This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
Alibaba has launched a newer release, Qwen3 Coder Next. We suggest considering it instead.
Qwen3 Coder 30B A3B Instruct: Intelligence, Performance & Price Analysis
Available providers
Model summary
Verbosity
Qwen3 Coder 30B A3B Instruct supports text input, outputs text, and has a 262k tokens context window.
Pricing for Qwen3 Coder 30B A3B Instruct is $0.19 per 1M input tokens (somewhat expensive, median: $0.13) and $0.77 per 1M output tokens (expensive, median: $0.25).
| Reasoning | No |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Context window | 262k ~393 A4 pages of size 12 Arial font |
| Total parameters | 30.5B |
| Active parameters | 3.3B Number of parameters active per token during inference |
| License | Apache 2.0 |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Openness Index
Artificial Analysis Openness Index: Score
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Performance
Measured by time per task (minutes), output speed (tokens per second), time to first answer token and time to first token (seconds)
Time per Intelligence Index Task
Output Speed
Time to First Answer Token
Context Window
Context Window
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Further details
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Qwen3 Coder 30B A3B Instruct | - | 30.5B 3.3B active at inference time | 262k | $0.25 | - | 154 |
Frequently Asked Questions
Common questions about Qwen3 Coder 30B A3B Instruct
Qwen3 Coder 30B A3B Instruct was released on July 31, 2025.
Qwen3 Coder 30B A3B Instruct was created by Alibaba.
Qwen3 Coder 30B A3B Instruct has a time to first answer token of 7.85s (based on the median across providers serving the model), which is at the higher end compared to other open weight non-reasoning models of similar size (median: 1.83s).
Qwen3 Coder 30B A3B Instruct costs $0.19 per 1M input tokens (somewhat higher than average, median: $0.13) and $0.77 per 1M output tokens (at the higher end, median: $0.25), based on the median across providers serving the model.
Qwen3 Coder 30B A3B Instruct costs $0.19 per 1M input tokens and $0.77 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.25 per 1M tokens. Pricing may vary by provider. Compare provider pricing
No, Qwen3 Coder 30B A3B Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Qwen3 Coder 30B A3B Instruct supports text input.
Qwen3 Coder 30B A3B Instruct supports text output.
No, Qwen3 Coder 30B A3B Instruct does not support image input. It can only process text.
No, Qwen3 Coder 30B A3B Instruct is not multimodal. It only supports text input.
Qwen3 Coder 30B A3B Instruct has a context window of 262k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Qwen3 Coder 30B A3B Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3 Coder 30B A3B Instruct has 30.5B parameters (3.3B active).
Qwen3 Coder 30B A3B Instruct is a Mixture of Experts (MoE) model with 30.5B total parameters, but only 3.3B active parameters are used during inference.
Qwen3 Coder 30B A3B Instruct is released under the Apache 2.0 license. This license allows commercial use. View license
Yes, Qwen3 Coder 30B A3B Instruct is available via API through 2 providers. Compare API providers
Qwen3 Coder 30B A3B Instruct is available through 2 API providers. Compare providers