Alibaba (Qwen) · language model
Qwen3 235B A22B Thinking 2507: pricing, context and benchmarks
Qwen3 235B A22B Thinking 2507 is Alibaba (Qwen)'s model released on July 25, 2025. It costs $0.45 per million input tokens and $3.5 per million output tokens, with a 128K-token context window. No independent score has been published for it so far.
What you need to know about Qwen3 235B A22B Thinking 2507
Alibaba (Qwen), based in China, put Qwen3 235B A22B Thinking 2507 online on July 25, 2025. It accepts text as input and produces text. Its context window reaches 128,000 tokens, larger than 19 % of the models in the registry, and it can write up to 16,384 tokens in one go.
It has been available for about 15 months, long enough for its prices and scores to have settled.
Qwen3 235B A22B Thinking 2507 pricing
On OpenRouter, Qwen3 235B A22B Thinking 2507 costs $0.45 per million input tokens and $3.5 per million output tokens. Counting three tokens read for every token written, its average price is $1.213 per million, more expensive than 63 % of paid models (1.6 times the median of $0.76).
A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0027. At 1,000 tasks a day, budget $80 a month. The price calculator redoes this with your own volumes.
Performance and benchmarks
Epoch AI does not yet publish a capabilities index for Qwen3 235B A22B Thinking 2507. We therefore show no made-up performance rating: only price, context and features count towards its score.
Scores published by Epoch AI on the benchmarks the site tracks:
| Benchmark | What it measures | Score | Date |
|---|---|---|---|
| GPQA Diamond | PhD-level science questions | 80.1 % | Jul 25, 2025 |
| OTIS Mock AIME | maths competition problems | 86.7 % | Jul 25, 2025 |
| SimpleQA Verified | accuracy on simple facts | 40.4 % | Jul 25, 2025 |
Features, privacy and local use
- It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
- It is a reasoning model: it "thinks" before answering, which helps on hard tasks but uses more output tokens.
- Its knowledge stops at June 2025.
Its weights are open and downloadable from Hugging Face (apache-2.0 licence): you can run it on your own machines without sending your data to a third party. With 235,093,634,560 billion parameters, it needs about 131,368,805,408 GB of memory at 4-bit quantisation. Check with the VRAM calculator. It was downloaded 14,791 times on Hugging Face last month.
Other Alibaba (Qwen) models
| Model | Released | Avg. price | ECI |
|---|---|---|---|
| Qwen3.8 Max Prime | Sep 23, 2026 | $6 | — |
| Qwen3.8 Omni Flash | Sep 21, 2026 | $0.23 | — |
| Qwen3.8 Max (0902) | Sep 3, 2026 | $3 | 155.1 |
| Qwen3.8 Flash | Aug 26, 2026 | $0.23 | — |
| Qwen3.8 27B | Aug 14, 2026 | $0.78 | 151.7 |
| Qwen3.8 2.4T A95B | Aug 12, 2026 | $3 | — |
| Qwen3.7 Flash | Jul 27, 2026 | $0.06 | 144.1 |
| Qwen3.7 Plus | Jun 3, 2026 | $0.56 | 147 |
Verdict
Computed score: 43/100, from public data (performance, price, context, features).
Strengths
- Open weights: self-hostable, your data stays with you.
Limitations
- No independent score published: performance cannot be verified.
- Text only: reads neither images nor files.
Avoid if…
- your tasks are mostly simple: a non-reasoning model will cost less;
- you want to host it on a single consumer computer (≈ 131,368,805,408 GB needed at 4-bit).
Alternatives
Comparisons and tools
Learn more
Frequently asked questions
How much does Qwen3 235B A22B Thinking 2507 cost?
$0.45 per million input tokens and $3.5 per million output tokens on OpenRouter (checked October 25, 2026). A task with 2,000 tokens read and 500 written costs $0.0027.
How big is Qwen3 235B A22B Thinking 2507's context window?
128,000 tokens, roughly 96,000 words, with a maximum of 16,384 output tokens.
Can Qwen3 235B A22B Thinking 2507 run locally?
Yes, its weights are published under the apache-2.0 licence. Expect about 131,368,805,408 GB of memory at 4-bit.
Is Qwen3 235B A22B Thinking 2507 suitable for an AI agent?
Technically yes: it supports tool calling. Then check its cost for your volume.
What are the alternatives to Qwen3 235B A22B Thinking 2507?
The closest models on price and performance are GPT Audio Mini, Nano Banana 2 (Gemini 3.1 Flash Image Preview), and Nano Banana 2 (Gemini 3.1 Flash Image).
Related articles
- Mistral AI: models, pricing and agentsOctober 25, 2026
- LLM benchmarks: how to read model rankingsOctober 24, 2026
- Running a local LLM: hardware, software, and limitationsOctober 24, 2026
- Open-source or closed models for your AI agents?October 5, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score