# Apertus 70B Instruct 2509 API

Swiss-ai's Apertus 70B Instruct 2509 costs $0.820 per million input tokens and $2.921 per million output tokens from 1 independent provider. Each request through the OpenAI-compatible API 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 apertus-70b-instruct-2509 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.

## About Apertus 70B Instruct 2509

Apertus 70B Instruct 2509 is a language model from Swiss-ai. It takes text and gives text. The largest offer takes 32,768 input tokens. 1 independent provider quotes it on this exchange now.

## Facts

- Model name: apertus-70b-instruct-2509
- Maker: Swiss-ai
- Context window: 32.8K tokens
- Input price: $0.820 per million tokens
- Output price: $2.921 per million tokens
- Providers: 1 independent provider
- Regions: us

## Providers

- [Architect](https://liquidinference.ai/providers/805445a7-0e40-4c1b-9baf-7b3b01e30e42.md): us, $0.820 input and $2.921 output per million tokens, $0.820 cache read per million tokens, 32.8K tokens of context

## Scores

- HLE: 5.5, #315 of 465
- GPQA: 27.2, #426 of 432
- AA-LCR: 0.0, #396 of 409
- Terminal-Bench Hard: 0.0, #305 of 311
- τ²-Bench: 12.9, #301 of 313
- IFBench: 25.9, #309 of 321

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": "apertus-70b-instruct-2509",
    "messages": [{"role":"user","content":"Say hello."}]
  }'
```

## Questions

### What is Apertus 70B Instruct 2509?

Apertus 70B Instruct 2509 is a language model from Swiss-ai.

### How much does Apertus 70B Instruct 2509 cost?

Offers now ask $0.820 per million input tokens and $2.921 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 Apertus 70B Instruct 2509?

The largest offer takes 32,768 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.

### What can Apertus 70B Instruct 2509 do?

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

### What inputs and outputs does Apertus 70B Instruct 2509 support?

Text → Text.

### Which providers serve Apertus 70B Instruct 2509?

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 Apertus 70B Instruct 2509?

Send "apertus-70b-instruct-2509" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.

### When was Apertus 70B Instruct 2509 listed?

The exchange first listed it on 11/11/2026. This is not its release date.

## Related pages

- [This page in a browser](https://liquidinference.ai/models/apertus-70b-instruct-2509)
- [Apertus 8B Instruct 2509](https://liquidinference.ai/models/apertus-8b-instruct-2509.md)
- [Set up a client](https://liquidinference.ai/connect/apertus-70b-instruct-2509)
- [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)