per 1M tokens
Qwen: Qwen2.5 VL 72B Instruct
qwen/qwen2.5-vl-72b-instruct
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.
Price
per 1M tokens
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| Parasail | parasail/fp8 | fp8 | $0.8/1M | $1/1M | 128K | 100% | Live | openrouter-endpoints |
| OVHcloud | — | — | $1.01/1M | $1.01/1M | 33K | — | Listed | ovh |
| Together | — | — | $1.95/1M | $8/1M | 33K | — | Listed | together |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$1.80 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.8/1M | $1/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-15 | token | $0.8 | $1 | Not published— |
| 2026-09-16 | token | $0.8 | $1 | Not published— |
| 2026-09-17 | token | $0.8 | $1 | Not published— |
| 2026-09-18 | token | $0.8 | $1 | Not published— |
| 2026-09-19 | token | $0.8 | $1 | Not published— |
| 2026-09-20 | token | $0.8 | $1 | Not published— |
| 2026-09-21 | token | $0.8 | $1 | Not published— |
| 2026-09-22 | token | $0.8 | $1 | Not published— |
| 2026-09-23 | token | $0.8 | $1 | Not published— |
| 2026-09-24 | token | $0.8 | $1 | Not published— |
| 2026-09-25 | token | $0.8 | $1 | Not published— |
| 2026-09-26 | token | $0.8 | $1 | Not published— |
| 2026-09-27 | token | $0.8 | $1 | Not published— |
| 2026-09-28 | token | $0.8 | $1 | Not published— |
| 2026-09-29 | token | $0.8 | $1 | Not published— |
| 2026-09-30 | token | $0.8 | $1 | Not published— |
| 2026-10-01 | token | $0.8 | $1 | Not published— |
| 2026-10-02 | token | $0.8 | $1 | Not published— |
| 2026-10-03 | token | $0.8 | $1 | Not published— |
| 2026-10-04 | token | $0.8 | $1 | Not published— |
| 2026-10-05 | token | $0.8 | $1 | Not published— |
| 2026-10-06 | token | $0.8 | $1 | Not published— |
| 2026-10-07 | token | $0.8 | $1 | Not published— |
| 2026-10-08 | token | $0.8 | $1 | Not published— |
| 2026-10-09 | token | $0.8 | $1 | Not published— |
| 2026-10-10 | token | $0.8 | $1 | Not published— |
| 2026-10-11 | token | $0.8 | $1 | Not published— |
| 2026-10-12 | token | $0.8 | $1 | Not published— |
| 2026-10-13 | token | $0.8 | $1 | Not published— |
| 2026-10-14 | token | $0.8 | $1 | Not published— |
| 2026-10-15 | token | $0.8 | $1 | Not published— |
| 2026-10-16 | token | $0.8 | $1 | Not published— |
| 2026-10-17 | token | $0.8 | $1 | Not published— |
| 2026-10-18 | token | $0.8 | $1 | Not published— |
| 2026-10-19 | token | $0.8 | $1 | Not published— |
| 2026-10-20 | token | $0.8 | $1 | Not published— |
| 2026-10-21 | token | $0.8 | $1 | Not published— |
| 2026-10-22 | token | $0.8 | $1 | Not published— |
| 2026-10-23 | token | $0.8 | $1 | Not published— |
| 2026-10-24 | token | $0.8 | $1 | Not published— |
| 2026-10-25 | token | $0.8 | $1 | Not published— |
| 2026-10-26 | token | $0.8 | $1 | Not published— |
| 2026-10-27 | token | $0.8 | $1 | Not published— |
| 2026-10-28 | token | $0.8 | $1 | Not published— |
| 2026-10-29 | token | $0.8 | $1 | Not published— |
| 2026-10-30 | token | $0.8 | $1 | Not published— |
Alternatives
- AionLabs: Aion-2.0$0.8/1M · Compare
- AionLabs: Aion-RP 1.0 (8B)$0.8/1M · Compare
- Amazon: Nova Pro 1.0$0.8/1M · Compare
- Amazon: Titan Multimodal Embeddings G1$0.8/1M · Compare
- Claude Instant$0.8/1M · Compare
- Deepseek Coder 33B Instruct$0.8/1M · Compare
Parameters (14)
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_logprobstop_p
Call this model
OpenRouter id qwen/qwen2.5-vl-72b-instruct. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"qwen/qwen2.5-vl-72b-instruct","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "qwen/qwen2.5-vl-72b-instruct",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "qwen/qwen2.5-vl-72b-instruct", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())