Qwen2.5 72B Instruct
- Input / output
- $0.288 / $0.32
- Providers
- 1
- Spread
- 1.25×
- 7 days
- −20.0%
- 30 days
- −20.0%
- Context
- 32K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
| fp8 | $0.288 | $0.32 | $0.296 | ref | |||
| fp8 | $0.36 | $0.40 | $0.37 | +25% |
- DeepInfraCheapestfp8/flex$0.296$0.288 in · $0.32 outref vs ref32K ctx100% uptimefp8
- $0.37$0.36 in · $0.40 out+25% vs ref32K ctx97.9% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.296 = 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 Qwen2.5 72B Instruct is DeepInfra at $0.296 per 1M tokens (blended), charging $0.288 per 1M input and $0.32 per 1M output tokens. It is served by a single provider. Its best price fell 20.0% over the last 30 days. Context window: 32K tokens. Prices tracked since Oct 3, 2026.
Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...
- Released
- Sep 19, 2024
- First tracked
- Oct 3, 2026
- Canonical slug
- qwen/qwen-2.5-72b-instruct
- Weights
- Qwen/Qwen2.5-72B-Instruct