Alibaba (Qwen) · Released Apr 2025Qwen3-Coder 30B-A3B Instruct
Smaller Qwen coder for efficient local agents and repo-level fixes.
- Capability
- —No ECI score yet
- Input
- $0.45per 1M tokens
- Output
- $2.25per 1M tokens
- Context
- 262K66K max output
What it costs
- Input
- $0.45per million tokens
- Output
- $2.25per million tokens
- Over 32K tokens
- $0.75 / $3.75input / output per million
- Blended (3:1)
- $0.90pricier than 53% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $2.02 |
| Team assistant25M input + 5M output tokens | $22.50 |
| Production app250M input + 50M output tokens | $225.00 |
Official Alibaba API price, as listed on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for Qwen3-Coder 30B-A3B Instruct yet.
The details
- Lab
- Alibaba (Qwen)
- Released
- Apr 2025
- Knowledge cutoff
- Apr 2025
- Context window
- 262,144 tokens
- Max output
- 65,536 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- No
- Weights
- Open weights
- API model ID
qwen3-coder-30b-a3b-instructon Alibaba- Availability
- 13 API providerslisted on models.dev
What Alibaba (Qwen) claims
Published by the lab at launch. Settings vary, so compare these only with care.
More from Alibaba (Qwen)
About Qwen3-Coder 30B-A3B Instruct
How much does Qwen3-Coder 30B-A3B Instruct cost?
Qwen3-Coder 30B-A3B Instruct costs $0.45 input / $2.25 output per million tokens (official Alibaba API price). Requests over 32K tokens are billed at $0.75 input / $3.75 output. At a 3:1 input-to-output mix that is $0.90 per million tokens, more expensive than 53% of the 360 priced models we track.
What is the context window of Qwen3-Coder 30B-A3B Instruct?
Qwen3-Coder 30B-A3B Instruct accepts up to 262,144 tokens per request and can write up to 65,536 tokens in one response.
How good is Qwen3-Coder 30B-A3B Instruct?
Epoch AI has not published a Capabilities Index score for Qwen3-Coder 30B-A3B Instruct yet.
Is Qwen3-Coder 30B-A3B Instruct open source?
Yes. Alibaba (Qwen) publishes the weights, so it can be downloaded and self-hosted.
What inputs does Qwen3-Coder 30B-A3B Instruct support?
Qwen3-Coder 30B-A3B Instruct accepts text and replies in text. It is not a dedicated reasoning model, supports tool calling.
When was Qwen3-Coder 30B-A3B Instruct released?
Alibaba (Qwen) released Qwen3-Coder 30B-A3B Instruct on Apr 2025. Its training data runs to Apr 2025.
What are the best alternatives to Qwen3-Coder 30B-A3B Instruct?
The closest current models from other labs on capability, price and release date are GLM-4.5V (Z.ai (Zhipu), $0.60 / $1.80), Mistral Medium 3.1 (Mistral AI, $0.40 / $2.00), Llama 3.1 Nemotron 70B Instruct (NVIDIA, $0.478 / $0.504) and Aya Expanse 32B (Cohere, $0.50 / $1.50).