GeniusRelay
Sign upConsole

Meituan LongCat: LongCat 2.5 Preview

longcat-2.5-preview

CompareAPIGet an API keyGet an API key

LongCat 2.5 Preview costs $1.02 per million input tokens and $4.03 per million output tokens, supports 1M context, and is available through the OpenAI-compatible API.

LongCat 2.5 Preview is multimodal model for long-context analysis, coding, and agent workflows. It supports image input, tool calling, optional extended thinking, a 1M-token context window, and up to 128K output tokens.

Modalities

Text + Image → Text

Input / output price

$1.02 / $4.03 per 1M

Context

1M · max output 131K

Capabilities

ReasoningVisionTool callingLong context

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$1.02
Output$4.03
Cached input$0.0205

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00629
Per day
$3.15
Per month (30 days)
$94.39

LongCat 2.5 Preview: input $1.0238/M · output $4.0267/M · cached input $0.0205/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "longcat-2.5-preview", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to longcat-2.5-preview.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "longcat-2.5-preview",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is LongCat 2.5 Preview billed?
Input is $1.02 and output is $4.03 per million tokens; cached input is $0.0205. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
1M tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.
LongCat 2.5 Preview API pricing · GeniusRelay