Qwen3 Coder 30B A3B Instruct
- Input / output
- $0.07 / $0.28
- Providers
- 2
- Spread
- 2.1×
- 7 days
- 0%
- 30 days
- 0%
- Context
- 256K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
SiliconFlowCheapest fp8 | $0.07 | $0.28 | $0.123 | ref | |||
Amazon Bedrockus-west-2 | $0.15 | $0.60 | $0.263 | +114% |
- SiliconFlowCheapest$0.123$0.07 in · $0.28 outref vs ref256K ctx99.0% uptimefp8
- us-west-2$0.263$0.15 in · $0.60 out+114% vs ref256K ctx99.9% uptime
Blended = (3 × input + output) / 4. Ref $0.123 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
Changes
- ListedNow served,Listed
- DelistedNo longer served,Delisted
- ListedNow served,Listed
- DelistedNo longer served,Delisted
- DelistedNo longer served,Delisted
- DelistedNo longer served,Delisted
About
The cheapest provider for Qwen3 Coder 30B A3B Instruct is SiliconFlow at $0.123 per 1M tokens (blended), charging $0.07 per 1M input and $0.28 per 1M output tokens. 2 providers serve it; the most expensive charges 2.1× the typical price. Context window: 256K tokens. Prices tracked since Oct 3, 2026.
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...
- Released
- Jul 31, 2025
- First tracked
- Oct 3, 2026
- Canonical slug
- qwen/qwen3-coder-30b-a3b-instruct
- Weights
- Qwen/Qwen3-Coder-30B-A3B-Instruct