qwen3-30b-a3b-instruct-2507Alibaba (Qwen)
- endpoints
- 2
- regions
- 2
- api
- chat
- released
- July 2025
capabilities 5/8
The same weights cost 2.0x more on alibaba cloud than on nebius ai. That is what the endpoints table is for.
| # | flags | ||||||
|---|---|---|---|---|---|---|---|
| 1 |  Nebius AI | EU | 128K | $0.10 | $0.30 | $0.10 | zdr |
| 2 |  Alibaba Cloud | Global | 131K | $0.20 | $0.80 | $0.20 | zdr |
no measured traffic for this model yet. the endpoints table above carries provider pricing
| eval | Score as a share of 100 | /100 |
|---|---|---|
| MMLU Pro | 77.7 | |
| Math Index | 72.3 | |
| AIME 2025 | 72.3 | |
| GPQA Diamond | 61.6 | |
| LiveCodeBench | 50.6 | |
| τ²-Bench | 26.0 | |
| Intelligence Index | 7.6 | |
| Humanity's Last Exam | 6.2 | |
| Terminal-Bench Hard | 2.3 | |
| 9 evals | mean | 41.8 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2025-04-28.
nebius/qwen/qwen3-30b-a3b-instruct-2507this model has no managed policy yet, so call the provider endpoint directly. every id in the endpoints table works the same way
Base url is https://router.requesty.ai/v1 for every id here. One key reaches the whole catalog.
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="nebius/qwen/qwen3-30b-a3b-instruct-2507", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url, use your Requesty key, set the model to any id in the call pane. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog, so switching later is a one-parameter change. Browse all models
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use. Post-trained on instruction data, it demonstrates competitive performance across reasoning (AIME, ZebraLogic), coding (MultiPL-E, LiveCodeBench), and alignment (IFEval, WritingBench) benchmarks. It outperforms its non-instruct variant on subjective and open-ended tasks while retaining strong factual and coding performance.
questions 5
Which providers serve qwen3-30b-a3b-instruct-2507?
How much does qwen3-30b-a3b-instruct-2507 cost?
Is qwen3-30b-a3b-instruct-2507 open weights?
What is the context window of qwen3-30b-a3b-instruct-2507?
How do I use qwen3-30b-a3b-instruct-2507 with the OpenAI SDK?
more from alibaba (qwen) 6
| model | context | from /M | providers |
|---|---|---|---|
| qwen3.8-2.4t-a95b | 1M | $2.50 | 1 |
| qwen3.8-flash-next | 262K | $0.20 | 1 |
| qwen3.8-flash | 1.0M | $0.16 | 1 |
| qwen3.8-max | 1.0M | $2.00 | 3 |
| qwen3.7-plus | 1.0M | $0.32 | 2 |
| qwen3.7-max | 1.0M | $2.50 | 1 |
route qwen3-30b-a3b-instruct-2507 through one endpoint
One key for 2 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in. Weekly aggregates in the measured pane come from production traffic routed through Requesty, one line per provider on a shared axis. Methodology