Models

The catalog at GET /v1/models is the truth. Models belong to one of two teams; the team decides the route and the admission bar. Pass the id as model unchanged.

Shell

curl -s https://api.kotoba.cloud/v1/models -H "Authorization: Bearer $KOTOBA_API_TOKEN"
# → data[].id · team · route · availability

Teams and admission

Blue team
General models on the shared route. A signed-in principal and free quota — and guardrails on every request.

requirements: authenticated-principal · available-free-quota · guardrails
Red team
Security-research-tuned models on the dedicated route. Card-based identity verification, AUP consent, trust route, approved scope, free quota — and guardrails on every request.

requirements: authenticated-principal · verified-ekyc-card · aup-consent · current-aml-ctf-clearance · current-trust-route · approved-research-scope · available-free-quota · guardrails

Current catalog

qwen/qwen3.8-27b served
Blue team · route: shared · source
qwen3.8-27b-whitehacker served
Red team · route: dedicated · source

A model whose route is not configured is refused by name at admission and spends no quota. Which providers stand behind each route is operator configuration and is not stated here.

Per-model detail

qwen/qwen3.8-27b

The general model on the shared route (Qwen3.8-27B itself). Sign-in only, no verification; the three standard tasks (code-review / vulnerability-triage / remediation). The id is the publisher's, used unchanged.

Team: Blue team · route: shared · served
Admission: a signed-in principal, free quota, guardrails (the three standard tasks only)
Ceilings: 524,288 input characters · 32,768 output tokens (reasoning included) · 128 tools · 2,048 turns
The answer's model echoes qwen/qwen3.8-27b (strictly matched)

Shell

curl -s -X POST https://api.kotoba.cloud/v1/chat/completions -H "Authorization: Bearer $KOTOBA_API_TOKEN" \
  -H "content-type: application/json" -d '{"model":"qwen/qwen3.8-27b","max_tokens":2048,"messages":[{"role":"user","content":"..."}]}'

qwen3.8-27b-whitehacker

A dense 27B model tuned for security research (a refusal-removed build of Qwen3.8-27B): code review, vulnerability triage, remediation, with a 262,144-token window. Unrestricted for authorized researchers; card verification and AUP consent are the premise.

Team: Red team · route: dedicated · served
Admission: card verification, AUP consent, approved scope (code-review comes with verification), free quota, guardrails
Ceilings: 524,288 input characters · 32,768 output tokens (reasoning included) · 128 tools · 2,048 turns
The answer's model echoes orcarouter/Qwen3.8-27B-Uncensored-NVFP4 (strictly matched)

Shell

curl -s -X POST https://api.kotoba.cloud/v1/chat/completions -H "Authorization: Bearer $KOTOBA_API_TOKEN" \
  -H "content-type: application/json" -d '{"model":"qwen3.8-27b-whitehacker","max_tokens":2048,"messages":[{"role":"user","content":"..."}]}'