LLMPrivate

Qwen 3 235B A22B Thinking 2507

Alibaba's flagship open-weight thinking MoE — 235B total, 22B active, reasoning-only mode with tool use and 262K native context.

Get API key
Provider
Alibaba Cloud
Price
$0.45 in · $3.50 out / 1M
Context window
128K tokens
Released
July 25, 2025
License
Apache 2.0

What is Qwen 3 235B A22B Thinking 2507?

Qwen 3 235B A22B Thinking 2507 is an open-weight, thinking-only Mixture-of-Experts language model from Alibaba's Qwen team. It activates 22 billion of its 235 billion parameters per forward pass, natively supports 262K context, and is optimized for deep reasoning, mathematics, coding, and tool use.

Use it privately on Venice

On Venice, Qwen 3 235B A22B Thinking 2507 runs privately with zero retention of your prompts or outputs. It ships with default reasoning enabled, plus native support for tool use, web search, and structured JSON output — all without the surveillance or usage profiling typical of Big-Tech inference APIs.

Private (zero retention)
No prompt training
TEE · hardware enclave
End-to-end encrypted

What can it do?

Strengths
  • State-of-the-art reasoning performance among open-source thinking models, with enforced step-by-step reasoning for logic, mathematics, science, and coding.
  • Strong tool use, function calling, web search, and structured JSON output support on Venice, making it ideal for agentic workflows.
  • Open weights under Apache 2.0 enable self-hosting, fine-tuning, and full model sovereignty.
  • Efficient MoE architecture activates only 22B parameters per forward pass, delivering high capability without full dense-model inference cost.
  • Default reasoning mode ensures deep deliberation on complex prompts rather than shallow, immediate responses.
Limitations
  • Thinking-only modethe model cannot disable reasoning, so even simple queries incur longer thinking chains and higher output token costs.
  • Venice caps context at 128K tokens and max output at 16.384K tokens, below the native 262K context and high-output design.
  • FP8 quantization on Venice trades a small amount of precision for inference efficiency compared to full-precision runs.
  • Not uncensoredsafety alignment is present, and the model may refuse certain sensitive or restricted requests.
  • Recommended primarily for highly complex reasoning tasks; for casual chat or quick answers, a smaller non-reasoning model is often more efficient.

Qwen 3 235B A22B Thinking 2507 capabilities

How to use it via API

Venice exposes an OpenAI-compatible API. Swap your base URL and call qwen3-235b-a22b-thinking-2507.

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 quantum tunneling simply." }]
  }'

Specifications

MakerAlibaba Cloud (Qwen team)
ReleasedJuly 25, 2025
ArchitectureMixture-of-Experts (MoE), 94 layers
Parameters235B total / 22B activated per forward pass
Experts128 total / 8 activated
AttentionGrouped-query attention (64 Q / 4 KV heads)
Open weightsYes — Apache 2.0
Context window128K tokens
Max output16.384K tokens
CapabilitiesFunction calling, Reasoning, Web search
Privacy on VenicePrivate — zero retention
Available on Venice sinceApr 2025

Pricing

Billed per token on Venice: $0.45 per 1M input tokens and $3.50 per 1M output tokens.

Input / 1M tokens
$0.45
Output / 1M tokens
$3.50

New Venice accounts include a free daily allowance and 500 welcome credits — no credit card required.

Qwen 3 235B A22B Thinking 2507 vs alternatives

ModelContext windowOpen weightsPrice (Venice)Best for
Qwen 3 235B A22B Thinking 2507128K tokensYes$0.45 in · $3.50 out / 1MDeep reasoning & tool use
DeepSeek V3.2160K tokensYes$0.33 in · $0.48 out / 1MEfficient coding & inference
Kimi K2.6256K tokensYes$0.75 in · $3.50 out / 1MLong-document analysis
Claude Sonnet 4.61M tokensNo$3.60 in · $18 out / 1MGeneral closed-model performance

The most capable open-source thinking variant in the Qwen3 series, with enforced reasoning, tool use, web search, and structured output.

What is it good for?

  • Advanced mathematics, scientific reasoning, and competitive programming requiring step-by-step derivation.
  • Long-document analysis and academic research leveraging its extensive context capacity.
  • Agentic automation with tool use, function calling, and structured JSON output for pipelines and integrations.
  • Multilingual reasoning and code generation across complex software engineering tasks.
  • Deep research workflows that benefit from web search grounding and extended reasoning chains.

Prompting tips

  • Budget extra output tokens: the model always generates a reasoning chain, so token consumption is higher than non-thinking models.
  • Use explicit tool schemas and JSON output formats when building agents to take advantage of native structured-output support.
  • For long-context tasks, place the most important instructions near the beginning or end of the prompt to maximize attention.
  • Reserve this model for complex problems; for simple Q&A or creative writing, a general-purpose model will be faster and cheaper.

Version history

Qwen3-235B-A22B
2025-04

Base Qwen3 MoE model.

Qwen3-235B-A22B-Thinking-2507
2025-07

CurrentThinking-only update with scaled reasoning depth.

Frequently asked questions

It is an open-weight, thinking-only Mixture-of-Experts language model developed by Alibaba's Qwen team. It activates 22 billion of its 235 billion parameters per forward pass and is optimized for deep reasoning, mathematics, coding, and tool use.

Venice charges $0.45 per 1 million input tokens and $3.50 per 1 million output tokens. There is no subscription required; you pay per token with credits.

Yes. The model weights are released under the Apache 2.0 license, allowing self-hosting, fine-tuning, and audit. On Venice it runs as open weights with FP8 quantization.

Yes. On Venice it supports function calling, structured JSON output, and web search, making it suitable for agentic workflows and automated pipelines.

Qwen 3 Thinking is a dedicated reasoning model with enforced step-by-step thinking and 235B total parameters, while DeepSeek V3.2 is a general-purpose MoE model with lower per-token pricing. Qwen 3 Thinking excels at complex math and logic; DeepSeek V3.2 is more cost-efficient for everyday coding and chat.

Yes. Venice runs it under a private, zero-retention tier — your prompts and outputs are not stored, profiled, or used for model training.

This model generates lengthy reasoning chains by default, which increases output token counts. The higher output price reflects the compute cost of producing deep reasoning and long-form responses.

No. This variant supports only thinking mode. The chat template automatically enforces reasoning, so every response will include a step-by-step chain of thought.

Related models

Run Qwen 3 235B A22B Thinking 2507 privately.

No prompt logging. No data used for training. Free to start — no credit card.

Room