jishie

Kimi-K2.5

nebius/moonshotai/Kimi-K2.5 · family kimi-k2 · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimage.

$1.00Blended $/1M (3:1)
$0.5Input $/1M
$2.5Output $/1M
$3.001M in + 1M out
$0.05 −90%Cache read $/1M
#3132 of 5,000Cheapest rank
Provider
Nebius Token Factory (nebius)
Context
256,000 tokens
Max output
8,192 tokens
Capabilities
toolsreasoningtextimage

Same model, other providers

“Kimi-K2.5” is offered by 5 providers — cheapest-effective first. Tencent Coding Plan (China) is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Tencent Coding Plan (China)freefree$0.00262k
Nebius Token Factory (this)$0.5$2.5$1.00256k
Poe$0.6$3$1.20128k
FrogBot$0.6$3$1.20256k
Hugging Face$0.6$3$1.20262k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Nebius Token Factory 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-K2.5","messages":[{"role":"user","content":"hello"}]}'

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