Claude Code

Claude Code is Anthropic's official terminal coding agent — a single claude command that reads files, makes edits, runs tools, and holds a session's worth of context across turns. The distinguishing behavior is how hard it pushes on exploration: slash commands, long tool chains, multi-file edits, thorough summaries. That thoroughness costs tokens. Because it reads ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN, pointing it at Melious is two environment variables — our Messages endpoint implements the Anthropic SDK and maps claude-* model names to the open-weight models we actually run.

Setup

melious tools install claude-code
melious launch claude-code

curl -fsSL https://claude.ai/install.sh | bash

irm https://claude.ai/install.ps1 | iex

brew install --cask claude-code            # macOS, Linux
winget install Anthropic.ClaudeCode        # Windows
npm install -g @anthropic-ai/claude-code   # any platform, requires Node 18+

# Required.
export ANTHROPIC_BASE_URL=https://api.melious.ai  
export ANTHROPIC_AUTH_TOKEN=sk-mel-<YOUR_API_KEY>
export ANTHROPIC_API_KEY=""

# Recommended. Pins every slot Claude Code may reach for at
# runtime — including hard-coded names like `claude-haiku-4-5`
# Anthropic uses for background tasks — to a known Melious model.
# Also raises the request timeout for long agent runs and stops
# Claude Code from phoning home to Anthropic for telemetry.
export ANTHROPIC_MODEL=<MODEL_ID>
export ANTHROPIC_SMALL_FAST_MODEL=<LIGHTWEIGHT_MODEL_ID>
export ANTHROPIC_DEFAULT_OPUS_MODEL=<MODEL_ID>
export ANTHROPIC_DEFAULT_SONNET_MODEL=<MODEL_ID>
export ANTHROPIC_DEFAULT_HAIKU_MODEL=<LIGHTWEIGHT_MODEL_ID>
export API_TIMEOUT_MS=3000000
export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.melious.ai",
    "ANTHROPIC_AUTH_TOKEN": "sk-mel-<YOUR_API_KEY>",
    "ANTHROPIC_API_KEY": "",
    "ANTHROPIC_MODEL": "<MODEL_ID>",
    "ANTHROPIC_SMALL_FAST_MODEL": "<LIGHTWEIGHT_MODEL_ID>",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "<MODEL_ID>",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "<MODEL_ID>",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "<LIGHTWEIGHT_MODEL_ID>",
    "API_TIMEOUT_MS": "3000000",
    "CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": "1"
  }
}

claude

Auth token: ANTHROPIC_AUTH_TOKEN
Anthropic base URL: https://api.melious.ai

How model names are mapped

Claude Code hard-codes Anthropic model names (opus, sonnet, haiku). We substring-match them at the edge and route each tier to a Melious model so you don't need a patched client:

The response carries the original claude-sonnet-4 (or whichever name you sent) back in the model field — so Claude Code's internal checks don't trip. The actually-executed model appears in your usage reports, not in the wire response.

The default mapping is admin-configurable per-instance. Browse melious.ai/hub/models for the current model list and see Routing for the full set of config keys.

Picking a specific model

Most current Claude Code releases accept arbitrary --model strings, so this works:

claude --model <MODEL_ID>

If your version validates against Anthropic's allow-list, set the ANTHROPIC_DEFAULT_*_MODEL env vars instead — Claude Code passes whatever string you put there straight through to the API:

export ANTHROPIC_MODEL=<MODEL_ID>
export ANTHROPIC_SMALL_FAST_MODEL=<LIGHTWEIGHT_MODEL_ID>
export ANTHROPIC_DEFAULT_OPUS_MODEL=<MODEL_ID>
export ANTHROPIC_DEFAULT_SONNET_MODEL=<MODEL_ID>
export ANTHROPIC_DEFAULT_HAIKU_MODEL=<LIGHTWEIGHT_MODEL_ID>
export CLAUDE_CODE_SUBAGENT_MODEL=<MODEL_ID>

These are passed through verbatim by Claude Code, and Melious accepts arbitrary model strings server-side, so they're the most reliable way to lock in a specific model. Pin every slot — Claude Code uses *_HAIKU_* and SMALL_FAST_MODEL for background and agent-spawn calls, so leaving them unset can route quietly to whatever's mapped to haiku. Find current IDs at melious.ai/hub/models.

What's different

• Responses carry extra fields server-side. environment_impact and billing_cost ride on every completion. The Anthropic SDK drops unknown fields before Claude Code sees them, but they're logged and surfaced in your usage dashboard.
• Prompt caching (cache_control) is not exposed. Open-weight providers don't surface the same cache handles Anthropic does, and we haven't written a translation. Sessions re-send context each turn; plan costs accordingly. If you need this, tell us.
• Extended thinking blocks pass through as regular text for non-reasoning models. Reasoning-class models produce thinking as part of their output, but the exact Anthropic thinking block shape isn't preserved.

When it breaks

• Hang on the first token — ANTHROPIC_BASE_URL probably has a trailing /v1. Strip it; the SDK adds it itself.
• 401 immediately — the token string lost its sk-mel- prefix when you copied it, or the key was rotated. Paste the full 128-character key.
• Traffic lands on api.anthropic.com / billing shows on Anthropic, not Melious — ANTHROPIC_API_KEY is set somewhere (shell, dotfile, CI secret) and the SDK prefers it over ANTHROPIC_AUTH_TOKEN. Blank it: export ANTHROPIC_API_KEY="". If you previously ran claude login, also /logout to drop cached creds.
• /status shows the wrong base URL — env vars didn't reach the process. Re-export in the same shell you launched claude from, or move the values into .claude/settings.local.json so they're read at startup regardless of shell state.
• Tool loops feel different than with Claude — model-capability thing, not a protocol thing. Stronger models handle longer tool sequences; smaller ones give up earlier. Check _meta.capabilities.tool_use on GET /v1/models?include_meta=true and override the mapping with ANTHROPIC_DEFAULT_*_MODEL for long agent sessions.
• Costs higher than expected — Claude Code's default prompt style is verbose. That's baked in. OpenCode runs the same agent workloads cheaper if that bothers you.

Errors and retry patterns: Errors.