Claude Code & Codex

Morph serves its open models on both the OpenAI and Anthropic wire formats (see Endpoints). You need a Morph API key.

Claude Code

Claude Code speaks the Anthropic Messages API, which Morph serves natively at /v1/messages. It’s the same two-env-var setup as any Anthropic-compatible provider. ANTHROPIC_MODEL remaps sonnet/opus, ANTHROPIC_SMALL_FAST_MODEL remaps haiku (background tasks like titles and summaries).

export ANTHROPIC_BASE_URL="https://api.morphllm.com"
export ANTHROPIC_AUTH_TOKEN="YOUR_MORPH_API_KEY"
export ANTHROPIC_MODEL="morph-glm52-744b"
export ANTHROPIC_SMALL_FAST_MODEL="morph-qwen36-27b"
claude

Or persist it in ~/.claude/settings.json:

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.morphllm.com",
    "ANTHROPIC_AUTH_TOKEN": "YOUR_MORPH_API_KEY",
    "ANTHROPIC_MODEL": "morph-glm52-744b",
    "ANTHROPIC_SMALL_FAST_MODEL": "morph-qwen36-27b"
  }
}

For per-task routing across several models in one session (a cheap model for background work, a bigger one for edits), use Claude Code Router (ccr code) with a morph provider pointed at https://api.morphllm.com/v1/chat/completions.

Codex

Codex speaks only the OpenAI Responses API; the wire_api = "chat" path was removed in February 2026, and Morph’s chat models serve Chat Completions and Messages, not Responses. Two ways to run Morph: Front Morph with a Responses gateway. Put LiteLLM (or any Responses-compatible router) in front of api.morphllm.com and point Codex’s base_url at the gateway:

# ~/.codex/config.toml
model = "morph-glm52-744b"
model_provider = "morph"

[model_providers.morph]
name = "Morph via LiteLLM"
base_url = "http://localhost:4000/v1"   # your LiteLLM proxy
env_key = "MORPH_API_KEY"
wire_api = "responses"

Or add Morph’s fast edits as a tool. Keep your current Codex model and give it edit_file backed by morph-v3-fast at 10,500+ tok/s (no gateway):

# ~/.codex/config.toml
[mcp_servers.morph]
command = "npx"
args = ["-y", "@morphllm/morphmcp"]
env = { MORPH_API_KEY = "YOUR_MORPH_API_KEY", ALL_TOOLS = "false" }

Model IDs and context windows are on the Open Source Models page; per-token rates are on the pricing page.

Get Started

Models

API Reference

Integrations

Claude Code

Codex

​Claude Code

​Codex

Claude Code

Codex