← All models
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. 262,144 token context window, maximum output of 32,768 tokens. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.
chatstreamingtoolsjson mode
Details
- Accepts
- text
- Context window
- 160K tokens
Pricing
- Input
- 8.75 cr / 1M tokens
- Output
- 35 cr / 1M tokens
Prices in credits (1 credit = $0.01).
Data schema
approximateInput
| Field | Type | Description |
|---|---|---|
| promptrequired | string | The text prompt. |
Output
| Field | Type | Description |
|---|---|---|
| text | string | Generated text (choices[0].message.content). |