Qwen2.5 72B Instruct API pricing
$2.36 in, $2.36 out per million tokens.
qwen2.5-72b-instructmanaged routeOpenAI SDK
Price · per million tokens, USD
Get a key| Tokens | Qwen list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $2.36 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $2.36 | — |
No list price on record. Same price on every host.
Real-model check: Same fingerprint since Oct 20
Qwen2.5 72B Instruct: what it is · from Qwen’s own model card, read 2026-10-20
The largest Qwen2.5 instruct model. Qwen’s card lists gains in knowledge, coding, math, long outputs, tables and JSON output, and it holds a system-prompt persona well. It is served as qwen2.5-72b-instruct at $2.36 input and $2.36 output per million tokens, on the same key as every other model in the catalog.
| Qwen2.5 72B Instruct | |
|---|---|
| Developer | Qwen |
| Parameters | 72.7B, dense |
| Context | 131,072 tokens, with up to 8,192 generated |
| License | the Qwen license |
| Published | 2024-09-16 |
| Downloads, 30 days to 2026-10-20 | 252,245 |
| Source | Qwen/Qwen2.5-72B-Instruct |
From Qwen/Qwen2.5-72B-Instruct, read 2026-10-20.
curl
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"qwen2.5-72b-instruct","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'Qwen2.5 72B Instruct next to Qwen’s other models · per million tokens, live
| Model | Here, in / out | 1,000 chat turns |
|---|---|---|
| Qwen3.6 27B | $0.09 / $0.60 | $0.48 |
| Qwen2.5 7B Instruct | $0.20 / $0.20 | $0.50 |
| Qwen3 8B | $0.24 / $0.24 | $0.60 |
| Qwen3.5 9B | $0.40 / $0.60 | $1.10 |
| Qwen3 14B | $0.28 / $1.12 | $1.12 |
| Qwen3 Coder 30B-A3B Instruct | $0.28 / $1.12 | $1.12 |
| Qwen3 30B-A3B Instruct 2507 | $0.36 / $1.20 | $1.32 |
| Qwen3 Coder 480B-A35B Instruct | $0.52 / $2.00 | $2.04 |
| Qwen3 32B | $0.56 / $2.28 | $2.26 |
| Qwen3 VL 32B Instruct | $0.80 / $2.40 | $2.80 |
| Qwen3 VL 8B Instruct | $0.72 / $2.72 | $2.80 |
| Qwen3.7 Plus | $0.80 / $3.20 | $3.20 |
| Qwen3 VL 30B-A3B Instruct | $1.16 / $4.00 | $4.32 |
| Qwen3 VL 30B-A3B Thinking | $1.16 / $4.00 | $4.32 |
| Qwen3 VL 32B Thinking | $0.80 / $6.00 | $4.60 |
| Qwen3.5 35B-A3B | $0.96 / $7.20 | $5.52 |
| Qwen3.6 35B-A3B | $0.96 / $7.20 | $5.52 |
| Qwen2.5 72B Instruct | $2.36 / $2.36 | $5.90 |
| Qwen3.5 27B | $1.00 / $8.00 | $6.00 |
| Qwen3.5 122B-A10B | $1.04 / $8.32 | $6.24 |
| QwQ 32B Uncensored | $2.64 / $4.00 | $7.28 |
| Qwen3.7 Max | $2.95 / $8.85 | $10.33 |
| Qwen3.8 2.4T-A95B | $8.00 / $24.00 | $28.00 |
A chat turn is 2,000 input and 500 output tokens. Live from the catalog, ordered by the cost of 1,000 turns.
Worked for Qwen2.5 72B Instruct: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $2.36 input and $2.36 output per million tokens, that is $4.72 + $1.18 = $5.90, paid from prepaid credit with no subscription.
Qwen2.5 72B Instruct API · base URL and key
Python · OpenAI SDK
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="qwen2.5-72b-instruct",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)TypeScript · OpenAI SDK
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.uplinkswitch.com/v1',
apiKey: 'sk-uplink-live-...',
});
const completion = await client.chat.completions.create({
model: 'qwen2.5-72b-instruct',
messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);curl
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"qwen2.5-72b-instruct","messages":[{"role":"user","content":"Hello"}]}'What would it cost? · paste a prompt, priced before you send it
Input is counted at about 4 characters per token.
Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.
More from Qwen
Qwen2.5 72B Instruct questions
- What is Qwen2.5 72B Instruct?
- Qwen2.5 72B Instruct is a model from Qwen. Through UplinkSwitch it answers the OpenAI SDK on one key as qwen2.5-72b-instruct.
- How much does the Qwen2.5 72B Instruct API cost?
- $2.36 per million input tokens and $2.36 per million output tokens.
- Is Qwen2.5 72B Instruct free?
- It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.0035.
- What is the Qwen2.5 72B Instruct model id?
- qwen2.5-72b-instruct. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Qwen2.5 72B Instruct API key?
- Create one in the console at uplinkswitch.ai/console: prepaid credit from $10, no subscription, and the key is live at once. The same key calls Qwen2.5 72B Instruct and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is it the real Qwen2.5 72B Instruct?
- Every day each model gets the same test prompt, and a model always counts that prompt the same way; a swapped one would not. Qwen2.5 72B Instruct's latest result: Same fingerprint since Oct 20.
- Is there a Qwen2.5 72B Instruct API?
- Yes: qwen2.5-72b-instruct on the OpenAI format at https://api.uplinkswitch.com/v1, $2.36 input and $2.36 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.
- How many parameters does Qwen2.5 72B Instruct have?
- 72.7B, dense, per Qwen/Qwen2.5-72B-Instruct.
- What is Qwen2.5 72B Instruct's context window?
- 131,072 tokens, with up to 8,192 generated, per Qwen/Qwen2.5-72B-Instruct.
- Is Qwen2.5 72B Instruct open source?
- Its weights are open on Hugging Face (Qwen/Qwen2.5-72B-Instruct); the license is the Qwen license.
- What does Qwen2.5 72B Instruct cost per 100 messages?
- $0.59 for 100 chat turns of 2,000 input and 500 output tokens each, at $2.36 input and $2.36 output per million tokens, from prepaid credit with no subscription.
- Qwen2.5 72B Instruct or Qwen2.5 7B Instruct?
- Same Qwen2.5 generation: 72B for quality, 7B for low cost. Qwen2.5 72B Instruct is $2.36 / $2.36 per million tokens in / out, $5.90 for 1,000 chat turns; Qwen2.5 7B Instruct is $0.20 / $0.20 per million tokens in / out, $0.50 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.