Qwen: Qwen3 Coder 30B A3B Instruct
by QwenQwen: Qwen3 Coder 30B A3B Instruct is a large language model from Qwen. It costs $0.070 per million input tokens and $0.280 per million output tokens. Its context window is 262K tokens.
- Input / 1M tokens
- $0.070
- Output / 1M tokens
- $0.280
- Cached input / 1M
- -
- Context window
- 262K
Not supported
tokens
Who serves it cheapest
4 hosts serve Qwen3 Coder 30B A3B Instruct. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| NovitaCheapestfp8 | $0.070 | $0.270 | 160K | - | 99.2% |
| SiliconFlowfp8 | $0.070 | $0.280 | 262K | - | 98.8% |
| Amazon Bedrock | $0.150 | $0.600 | 0 | - | - |
| Alibaba | $0.292 | $1.46 | 262K | - | 100.0% |
The spread between Novita and Alibaba is 4.9× for identical weights. Quantization and context limits differ, so check both columns before switching.
About Qwen3 Coder 30B A3B Instruct
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. Built on the...
Specifications
| Model ID | qwen/qwen3-coder-30b-a3b-instruct |
|---|---|
| Provider | Qwen |
| Context window | 262K tokens |
| Max output | 236K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | 2025-06-30 |
| Open weights | Yes - Qwen/Qwen3-Coder-30B-A3B-Instruct |
| Released | July 31, 2025 |
Cheaper alternatives
Models that cost less than Qwen3 Coder 30B A3B Instruct while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Qwen: Qwen3 Coder 30B A3B Instruct cost?
$0.070 per million input tokens and $0.280 per million output tokens.
What is the context window of Qwen: Qwen3 Coder 30B A3B Instruct?
262K tokens, with up to 236K tokens of output per request.
Which provider serves Qwen: Qwen3 Coder 30B A3B Instruct cheapest?
Novita at $0.070 per million input tokens - 4.9× cheaper than Alibaba, the most expensive of the 4 hosts serving it.
Confirm against the source: Qwen official pricing.