How is K2-Think billed?

Input is $0.221 and output is $0.884 per million tokens; cached input is $0.111. The charge for every request is listed in Usage Logs in the console.

How long is the context window?

128K 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.

Community: K2-Think

k2-think

Compare API Get an API key Get an API key

K2-Think costs $0.221 per million input tokens and $0.884 per million output tokens, supports 128K context, and is available through the OpenAI-compatible API.

K2-Think is a 32B open-weights general reasoning model with strong competitive math performance. Benchmarks: AIME 2024 90.83, AIME 2025 81.24, GPQA-Diamond 71.08, LiveCodeBench v5 63.97.

Modalities

Text → Text

Input / output price

$0.221 / $0.884 per 1M

Context

128K · max output 33K

Capabilities

Open weights

Pricing

Billed per token actually used and deducted from your credits.

Item	USD per 1M tokens
Input	$0.221
Output	$0.884
Cached input	$0.111

Calculator

Drag the sliders to estimate what this model will cost.

Input per request 3K tokensOutput per request 800 tokensRequests per day 500Cached input 0%(higher with long chats or a fixed system prompt)

Per request: $0.00137
Per day: $0.6851
Per month (30 days): $20.55

K2-Think: input $0.221/M · output $0.884/M · cached input $0.1105/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": "k2-think", "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 k2-think.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "k2-think",
    "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 K2-Think billed?: Input is $0.221 and output is $0.884 per million tokens; cached input is $0.111. The charge for every request is listed in Usage Logs in the console.
How long is the context window?: 128K 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.

Pricing

Calculator

Code samples

Parameters

Related models

FAQ