Qwen3 30B A3B Instruct 2507
- Input / output
- $0.09 / $0.30
- Providers
- 3
- Spread
- 1.05×
- 7 days
- 0%
- 30 days
- 0%
- Context
- 256K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
DekaLLMCheapest | $0.09 | $0.30 | $0.143 | ref | |||
| fp8 | $0.09 | $0.30 | $0.143 | ref | |||
| fp8 | $0.10 | $0.30 | $0.15 | +5.3% |
- DekaLLMCheapest$0.143$0.09 in · $0.30 outref vs ref256K ctx98.8% uptime
- $0.143$0.09 in · $0.30 outref vs ref256K ctx98.6% uptimefp8
- $0.15$0.10 in · $0.30 out+5.3% vs ref256K ctx96.9% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.143 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
Other pricing
| Offered by | Cache read |
|---|---|
| Nebius | $0.10 |
Changes
- PriceCache read price,—→$0.10—
- DelistedNo longer served,Delisted
- DelistedNo longer served,Delisted
- DelistedNo longer served,Delisted
- ListedNow served,Listed
About
The cheapest provider for Qwen3 30B A3B Instruct 2507 is DekaLLM at $0.143 per 1M tokens (blended), charging $0.09 per 1M input and $0.30 per 1M output tokens. 3 providers serve it; the most expensive charges 1.05× the typical price. Context window: 256K tokens. Prices tracked since Oct 3, 2026.
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
- Released
- Jul 29, 2025
- First tracked
- Oct 3, 2026
- Canonical slug
- qwen/qwen3-30b-a3b-instruct-2507
- Weights
- Qwen/Qwen3-30B-A3B-Instruct-2507