Coding agents

These docs are markdown-first on purpose: the primary reader is often a coding agent. Every page is dual-served — /docs/<slug> rendered for humans, /docs/<slug>.md as raw markdown for agents — and the machine index lives at https://app.routerplus.com/llms.txt.

This page covers wiring Claude Code and Codex CLI through the gateway and an installation runbook for a coding agent. The user completes signup and email verification through Clerk in a browser before the agent configures an API client. To build the gateway into a product instead, give your agent the Agent integration guide.

Claude Code

Claude Code speaks the Anthropic wire format, which the gateway's /v1/messages surface accepts directly. Two environment variables, no other change:

export ANTHROPIC_BASE_URL=https://api.routerplus.com
export ANTHROPIC_AUTH_TOKEN=$TM_API_KEY
claude

Or as a one-shot launch:

ANTHROPIC_BASE_URL=https://api.routerplus.com ANTHROPIC_AUTH_TOKEN=$TM_API_KEY claude

What makes this work:

• ANTHROPIC_AUTH_TOKEN is sent as Authorization: Bearer …, which the gateway accepts everywhere (as it does x-api-key).
• Claude Code appends query strings (/v1/messages?beta=true); the gateway routes on the pathname, so these pass through cleanly.
• Model ids resolve against the catalog at https://app.routerplus.com/api/models.json, which lists one clean id per model (claude-haiku-4-5, claude-sonnet-4-5, …). Claude Code often sends dated ids (claude-haiku-4-5-20251001); those resolve to their family automatically and your original id goes to the provider verbatim — see Models & catalog. A genuinely unknown id gets an honest 404 naming it.
• Every request Claude Code makes lands in https://api.routerplus.com/v1/usage with its token counts and cost_usd, so you can watch what a session costs.

Persistent setup

Exports vanish with the shell. To make the gateway Claude Code's default, put the env block in ~/.claude/settings.json (or a project's .claude/settings.json to scope it to one repo):

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.routerplus.com",
    "ANTHROPIC_AUTH_TOKEN": "tm_vk_..."
  }
}

Pinning which models Claude Code uses

Claude Code picks its own model ids; steer them with the standard variables, using any Claude id from the catalog:

export ANTHROPIC_MODEL=claude-sonnet-5          # main model
export ANTHROPIC_SMALL_FAST_MODEL=claude-haiku-4-5  # background/fast tasks

Inside a session, /model accepts any catalog id the same way. Spend from every session lands in the console and https://api.routerplus.com/v1/usage, per request.

Codex CLI

Codex releases from before February 2026 still speak Chat Completions. For those, pin the wire in the provider block:

# ~/.codex/config.toml
[model_providers.tm]
name = "RouterPlus"
base_url = "https://api.routerplus.com/v1"
env_key = "TM_API_KEY"
wire_api = "chat"

[profiles.tm]
model_provider = "tm"
model = "gpt-4o-mini"

TM_API_KEY=tm_vk_... codex --profile tm

On such a release, wire_api = "chat" is a requirement, not a preference: a profile left on the Responses wire fails on every call.

Other OpenAI-compatible harnesses

Most coding tools that speak "OpenAI-compatible" take the same two values: base URL https://api.routerplus.com/v1 and API key tm_vk_.... The pattern, in the tools' own vocabulary:

Every chat model in the catalog works through this surface — Claude models included (image models use POST /v1/images/generations, video models POST /v1/videos); the gateway translates. Two honest caveats:

• Tools built on the OpenAI Responses API (the OpenAI Agents SDK's default, and every current Codex CLI release) do not work yet: POST /v1/responses returns a
  404. 404
       Pick the tool's Chat Completions mode where one exists.
• These are configuration patterns, not per-version walkthroughs — tool UIs move. The two values above are the invariant.

SDKs inside the project your agent is editing

Full streaming examples for both surfaces are in the Quickstart; for migrating a whole codebase in one prompt, see Migrate.

The installation runbook

This section is written to be executed. Give it to your agent — read https://app.routerplus.com/docs/install.md and get me set up — or walk it yourself.

Objective: this environment makes a successful, streamed, billed model call through the gateway.

Done when: a streamed completion ends with a usage object containing a cost field, and https://api.routerplus.com/v1/usage shows the request.

1. 01

   Get a key (skip if TM_API_KEY is already set). The user opens Sign up, completes Clerk authentication and email verification, and saves the first key shown after sign-in. Signup does not grant free credit: add paid credits in Billing. Existing customers sign in at https://app.routerplus.com/login with the same verified email and create a key at API keys. Raw keys are shown once. Account creation has no terminal API; do not call the retired POST /v1/signup or local POST /login routes. Continue client setup when the key is available.

2. 02

   Export the key, and write it to the project's .env if one exists (never commit it):

   bashcopy

   export TM_API_KEY=tm_vk_...

3. 03

   Discover the models. Any id in this file works in step 4:

   bashcopy

   curl -s https://app.routerplus.com/api/models.json

4. 04

   Make the test call. OpenAI-compatible surface; works for every chat model, including Claude models — the gateway translates:

   bashcopy

   curl -N https://api.routerplus.com/v1/chat/completions \
     -H "Authorization: Bearer $TM_API_KEY" \
     -H "content-type: application/json" \
     -d '{"model":"claude-haiku-4-5","stream":true,"max_tokens":40,"messages":[{"role":"user","content":"Reply with exactly: MARKETPLACE OK"}]}'

   Expected: an SSE stream ending with a usage chunk that has a cost field, then data: [DONE].

   On HTTP 429 with error_type: insufficient_quota, stop and have the user check their balance and spend caps in Billing. Retry once after they resolve the cause — never in a loop. The full retry discipline per error class is in Errors.

5. 05

   Wire the user's stack. Apply every branch that matches this environment: the OpenAI SDK, Anthropic SDK, and raw-HTTP changes from the table above; Claude Code exactly as configured earlier on this page, and Codex CLI only when its release is from before February 2026 (see Codex CLI).

6. 06

   Verify billing — the done-when condition:

   bashcopy

   curl -s -H "Authorization: Bearer $TM_API_KEY" https://api.routerplus.com/v1/usage

   The test call must appear in recent_attempts with its token counts and cost_usd.

7. 07

   Optional, recommended: add attribution headers to the user's app — HTTP-Referer: https://the-users-app.example and X-Title: The App Name. Content-free; they identify the app for future per-app analytics and expose no request data.

Finally, report to the user: the org id, where the key is stored, which stacks were wired, and the cost of the test call.

/llms.txt — start here if you are an agent

curl -s https://app.routerplus.com/llms.txt

It carries the gateway base URL, browser signup instructions, links to every doc page in raw-markdown form, and the machine-readable model catalog. Fetch it first; everything else on this page is reachable from it. Its first link is the Agent integration guide, the one page to read before you build the gateway into a product. To load every page with one fetch, use https://app.routerplus.com/llms-full.txt.

Signup requires the browser

Public signup and sign-in use Clerk at Sign up and Sign in. Complete the authentication and email-verification steps there. Local magic-link submission and programmatic signup are retired; there is no dev_verify_link in a public signup response. After signup, agents can use the existing tm_vk_ key with the gateway normally.

Next steps