Alibaba
No resultsEnough results for an index.Qwen3 30B A3B Thinking 2507
Qwen3 30B A3B Thinking 2507 is a model from Alibaba. It has no scored result.
IndexAll categories, out of 100.UnrankedMedian 51.0
CoverageIndex weight that has results.0%
SpeedOutput tokens per second.122/sMedian 67/s
First tokenSeconds to the first output token.0.3 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.20Median $0.60
Output / 1MUS dollars per 1M output tokens.$2.40Median $2.55
ContextMaximum tokens in one request.82KMedian 262K
EloLMArena rating and rank.—Median 1422
Details
From OpenRouter- API IDThe model ID on OpenRouter.
qwen/qwen3-30b-a3b-thinking-2507- Max outputMaximum output tokens per request.
- 33K
- Knowledge cutoffLast date of training data.
- 30 Jun 2025
- ToolsTool calls on OpenRouter.
- Yes
- JSON outputOutput follows a given JSON schema.
- No
- Cache read / 1MUS dollars per 1M cached tokens.
- —
- WeightsLink to the published weights.
- Hugging Face (opens in a new tab) ↗
- RetiresDate OpenRouter removes the model.
- 9 Oct 2026
Capabilities
Index per category, out of 100.Results
0 countedThis model has no scored result.
Sources
BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseHistory
5 releases23 Oct 202612 Nov 2026
Questions
- How much does Qwen3 30B A3B Thinking 2507 cost?
- $0.20 per 1M input tokens, $2.40 per 1M output tokens.
- How fast is Qwen3 30B A3B Thinking 2507?
- 122 output tokens per second, 0.3 s to the first token.
- What is the context window of Qwen3 30B A3B Thinking 2507?
- 82K tokens.
- Is Qwen3 30B A3B Thinking 2507 open source?
- Yes. Its weights are published.
- When was Qwen3 30B A3B Thinking 2507 released?
- August 2025.