Qwen 3 235B A22B Thinking 2507 API

Qwen 3 235B A22B Thinking 2507 is a large language model by Alibaba Qwen, available on the Venice API as qwen3-235b-a22b-thinking-2507. It runs privately, with zero data retention.Built for in-depth research and handling long, complex documents. Ideal for technical work, multimodal input, and high-precision tasks.

Qwen 3 235B A22B Thinking 2507 API pricing

Model ID	Variant	Privacy	Price
`qwen3-235b-a22b-thinking-2507`	Standard	Private	$0.45 input /$ 3.50 output per 1M tokens

Qwen 3 235B A22B Thinking 2507 specifications

Spec	Value
Provider	Alibaba Qwen
Released	Apr 29, 2025
Privacy	Private
Open weights	Yes
Context window	125K tokens
Max output	16K tokens
Reasoning effort	low, medium, high
Served precision	FP8

How to use the Qwen 3 235B A22B Thinking 2507 API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "qwen3-235b-a22b-thinking-2507" and your API key.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-235b-a22b-thinking-2507",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
    "reasoning_effort": "low"
  }'

Qwen 3 235B A22B Thinking 2507 API FAQ

How much does the Qwen 3 235B A22B Thinking 2507 API cost?

0.45 per 1M input tokens and

3.50 per 1M output tokens. Prices are in USD and can be paid in DIEM at parity.

What is the Qwen 3 235B A22B Thinking 2507 model ID?

Use qwen3-235b-a22b-thinking-2507 as the model parameter.

Is the Qwen 3 235B A22B Thinking 2507 API private?

Qwen 3 235B A22B Thinking 2507 is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.

What is the context window of Qwen 3 235B A22B Thinking 2507?

125K tokens of context, with up to 16K output tokens per response.

What does Qwen 3 235B A22B Thinking 2507 support?

Qwen 3 235B A22B Thinking 2507 supports function calling, structured outputs, reasoning and web search. Reasoning effort is adjustable with reasoning_effort: low, medium and high (default low).

Which endpoint does the Qwen 3 235B A22B Thinking 2507 API use?

Call POST /chat/completions. /responses (Alpha) is also supported.

Related models

Llama 3.3 70B API: $0.70 input /$ 2.80 output per 1M tokens
Kimi K2.5 API: $0.56 input /$ 3.50 output per 1M tokens
GLM 4.7 API: $0.55 input /$ 2.65 output per 1M tokens
Hermes 3 Llama 3.1 405b API: $1.10 input /$ 3.00 output per 1M tokens

Explore

By modality