Qwen3.6-35B-A3B-FP8

Call as Qwen/Qwen3.6-35B-A3B-FP8

Capabilities, limits, and token rates published by GET /v1/catalog/models.

Capabilities

Input	text, image
Output	text
Reasoning	Supported
Tool calling	Supported
JSON mode	Supported
Structured output	Supported
Image input	Supported
Image generation	Not supported
Streaming	Supported

Capabilities apply to this served revision. “Not verified” means no qualification result is available.

Limits

Context window	262,144 tokens
Maximum output	Limited by remaining context

Input and output share the context window. The available output depends on the length of your input.

Pricing

Input	$0.10 per million tokens
Cache read	$0.025 per million tokens
Cache write	$0.00 per million tokens
Output	$0.90 per million tokens

Use this model

POST/v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://api.boardwalk.cloud/v1",
    api_key="your-api-key",
)

response = client.chat.completions.create(
    model="Qwen/Qwen3.6-35B-A3B-FP8",
    messages=[{"role": "user", "content": "Say hello in five words."}],
    max_completion_tokens=1024,
)
print(response.choices[0].message.content)
print(response.usage)

SDK setup: pip install openai · npm install openai. cURL needs no SDK.

See the API reference for request fields. The model’s API metadata lists its supported parameters and response formats.

Configuration

Model id	`Qwen/Qwen3.6-35B-A3B-FP8`
Hugging Face repo	Qwen/Qwen3.6-35B-A3B-FP8
Pinned revision	95a723d08a9490559dae23d0cff1d9466213d989
dtype	bfloat16
Quantization	fp8
Engine	vllm
Engine version	v0.32.0
Status	active