Qwen2.5 VL 72B Instruct
- Input / output
- $0.80 / $1.00
- Providers
- 1
- Spread
- —
- 7 days
- 0%
- 30 days
- 0%
- Context
- 125K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
ParasailCheapest fp8 | $0.80 | $1.00 | $0.85 | ref |
- ParasailCheapest$0.85$0.80 in · $1.00 outref vs ref125K ctx99.9% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.85 = 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 | $0.40 |
Changes
No changes yet
Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.
About
The cheapest provider for Qwen2.5 VL 72B Instruct is Parasail at $0.85 per 1M tokens (blended), charging $0.80 per 1M input and $1.00 per 1M output tokens. It is served by a single provider. Context window: 125K tokens. Prices tracked since Oct 3, 2026.
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
- Released
- Feb 1, 2025
- First tracked
- Oct 3, 2026
- Canonical slug
- qwen/qwen2.5-vl-72b-instruct
- Weights
- Qwen/Qwen2.5-VL-72B-Instruct