Alibaba (Qwen) · Released Apr 17, 2026Qwen3.6 35B-A3B
Open multimodal Qwen MoE for local agents that need vision, audio, and code.
- Capability
- 143.9ECI · #83 of 148
- Input
- $0.248per 1M tokens
- Output
- $1.49per 1M tokens
- Context
- 262K66K max output
What it costs
- Input
- $0.248per million tokens
- Output
- $1.49per million tokens
- Blended (3:1)
- $0.557cheaper than 57% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $1.24 |
| Team assistant25M input + 5M output tokens | $13.63 |
| Production app250M input + 50M output tokens | $136.25 |
Official Alibaba API price, as listed on models.dev.
Independent benchmarks
#83 of 148 scored models
The shaded band is Epoch AI’s confidence range (141.2–146.0); the tick marks the median scored model.
Scores from Epoch AI, run independently of Alibaba (Qwen).
The details
- Lab
- Alibaba (Qwen)
- Released
- Apr 17, 2026
- Context window
- 262,144 tokens
- Max output
- 65,536 tokens
- Inputs
- Text, Images, Audio, Video
- Output
- Text
- Reasoning
- Thinking budget
- Tool calling
- Yes
- Structured output
- Yes
- Weights
- Open weights
- API model ID
qwen3.6-35b-a3bon Alibaba- Availability
- 34 API providerslisted on models.dev
What Alibaba (Qwen) claims
Published by the lab at launch. Settings vary, so compare these only with care.
| Benchmark | Score | Setting | Source |
|---|---|---|---|
| SWE-Bench Verified | 73.4 resolved | — | Source |
More from Alibaba (Qwen)
About Qwen3.6 35B-A3B
How much does Qwen3.6 35B-A3B cost?
Qwen3.6 35B-A3B costs $0.248 input / $1.49 output per million tokens (official Alibaba API price). At a 3:1 input-to-output mix that is $0.557 per million tokens, cheaper than 57% of the 360 priced models we track.
What is the context window of Qwen3.6 35B-A3B?
Qwen3.6 35B-A3B accepts up to 262,144 tokens per request and can write up to 65,536 tokens in one response.
How good is Qwen3.6 35B-A3B?
Epoch AI gives Qwen3.6 35B-A3B a Capabilities Index score of 143.9 (likely range 141.2–146.0), ranking it #83 of 148 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 84.9%, FrontierMath Tiers 1–3 20.4%, OTIS Mock AIME 2024–2025 86.7%.
Is Qwen3.6 35B-A3B open source?
Yes. Alibaba (Qwen) publishes the weights, so it can be downloaded and self-hosted.
What inputs does Qwen3.6 35B-A3B support?
Qwen3.6 35B-A3B accepts text, images, audio and video and replies in text. It is a reasoning model, supports tool calling and can return structured JSON output.
When was Qwen3.6 35B-A3B released?
Alibaba (Qwen) released Qwen3.6 35B-A3B on Apr 17, 2026.
What are the best alternatives to Qwen3.6 35B-A3B?
The closest current models from other labs on capability, price and release date are MiniMax-M2.7 (MiniMax, ECI 145.9, $0.30 / $1.20), GPT-5.4 nano (OpenAI, ECI 145.8, $0.20 / $1.25), Gemini 3.5 Flash Lite (Google, ECI 145.1, $0.30 / $2.50) and GLM-4.7 (Z.ai (Zhipu), ECI 143.5, $0.60 / $2.20).