Qwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 2507 is a chat model from Qwen, released July 25, 2025. 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...
by Qwen · 131K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Qwen3 235B A22B Thinking 2507 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Qwen API key. osFoundry discovers Qwen3 235B A22B Thinking 2507 automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
Run Qwen3 235B A22B Thinking 2507 yourself
Qwen3 235B A22B Thinking 2507 is also available as open weights — self-host it for full data control and no per-token cost. See that page for GPU requirements and a cost comparison against API pricing.
Qwen3 235B A22B Thinking 2507 vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Qwen3 235B A22B Thinking 2507 | Qwen | — | 131K | $ 0.150 /1M | API only |
| GLM 4.5 Air | Z.ai | — | 131K | $ 0.130 /1M | API only |
| Switchpoint Router | switchpoint | — | 131K | $ 0.850 /1M | API only |
| Codestral 2508 | Mistral | — | 256K | $ 0.300 /1M | API only |
Licence
Hosted — usage subject to provider terms — Hosted-only model — usage governed by the provider's API terms. Bring your own provider key.
No weights distributed; usage subject to provider terms.
Frequently asked about Qwen3 235B A22B Thinking 2507
How much does Qwen3 235B A22B Thinking 2507 cost?
Qwen3 235B A22B Thinking 2507 is metered at $ 0.150 /1M for input, and $ 1.50 /1M for output. Bring your own Qwen API key — osFoundry passes through provider pricing without markup.
Can I use Qwen3 235B A22B Thinking 2507 commercially?
Commercial use is allowed with conditions. Hosted-only model — usage governed by the provider's API terms. Bring your own provider key. No weights distributed; usage subject to provider terms.
What is the context window of Qwen3 235B A22B Thinking 2507?
Qwen3 235B A22B Thinking 2507 supports a 131K token context window.
Can I run Qwen3 235B A22B Thinking 2507 locally?
No — Qwen3 235B A22B Thinking 2507 is hosted only and accessed via the Qwen API. An open-weights equivalent is available to self-host — see the cross-link above.
What is Qwen3 235B A22B Thinking 2507 best at?
Qwen3 235B A22B Thinking 2507 is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Qwen3 235B A22B Thinking 2507 in osFoundry?
Paste your Qwen API key in the key dialog (or deploy the open weights for self-hostable models), assign Qwen3 235B A22B Thinking 2507 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Qwen on July 25, 2025. Source: https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507