per 1M tokens
Qwen/Qwen2.5-72B-Instruct
deepinfra/Qwen/Qwen2.5-72B-Instruct
Qwen2.5 is a model pretrained on a large-scale dataset of up to 18 trillion tokens, offering significant improvements in knowledge, coding, mathematics, and instruction following compared to its predecessor Qwen2. The model also features enhanced capabilities in generating long texts, understanding structured data, and generating structured outputs, while supporting multilingual capabilities for over 29 languages.
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 |
|---|---|---|---|---|---|---|---|---|
| DeepInfra | — | — | $0.36/1M | $0.4/1M | 33K | — | Listed | deepinfra |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$0.76 at list price for this workload
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.36/1M | $0.4/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-08 | token | $0.36 | $0.4 | Not published— |
| 2026-10-09 | token | $0.36 | $0.4 | Not published— |
| 2026-10-10 | token | $0.36 | $0.4 | Not published— |
| 2026-10-11 | token | $0.36 | $0.4 | Not published— |
| 2026-10-12 | token | $0.36 | $0.4 | Not published— |
| 2026-10-13 | token | $0.36 | $0.4 | Not published— |
| 2026-10-14 | token | $0.36 | $0.4 | Not published— |
| 2026-10-15 | token | $0.36 | $0.4 | Not published— |
| 2026-10-16 | token | $0.36 | $0.4 | Not published— |
| 2026-10-17 | token | $0.36 | $0.4 | Not published— |
| 2026-10-18 | token | $0.36 | $0.4 | Not published— |
| 2026-10-19 | token | $0.36 | $0.4 | Not published— |
| 2026-10-20 | token | $0.36 | $0.4 | Not published— |
| 2026-10-21 | token | $0.36 | $0.4 | Not published— |
| 2026-10-22 | token | $0.36 | $0.4 | Not published— |
| 2026-10-23 | token | $0.36 | $0.4 | Not published— |
| 2026-10-24 | token | $0.36 | $0.4 | Not published— |
| 2026-10-25 | token | $0.36 | $0.4 | Not published— |
| 2026-10-26 | token | $0.36 | $0.4 | Not published— |
| 2026-10-27 | token | $0.36 | $0.4 | Not published— |
| 2026-10-28 | token | $0.36 | $0.4 | Not published— |
| 2026-10-29 | token | $0.36 | $0.4 | Not published— |
| 2026-10-30 | token | $0.36 | $0.4 | Not published— |
Alternatives
- Qwen2.5 72B Instruct$0.36/1M · Compare
- MiniMaxAI/MiniMax-M2.5$0.353/1M · Compare
- Gemma 4 31B ()$0.3674/1M · Compare
- @cf/aisingapore/gemma-sea-lion-v4-27b-it$0.351/1M · Compare
- @cf/mistralai/mistral-small-3.1-24b-instruct$0.351/1M · Compare
- Mistral: Mistral Small 3.1 24B$0.351/1M · Compare
Parameters (1)
chat
Call this model
OpenRouter id deepinfra/Qwen/Qwen2.5-72B-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":"deepinfra/Qwen/Qwen2.5-72B-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: "deepinfra/Qwen/Qwen2.5-72B-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": "deepinfra/Qwen/Qwen2.5-72B-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())