GeniusRelay
Sign upConsole

Moonshot: Kimi K2.5 Thinking

kimi-k2.5:thinking

CompareAPIGet an API keyGet an API key

Kimi K2.5 Thinking costs $0.815 per million input tokens and $4.18 per million output tokens, supports 262K context, and is available through the OpenAI-compatible API.

Kimi K2.5 with thinking mode enabled. Built on Kimi K2 with ~15T mixed visual and text tokens, it excels at general reasoning, visual coding, and agentic tool-calling. Produces reasoning traces for complex multi-step workflows.

Modalities

Text + Image → Text

Input / output price

$0.815 / $4.18 per 1M

Context

262K · max output 66K

Capabilities

ReasoningVisionTool callingLong contextOpen weights

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$0.815
Output$4.18
Cached input$0.137

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00579
Per day
$2.90
Per month (30 days)
$86.86

Kimi K2.5 Thinking: input $0.8145/M · output $4.1843/M · cached input $0.1369/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": "kimi-k2.5:thinking", "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 kimi-k2.5:thinking.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.5:thinking",
    "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 Kimi K2.5 Thinking billed?
Input is $0.815 and output is $4.18 per million tokens; cached input is $0.137. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
262K 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.
Kimi K2.5 Thinking API pricing · GeniusRelay