jishie

Kimi K2.5

aihubmix/kimi-k2.5 · family kimi-k2 · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.

$1.20
Blended $/1M (3:1)
$0.6
Input $/1M
$3
Output $/1M
$3.60
1M in + 1M out
$0.1 −83%
Cache read $/1M
#4358 of 7,708
Cheapest rank
Provider
AIHubMix (aihubmix)
Kind
text (outputs text)
Context
262,144 tokens
Max output
32,768 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“Kimi K2.5” is offered by 37 providers — cheapest-effective first. Alibaba Token Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Alibaba Token Planfreefree$0.00262k
Alibaba Coding Planfreefree$0.00262k
Alibaba Token Plan (China)freefree$0.00262k
SCNet Token Planfreefree$0.00262k
Alibaba Coding Plan (China)freefree$0.00262k
NanoGPT$0.3$1.9$0.70256k
DevPass (LLM Gateway)$0.405$1.98$0.80262k
Deep Infra$0.45$2.25$0.90262k
OpenRouter$0.45$2.25$0.90262k
Meganova$0.45$2.8$1.04262k
DigitalOcean$0.5$2.7$1.05262k
Cortecs$0.495$2.77$1.06262k
AIHubMix (this)$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 AIHubMix and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"kimi-k2.5","messages":[{"role":"user","content":"hello"}]}'

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

← all AIHubMix models · model index · JSON