jishie

Kimi K2.5

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

$1.18
Blended $/1M (3:1)
$0.574
Input $/1M
$3.01
Output $/1M
$3.58
1M in + 1M out
$0.225 −61%
Cache read $/1M
#4726 of 8,512
Cheapest rank
Provider
DevPass (LLM Gateway) (llmgateway)
Kind
text (outputs text)
Context
262,144 tokens
Max output
262,144 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“Kimi K2.5” is offered by 29 providers — cheapest-effective first. Alibaba Coding Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Alibaba Coding Planfreefree$0.00262k
SCNet Token Planfreefree$0.00262k
Alibaba Token Plan (China)freefree$0.00262k
Alibaba Coding Plan (China)freefree$0.00262k
Alibaba Token Planfreefree$0.00262k
NanoGPT$0.375$2$0.78262k
Deep Infra$0.45$2.25$0.90262k
Meganova$0.45$2.25$0.90262k
Auriko$0.45$2.25$0.90262k
TensorX$0.5$2.8$1.07262k
DevPass (LLM Gateway) (this)$0.574$3.01$1.18262k
Merge Gateway$0.6$3$1.20262k
Kilo Gateway$0.6$3$1.20256k

Call it

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

Most providers are OpenAI-compatible — point base_url at DevPass (LLM Gateway) 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 DevPass (LLM Gateway) models · model index · JSON