LongCat-2.0
vancine/LongCat-2.0 · family longcat · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.42
Blended $/1M (3:1)
$0.24
Input $/1M
$0.96
Output $/1M
$1.20
1M in + 1M out
$0.0048 −98%
Cache read $/1M
#2271 of 7,000
Cheapest rank
- Provider
- Vancine (
vancine) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“LongCat-2.0” is offered by 3 providers — cheapest-effective first. This one (Vancine) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Vancine (this) | $0.24 | $0.96 | $0.42 | 1M |
| OpenCode Go | $0.3 | $1.2 | $0.52 | 1M |
| LongCat | $0.75 | $2.95 | $1.30 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Vancine and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"LongCat-2.0","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):