jishie

moonshotai/Kimi-K2.5

siliconflow/moonshotai/Kimi-K2.5 · family kimi · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.

$0.90
Blended $/1M (3:1)
$0.45
Input $/1M
$2.25
Output $/1M
$2.70
1M in + 1M out
$0.07 −84%
Cache read $/1M
#3904 of 7,708
Cheapest rank
Provider
SiliconFlow (siliconflow)
Kind
text (outputs text)
Context
262,000 tokens
Max output
262,000 tokens
Capabilities
tools reasoning text image

Same model, other providers

“moonshotai/Kimi-K2.5” is offered by 2 providers — cheapest-effective first. This one (SiliconFlow) is the cheapest.

ProviderInputOutputBlendedContext
SiliconFlow (this)$0.45$2.25$0.90262k
Qiniu———256k

Call it

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

Most providers are OpenAI-compatible — point base_url at SiliconFlow 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):

← all SiliconFlow models · model index · JSON