Kimi K2.5
Moonshot most versatile model, native multimodal architecture, supports vision and text, thinking and non-thinking modes, dialogue and Agent tasks
Description
Moonshot most versatile model, native multimodal architecture, supports vision and text, thinking and non-thinking modes, dialogue and Agent tasks
Available Providers
AllToken can route requests to the providers below based on route priority and policy.
Best For
Moonshot most versatile model, native multimodal architecture, supports vision and text, thinking and non-thinking modes, dialogue and Agent tasks
How To Use This Model
Use the exact model ID shown below. This is the safest way to avoid call failures, variant mismatches, or incorrect route assumptions.
curl https://api.alltoken.ai/v1/chat/completions \
-H "Authorization: Bearer sk-your-key" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k2.5",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'temperaturetop_pmax_tokenstoolsresponse_formatreasoning_effortweb_searchLet the platform choose the best provider path automatically.
If a request does not specify a model, default the key to kimi-k2.5.
Always override incoming requests and lock the key to kimi-k2.5.