Qwen3 30B A3B
- Input / output
- $0.096 / $0.40
- Providers
- 1
- Spread
- 1.88×
- 7 days
- −20.0%
- 30 days
- −20.0%
- Context
- 40K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
| fp8 | $0.096 | $0.40 | $0.172 | ref | |||
| fp8 | $0.12 | $0.50 | $0.215 | +25% | |||
DeepInfrafp8/priority fp8 | $0.18 | $0.75 | $0.323 | +88% |
- DeepInfraCheapestfp8/flex$0.172$0.096 in · $0.40 outref vs ref40K ctxfp8
- $0.215$0.12 in · $0.50 out+25% vs ref40K ctx100% uptimefp8
- fp8/priority$0.323$0.18 in · $0.75 out+88% vs ref40K ctx99.1% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.172 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
No provider has changed its price since tracking began on Oct 3, 2026.
Changes
About
The cheapest provider for Qwen3 30B A3B is DeepInfra at $0.172 per 1M tokens (blended), charging $0.096 per 1M input and $0.40 per 1M output tokens. It is served by a single provider. Its best price fell 20.0% over the last 30 days. Context window: 40K tokens. Prices tracked since Oct 3, 2026.
Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...
- Released
- Apr 28, 2025
- First tracked
- Oct 3, 2026
- Canonical slug
- qwen/qwen3-30b-a3b-04-28
- Weights
- Qwen/Qwen3-30B-A3B