Models / Meituan
LongCat 2.0 API pricing
$3.00 in, $11.8002 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | Meituan list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $3.00 | — |
| Cached input | — | $0.06 | — |
| Output | — | $11.8002 | — |
LongCat 2.0: what it is · from Meituan’s own model card, read 2026-10-20
Meituan’s LongCat-2.0, a mixture of experts with 1.6 trillion parameters. Meituan trained it on more than 35 trillion tokens and built LongCat Sparse Attention for long-horizon tasks. It is served as longcat-2.0 at $3.00 input and $11.8002 output per million tokens, on the same key as every other model in the catalog.
| LongCat 2.0 | |
|---|---|
| Developer | Meituan |
| Parameters | 1.6T total, about 48B active per token |
| Context | 262,144 tokens in its config |
| License | MIT |
| Published | 2026-07-05 |
| Downloads, 30 days to 2026-10-20 | 2,497 |
| Source | meituan-longcat/LongCat-2.0 |
From meituan-longcat/LongCat-2.0, read 2026-10-20.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"longcat-2.0","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'LongCat 2.0 next to Meituan’s other models · per million tokens, live
| Model | Here, in / out | 1,000 chat turns |
|---|---|---|
| LongCat 2.0 | $3.00 / $11.8002 | $11.90 |
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 LongCat 2.0: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $3.00 input and $11.8002 output per million tokens, that is $6.00 + $5.9001 = $11.90, paid from prepaid credit with no subscription.
LongCat 2.0 API key · base URL and setup
- Create a key in the console at uplinkswitch.ai/console. Credit is prepaid from $10 with no subscription, and the key works at once.
- Point your SDK or tool at https://api.uplinkswitch.com/v1, for example with OPENAI_BASE_URL, and send the key as the bearer token.
- Send longcat-2.0 as the model. The same key calls every other model in the catalog.
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="longcat-2.0",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)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: 'longcat-2.0',
messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"longcat-2.0","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.