LongCat-2.0
siliconflow/meituan-longcat/LongCat-2.0 · family longcat · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$1.30
Blended $/1M (3:1)
$0.75
Input $/1M
$2.95
Output $/1M
$3.70
1M in + 1M out
$0.015 −98%
Cache read $/1M
#4459 of 7,708
Cheapest rank
- Provider
- SiliconFlow (
siliconflow) - Kind
- text (outputs text)
- Context
- 1,049,000 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“LongCat-2.0” is offered by 4 providers — cheapest-effective first. OpenCode Go is the cheapest at $0.52 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| OpenCode Go | $0.3 | $1.2 | $0.52 | 1M |
| SiliconFlow (this) | $0.75 | $2.95 | $1.30 | 1M |
| LongCat | $0.75 | $2.95 | $1.30 | 1M |
| AIHubMix | $0.7746 | $3.1 | $1.36 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at SiliconFlow and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"meituan-longcat/LongCat-2.0","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):