Qwen3 Next 80B A3B Instruct
- Input / output
- $0.072 / $0.88
- Providers
- 2
- Spread
- 1.88×
- 7 days
- 0%
- 30 days
- 0%
- Context
- 256K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
| fp8 | $0.072 | $0.88 | $0.274 | ref | |||
| fp8 | $0.09 | $1.10 | $0.343 | +25% | |||
| fp8 | $0.10 | $1.10 | $0.35 | +28% | |||
DeepInfrafp8/priority fp8 | $0.135 | $1.65 | $0.514 | +88% |
- DeepInfraCheapestfp8/flex$0.274$0.072 in · $0.88 outref vs ref256K ctx100% uptimefp8
- $0.343$0.09 in · $1.10 out+25% vs ref256K ctx99.5% uptimefp8
- $0.35$0.10 in · $1.10 out+28% vs ref256K ctx100% uptimefp8
- fp8/priority$0.514$0.135 in · $1.65 out+88% vs ref256K ctx99.4% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.274 = 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.
Other pricing
| Offered by | Cache read |
|---|---|
| Parasail | $0.07 |
Changes
About
The cheapest provider for Qwen3 Next 80B A3B Instruct is DeepInfra at $0.274 per 1M tokens (blended), charging $0.072 per 1M input and $0.88 per 1M output tokens. 2 providers serve it; the most expensive charges 1.88× the typical price. Context window: 256K tokens. Prices tracked since Oct 3, 2026.
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
- Released
- Sep 11, 2025
- First tracked
- Oct 3, 2026
- Canonical slug
- qwen/qwen3-next-80b-a3b-instruct-2509
- Weights
- Qwen/Qwen3-Next-80B-A3B-Instruct