Qwen/Qwen2.5-VL-72B-Instruct| Provider | Input, $ per 1M | Output, $ per 1M | In our data since |
|---|---|---|---|
Nebius Token Factory
nebius/Qwen/Qwen2.5-VL-72B-Instruct
|
$0.13 | $0.4 | 31 Jul 2026 |
| LLM Gateway | $0.25 | $0.75 | 31 Jul 2026 |
Nebius Token Factory
Qwen/Qwen2.5-VL-72B-Instruct
|
$0.25 | $0.75 | 31 Jul 2026 |
| NanoGPT | $0.7 | $0.7 | 31 Jul 2026 |
| novita-ai | $0.8 | $0.8 | 31 Jul 2026 |
| Kilo Code | $0.8 | $0.8 | 31 Jul 2026 |
| Novita AI | $0.8 | $0.8 | 31 Jul 2026 |
| OpenRouter | $0.8 | $1 | 31 Jul 2026 |
| Fireworks AI | $0.9 | $0.9 | 1 Aug 2026 |
OVHCloud AI Endpoints
ovhcloud/Qwen2.5-VL-72B-Instruct
|
$0.91 | $0.91 | 31 Jul 2026 |
OVHCloud AI Endpoints
qwen2.5-vl-72b-instruct
|
$1.01 | $1.01 | 31 Jul 2026 |
| alibaba-cn | $2.294 | $6.881 | 31 Jul 2026 |
| Alibaba (Qwen) | $2.8 | $8.4 | 31 Jul 2026 |
Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.
A single provider appears several times if it sells this model under different identifiers and at different prices — for example, at different weight precision. The identifier is shown next to the name. Identical offers that arrived from two sources under different spellings are merged into one row.
The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.
| Task set | Result | Run conditions | Measured by |
|---|---|---|---|
| Arena Score, working with images | 1,107.58 1,097–1,118 | — | — |
| GeoBench — locating a place from a photograph | 62 % | — | GeoBench leaderboard |
| OSWorld — working inside an operating system, first version | 5 % | · with a tuned harness | OS World Website |