jishie

Kimi-K2-Thinking

huggingface/moonshotai/Kimi-K2-Thinking · family kimi-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$1.07
Blended $/1M (3:1)
$0.6
Input $/1M
$2.5
Output $/1M
$3.10
1M in + 1M out
$0.15 −75%
Cache read $/1M
#4205 of 7,708
Cheapest rank
Provider
Hugging Face (huggingface)
Kind
text (outputs text)
Context
262,144 tokens
Max output
262,144 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 (this)$0.6$2.5$1.07262k
Poe———256k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"moonshotai/Kimi-K2-Thinking","messages":[{"role":"user","content":"hello"}]}'

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

← all Hugging Face models · model index · JSON