jishie

kimi-k2-thinking

poe/novita/kimi-k2-thinking · family kimi-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

This is a text model — providers price it per unit, not per token, so models.dev carries no token price (fields read “—”). See Poe’s docs for per-unit rates.

Provider
Poe (poe)
Kind
text (outputs text)
Context
256,000 tokens
Max output
0 tokens
Capabilities
tools reasoning text

Same model, other providers

“kimi-k2-thinking” is offered by 3 providers — cheapest-effective first. 302.AI is the cheapest at $1.01 blended.

ProviderInputOutputBlendedContext
302.AI$0.575$2.3$1.01262k
Hugging Face$0.6$2.5$1.07262k
Poe (this)———256k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Poe and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"novita/kimi-k2-thinking","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Poe models · model index · JSON