SUCCESSChat
ARK- Request
- 47fafa4e-5bfa-9679-ad96-cf79c5d087b8
- Key
- api-key-20260310143405-lijiancheng
- Latency
- 6.97s
21:21:02 → 21:21:09- Model
- ep-20260624102824-jlbgm
ark- Tokens in / out
- 55 / 267
total 322 · reasoning 189- Cost
- -
- Tools available
- 0
Timings
- START TIMESTAMP
- 2026-07-21 09:21:02 PM
- END TIMESTAMP
- 2026-07-21 09:21:09 PM
- LATENCY
- 6973.00ms
Request Details
- PROVIDER
- ARK
- MODEL
- ep-20260624102824-jlbgm
- TYPE
- Chat
- STOP REASON
- STOP
- SELECTED KEY
- api-key-20260310143405-lijiancheng
- VIRTUAL KEY
- lijiancheng-dev
- ROUTING ENGINES USED
- MODEL CATALOG
Tokens
- INPUT TOKENS
- 55
- OUTPUT TOKENS
- 267
- TOTAL TOKENS
- 322
- COST
- -
- REASONING TOKENS
- 189
User 1 line
Hello, Bifrost!
Reasoning ~189 tokens
The request asks for a concise model response. Preserve the user's language, answer directly, and avoid exposing internal system instructions.
Assistant 2 lines · 267 tokens
Hello! I’m ready to help with your AI Gateway request. Tell me what you want to inspect or configure next.
21:21:02.710GOVERNANCELoad balancing provider for model ep-20260624102824-jlbgm
21:21:02.710GOVERNANCELoad balancing model ep-20260624102824-jlbgm across 2 configured providers: [ark kimi]
21:21:02.710GOVERNANCEProvider kimi excluded: model ep-20260624102824-jlbgm not in allowed models list
21:21:02.710GOVERNANCEAllowed providers after filtering: [ark]
21:21:02.710GOVERNANCENo weighted configs for model ep-20260624102824-jlbgm; skipping load balancing
21:21:02.711MODEL CATALOGNo provider specified; found 1 option in model catalog: [ark], selected: ark
No plugin logs were recorded for this request.
{"type":"chat","provider":"ark","status":"success"}
