Dashboard

# Anthropic Messages is not served on api.mithril.fund (POST /v1/messages → 405).
# Run a translating proxy (LiteLLM, etc.), then point Claude Code at the proxy.
# The proxy calls OpenAI wire: https://api.mithril.fund/v1 with Bearer kc_pat_…

export OPENAI_BASE_URL="https://api.mithril.fund/v1"
export OPENAI_API_KEY="kc_pat_<your-token>"
# export ANTHROPIC_BASE_URL=http://127.0.0.1:4000   # local proxy
# export ANTHROPIC_API_KEY=anything                 # proxy holds the real token
# claude -p "Reply with exactly: OK"

export KOTOBA_API_BASE="https://api.mithril.fund/v1"
export KOTOBA_API_TOKEN="kc_pat_<your-token>"

# test the connection
codex exec "Reply with exactly: OK"

Base URL: https://api.mithril.fund/v1
API Key: kc_pat_<your-token>
Model ID: qwen3.8-flash-next-whitehacker

Provider ID: kotobacloud (lowercase)
Base URL: https://api.mithril.fund/v1
API Key: kc_pat_<your-token>
Model ID: qwen3.8-flash-next-whitehacker

~/.config/opencode/opencode.json:
{
  "provider": {
    "kotobacloud": {
      "baseUrl": "https://api.mithril.fund/v1",
      "apiKey": "kc_pat_<your-token>",
      "models": {"qwen3.8-flash-next-whitehacker": {}}
    }
  }
}

export OPENAI_API_BASE="https://api.mithril.fund/v1"
export OPENAI_API_KEY="kc_pat_<your-token>"

# the openai/ prefix stacks on our model id
aider --model openai/qwen3.8-flash-next-whitehacker

# ~/.hermes/config.yaml (or a profile's config.yaml)
model:
  provider: kotoba
  default: qwen3.8-flash-next-whitehacker
  # no max_tokens: hermes ignores it; the edge's default output budget is 32,768
providers:
  kotoba:
    api: https://api.mithril.fund/v1   # literal: a KOTOBA_API_BASE that already ends in /v1 would become /v1/v1 (405)
    key_env: KOTOBA_API_TOKEN
    transport: chat_completions
    discover_models: true
    request_timeout_seconds: 900
    stale_timeout_seconds: 900
    models:
      qwen3.8-flash-next-whitehacker:
        context_length: 98304   # 131,072 slot - 32,768 output budget
  custom:
    # a named provider runs under this label at runtime — these are the timeouts that apply
    request_timeout_seconds: 900
    stale_timeout_seconds: 900
compression:
  # the answer arrives whole; a summary can take minutes under load
  context_timeout_seconds: 900
  context_total_ceiling_seconds: 900
auxiliary:
  compression:
    provider: kotoba            # REQUIRED with a bare base_url: without it (or key_env) hermes resolves the task to "auto" = the main model
    key_env: KOTOBA_API_TOKEN
    model: qwen/qwen3.8-flash   # the blue route: shares no slot with your session
    base_url: https://api.mithril.fund/v1
    reasoning_effort: none
    timeout: 900
    # optional, off-edge: where the summary goes when THIS edge is silent (needs an OpenRouter key in .env).
    # key_env is required — the stall retry pins the entry as-is and 401s without it. :free SKUs only.
    fallback_chain:
      - provider: openrouter
        model: qwen/qwen3.8-27b:free
        key_env: OPENROUTER_API_KEY
        timeout: 180
      - provider: openrouter
        model: nex-agi/nex-n2.5-mini:free
        key_env: OPENROUTER_API_KEY
        timeout: 120
  title_generation:
    provider: kotoba
    key_env: KOTOBA_API_TOKEN
    model: qwen/qwen3.8-flash
    base_url: https://api.mithril.fund/v1
    reasoning_effort: none
    timeout: 120
fallback_providers:
  - provider: kotoba
    model: qwen/qwen3.8-flash   # same edge; another provider's reasoning_details would be replayed here
    base_url: https://api.mithril.fund/v1
    api_mode: chat_completions

# ~/.hermes/.env — the token is the only thing read from the environment
KOTOBA_API_TOKEN=kc_pat_<your-token>   # issue at https://admin.mithril.fund/account (shown once)
OPENROUTER_API_KEY=sk-or-<optional>     # only for auxiliary.compression.fallback_chain; omit the chain without it

# `personal API token refused: token-unknown` = the token in THIS machine's .env is not in the
# account's registry (issued elsewhere, or before the registry): paste a current one here.
# profiles: start them as `hermes -p <profile>` or with HERMES_HOME=~/.hermes/profiles/<profile>,
# not via the sticky `hermes profile use` (subprocesses then write to the default profile)
hermes chat -Q --oneshot -q "Reply with exactly: OK"

docker run -d -p 3000:8080 \
  -e OPENAI_API_BASE_URL="https://api.mithril.fund/v1" \
  -e OPENAI_API_KEY="kc_pat_<your-token>" \
  ghcr.io/open-webui/open-webui:main

# then open http://localhost:3000 and pick the model

Base URL: https://api.mithril.fund/v1
API Key: kc_pat_<your-token>
Model: qwen3.8-flash-next-whitehacker

from openai import OpenAI
client = OpenAI(
  base_url="https://api.mithril.fund/v1",
  api_key="kc_pat_<your-token>",
)
r = client.chat.completions.create(
  model="qwen3.8-flash-next-whitehacker",
  messages=[{"role": "user", "content": "Reply with exactly: OK"}],
)