Alibaba (Qwen) · language model
Qwen3.5-35B-A3B: pricing, context and benchmarks
Qwen3.5-35B-A3B is a language model from Alibaba (Qwen) released on February 25, 2026. It costs $0.14 per million input tokens and $1 per million output tokens, with a 262.1K-token context window. Epoch AI ranks it #94 of 125 rated models.
| Performance (ECI) | 10/40 | |
|---|---|---|
| Price | 21/30 | |
| Context | 9/15 | |
| Features | 15/15 |
What you need to know about Qwen3.5-35B-A3B
Qwen3.5-35B-A3B was released by Alibaba (Qwen) (China) on February 25, 2026. It accepts text, images, and video as input and produces text. Its context window reaches 262,144 tokens, larger than 58 % of the models in the registry, and it can write up to 81,920 tokens in one go.
It has been available for about 8 months, long enough for its prices and scores to have settled.
Qwen3.5-35B-A3B pricing
On OpenRouter, Qwen3.5-35B-A3B costs $0.14 per million input tokens and $1 per million output tokens. Counting three tokens read for every token written, its average price is $0.355 per million, more expensive than 31 % of paid models (2.1 times cheaper than 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 $0.0008. At 1,000 tasks a day, budget $23 a month. The price calculator redoes this with your own volumes.
Tokens already sent and cached are billed at $0.05 per million.
Performance and benchmarks
The Epoch Capabilities Index (ECI), which aggregates published results across many benchmarks, gives Qwen3.5-35B-A3B a score of 142.5 (range 140.4 to 145). That places it #94 of 125 rated models.
Scores published by Epoch AI on the benchmarks the site tracks:
| Benchmark | What it measures | Score | Date |
|---|---|---|---|
| GPQA Diamond | PhD-level science questions | 83.5 % | Feb 24, 2026 |
| OTIS Mock AIME | maths competition problems | 70 % | Feb 24, 2026 |
For at least equal performance, Claude Haiku 5.5, GPT-6 Luna, and DeepSeek V4 Flash 0731 cost at least 30% less.
Features, privacy and local use
- It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
- It can answer in an enforced JSON format (structured outputs).
- It is a reasoning model: it "thinks" before answering, which helps on hard tasks but uses more output tokens.
Its weights are open and downloadable from Hugging Face: you can run it on your own machines without sending your data to a third party.
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
Qwen3.5-35B-A3B scores 55/100 on our grid, which only uses published figures.
Strengths
- Open weights: self-hostable, your data stays with you.
- Agent-ready: tool calling and structured JSON output.
Limitations
- Modest performance: behind 74 % of rated models.
Alternatives
- Gemma 4 31B$0.25
- Gemma 4 26B A4B$0.11
- DeepSeek V3.1$0.43
- DeepSeek V3.2 Exp$0.31
- gpt-oss-120b$0.26
- GPT-5.4 Nano$0.46
Comparisons and tools
Learn more
Frequently asked questions
How much does Qwen3.5-35B-A3B cost?
$0.14 per million input tokens and $1 per million output tokens on OpenRouter (checked October 25, 2026). A task with 2,000 tokens read and 500 written costs $0.0008.
How big is Qwen3.5-35B-A3B's context window?
262,144 tokens, roughly 197,000 words, with a maximum of 81,920 output tokens.
Can Qwen3.5-35B-A3B run locally?
Yes, its weights are published.
Is Qwen3.5-35B-A3B suitable for an AI agent?
Technically yes: it supports tool calling and structured outputs. Then check its cost for your volume.
How good is Qwen3.5-35B-A3B?
Epoch AI ranks it #94 of 125 rated models (ECI 142.5). On GPQA Diamond, it scores 83.5%.
What are the alternatives to Qwen3.5-35B-A3B?
The closest models on price and performance are Gemma 4 31B, Gemma 4 26B A4B, and DeepSeek V3.1.
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