# Qwen 3.6 35B A3B FP8

- Model ID for the API: `Qwen/Qwen3.6-35B-A3B-FP8`
- Privacy tier: Private TEE. Runs in a secure enclave on NEAR AI's infrastructure. Not even NEAR AI can see your prompts. Verify it with a free attestation report.
- Input price: $0.17 per 1M tokens
- Output price: $1.1 per 1M tokens
- Cache read price: $0.056 per 1M tokens
- Context window: 262K tokens
- Input modalities: Text
- Output modalities: Text
- API base URL: https://cloud-api.near.ai/v1

Canonical page: https://near.ai/models/Qwen/Qwen3.6-35B-A3B-FP8
Generated: 2026-11-18T10:03:09.049Z

## About this model

Qwen 3.6 35B is a fast mixture-of-experts language model with ~3B active parameters per token. Strong at reasoning, coding, and multilingual tasks with 32K context window.

## Make your first request

Send `POST https://cloud-api.near.ai/v1/chat/completions` over HTTPS. Get an API key at https://cloud.near.ai/signin, then set it as the `NEARAI_API_KEY` environment variable.

```bash
curl --fail-with-body "https://cloud-api.near.ai/v1/chat/completions" \
  -H "Authorization: Bearer $NEARAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "Qwen/Qwen3.6-35B-A3B-FP8",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'
```

## Verify

- Attestation report for this model: https://cloud.near.ai/verify?model=Qwen%2FQwen3.6-35B-A3B-FP8
- How verification works: https://docs.near.ai/cloud/verification
- Inference SDK, which checks attestations and signatures for you: https://docs.near.ai/cloud/inference-sdk

## More

- Try it in the Playground: https://cloud.near.ai/playground?model=Qwen%2FQwen3.6-35B-A3B-FP8
- All models: https://near.ai/models.md
- Pricing: https://near.ai/pricing.md
- Documentation: https://docs.near.ai/cloud/introduction
