Qwen3 4B

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

Capabilities

Input	Not verified
Output	Not verified
Reasoning	Not verified
Tool calling	Not verified
JSON mode	Not verified
Structured output	Not verified
Image input	Not verified
Image generation	Not verified
Streaming	Not verified

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

Limits

Context window	32,768 tokens
Maximum output	Not published

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

Pricing

Input	$0.3441 per million tokens
Cache read	$0.0344 per million tokens
Cache write	$0.00 per million tokens
Output	$0.6881 per million tokens

Use this model

curl https://api.boardwalk.cloud/v1/chat/completions \
  -H "Authorization: Bearer $BOARDWALK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "Qwen/Qwen3-4B",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

See the Chat Completions referencefor request fields. The model's API metadata lists its supported parameters and response formats.

Configuration

Model id	`Qwen/Qwen3-4B`
Hugging Face repo	Qwen/Qwen3-4B
Pinned revision	1cfa9a7208912126459214e8b04321603b3df60c
dtype	bfloat16
Quantization	none
Engine	vllm
Engine version	v0.27.1
Status	active