Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | qwenQwen: Qwen3 Coder 30B A3B InstructRemove × |
|---|---|
| What’s different | 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… |
| Date | Jul 31, 2025Listed |
API prices USD · provider configuration shown below | |
| Listed rate | $0.07 in / $0.28 out/ 1M tokensSiliconFlow · via OpenRouter · all routes ↗siliconflow/fp8 · quantization=fp8 |
| Provider endpoints | 5 endpoints → |
Specifications | |
| Context window | 262.1K |
| Max output | 235.9K |
| Parameters | 30B |
| Tool calling | Supported |
| Structured output | Supported |
| Open weights | Supported |