The Orchestrator › Models › Qwen
Qwen: Qwen3 235B A22B Thinking 2507
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
Specifications
| Provider | Qwen |
| Model ID | qwen/qwen3-235b-a22b-thinking-2507 |
| Context window | 128K tokens (128,000) |
| Modalities | text → text |
| Tokenizer | Qwen3 |
| Router sources | OpenRouter, TrustedRouter |
| Released | 2025-07-25 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Mandatory |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | qwen/qwen3-235b-a22b-thinking-2507 | $0.45 | $3.50 | 128K |
| standard | TrustedRouter | qwen/qwen3-235b-a22b-thinking-2507 | $0.475 | $3.69 | 128K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.475 | $3.69 | 128K |
| 2026-11-14 | $0.45 | $3.50 | 128K |
Capabilities
Agentic tool useReasoning (always on)Controllable reasoningNo content storage (attested)Zero data retention
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, stop, temperature, tool_choice, tools, top_k, top_p