Qwen3-235B-A22B-Thinking-2507
- Next shutdown
- None setNo date on 1 platform
- Arena Text
- 1,400#77 of 128 · Arena
- GPQA Diamond
- 80.1%#61 of 108 · Epoch AI
- Context window
- 262.1Ktokens
Dates on every platform
1 listings · a floor is the earliest possible date
| Platform | Model ID and status | Deprecated | Shuts down | Replacement |
|---|---|---|---|---|
| Together AITogether AI: Deprecations (opens in a new tab) · checked Oct 14, 2026 | Qwen/Qwen3-235B-A22B-Thinking-2507Shut down | – | Shut down | – |
What breaks when you move off Qwen3-235B-A22B-Thinking-2507
Intelligence
Third-party results, credited below
| Benchmark | Publisher | Score | Rank | Published |
|---|---|---|---|---|
| Arena Text | Arena | 1,400 ± 3 | #77 of 128 | Oct 8, 2026 |
| GPQA Diamond | Epoch AI | 80.1% ± 2.6% | #61 of 108 | Dec 11, 2025 |
| OTIS Mock AIME 2024-2025 | Epoch AI | 86.7% ± 5.1% | #51 of 105 | Dec 10, 2025 |
| SimpleQA Verified | Epoch AI | 40.4% ± 1.6% | #41 of 68 | Aug 27, 2026 |
Arena (arena.ai), https://arena.ai/leaderboard
Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource].
Change history
ShutdownQwen3 VL 8B, Qwen3 235B Thinking 2507 and Mixtral 8x7B leave Together serverlessTogether AI1 break
Together removed Qwen/Qwen3-VL-8B-Instruct, Qwen/Qwen3-235B-A22B-Thinking-2507 and mistralai/Mixtral-8x7B-Instruct-v0.1 from serverless inference.
- Platform
- Together AI
- AvailabilityRequests to the removed serverless model ID fail. The model can still run on an on-demand dedicated endpoint, billed per minute.
Source: Together AI, Deprecations (opens in a new tab); Together AI, Changelog (opens in a new tab)