> ## Documentation Index
> Fetch the complete documentation index at: https://docs.venice.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> The Venice API is OpenAI-compatible: use any OpenAI SDK with the base URL `https://api.venice.ai/api/v1` and a Venice API key, or pay per request from a USDC wallet through x402 with no account.
> Read model IDs from `GET /models` or `GET /models/traits` at runtime instead of hardcoding them from memory or from these pages. Models are added and retired often.
> Every model's price is in https://docs.venice.ai/pricing.md. Quote video and audio jobs with `POST /video/quote` or `POST /audio/quote` before you queue them.
> Search these docs from an MCP client at https://docs.venice.ai/mcp. The full agent guide is https://docs.venice.ai/agents.md.

# Qwen 3.5 397B API

> Qwen 3.5 397B API on Venice: 128K context, $0.75 input and $4.50 output per 1M tokens. Anonymized access without your identity.



## Qwen 3.5 397B API

Qwen 3.5 397B is a large language model by Alibaba Qwen, available on the Venice API as `qwen3-5-397b-a17b`. The provider of this model may retain prompt data (though it is anonymized by Venice). For sensitive content, use a private model.

Qwen 3.5 is a reasoning model from Alibaba featuring a 397B parameter Mixture-of-Experts architecture with 17B active parameters. It excels at complex reasoning, coding, and general knowledge tasks.

### Qwen 3.5 397B API pricing

| Model ID | Variant | Privacy | Price |
| - | - | - | - |
| `qwen3-5-397b-a17b` | Standard | Anonymized | $0.75 / $4.50 per 1M |

### Qwen 3.5 397B specifications

| Spec | Value |
| - | - |
| Provider | Alibaba Qwen |
| Released | Feb 16, 2026 |
| Privacy | Anonymized |
| Status | Stable |
| Open weights | [Qwen/Qwen3.5-397B-A17B](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| Context window | 128K tokens |
| Max output | 32K tokens |
| Reasoning effort | none, low, medium, high |
| [GPQA Diamond](https://docs.venice.ai/models/methodology.md#benchmarks) | 55.4% ±4.0 (95% interval), run by Venice through the API at its default reasoning on Oct 12, 2026 |

### How to use the Qwen 3.5 397B API

Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "qwen3-5-397b-a17b"` and your API key.

```bash theme={"system"}
curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-5-397b-a17b",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
    "reasoning_effort": "low"
  }'
```

### Related models

* [Qwen 3.8 27B API](https://docs.venice.ai/models/qwen-3-8-27b.md): $0.45 / $3.20 per 1M
* [Qwen 3.6 27B API](https://docs.venice.ai/models/qwen-3-6-27b.md): $0.325 / $3.25 per 1M
* [GPT-5.4 Mini API](https://docs.venice.ai/models/gpt-5-4-mini.md): $0.75 / $4.50 per 1M
* [Grok 4.20 API](https://docs.venice.ai/models/grok-4-20.md): $1.42 / $2.83 per 1M
* [Grok 4.20 Multi-Agent API](https://docs.venice.ai/models/grok-4-20-multi-agent.md): $1.42 / $2.83 per 1M
* [GLM 5 API](https://docs.venice.ai/models/glm-5.md): $1.00 / $3.20 per 1M


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.