role":"user","content":"Say hello."}]
  }'
```

## Questions

### What is GPT 5.4 Mini?

Served by intent-router: each job goes to the cheapest healthy upstream for this model.

### How much does GPT 5.4 Mini cost?

Offers now ask $0.750 per million input tokens and $4.500 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 5.4 Mini?

The largest offer takes 272,000 input tokens. One job can generate up to 32,768 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.

### What can GPT 5.4 Mini do?

Its providers list Text.

### What inputs and outputs does GPT 5.4 Mini support?

Text → Text.

### Which providers serve GPT 5.4 Mini?

1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.

### How do I call GPT 5.4 Mini?

Send "gpt-5.4-mini" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.

### When was GPT 5.4 Mini listed?

The exchange first listed it on 10/8/2026. This is not its release date.

## Related pages

- [This page in a browser](https://liquidinference.ai/models/gpt-5.4-mini)
- [GPT: OSS 120B](https://liquidinference.ai/models/gpt-oss-120b.md)
- [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)
- [Set up a client](https://liquidinference.ai/connect/gpt-5.4-mini)
- [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)