log inget an API key

Claude Code with SayGM

Anthropic's terminal agent, running on SayGM's Claude models.

Model

Claude Opus 5.5Best quality

In $4.00$3.57Out $20.00$17.86/1M

Sign in to fill these snippets with a SayGM key for Claude Code.

Sign in

Setup for Claude models

Use this setup with the models listed under Claude below.

  1. 11 · Point it at SayGM
    json
    {
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.saygm.com",
    "ANTHROPIC_API_KEY": "<YOUR_SAYGM_KEY>",
    "ANTHROPIC_MODEL": "claude-opus-5-5"
  }
}
  2. 22 · Run
    bash
    claude

Switch models inside Claude Code with /model claude-sonnet-5.

First request

  1. 1Send a first request
    bash
    claude -p "say gm"

Troubleshooting

Claude Code still shows the login screen.
Put the variables in ~/.claude/settings.json or your shell. A project .claude/settings.json only applies after the first-run wizard and the trust prompt.
Claude Code asks whether to use a custom API key.
Choose Yes. It asks once, in interactive mode, with No selected by default. To change your answer later, use the Use custom API key toggle in /config.
Claude Code still uses your Claude subscription.
An approved ANTHROPIC_API_KEY takes priority over a subscription login, and claude -p always uses it. If you chose No at the key prompt, turn on Use custom API key in /config.
400 errors that mention context_management or another unknown field.
Set CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1 to turn off beta request fields.
Not sure which endpoint Claude Code is using.
Run /status. It shows the Anthropic base URL and which credential is in use.

Models you can use with Claude Code

Claude Code is built for Claude, so it runs SayGM's Claude models.

Claude

9 models
  • Claude Opus 5.5claude-opus-5-5Best qualityThe newest Opus: hard coding and long agentic work at a lower Opus price.In $4.00$3.57Out $20.00$17.86/1M
  • Claude Sonnet 5claude-sonnet-5Best valueEveryday coding and agent work at a fraction of Opus pricing.In $2.00$1.79Out $10.00$8.93/1M
  • Claude Fable 5.1claude-fable-5-1Anthropic's most capable model, for the most demanding long-horizon tasks.In $10.00$8.93Out $50.00$44.65/1M
  • Claude Fable 5claude-fable-5Anthropic's top tier before Fable 5.1, for deep reasoning and agentic work.In $10.00$8.93Out $50.00$44.65/1M
  • Claude Opus 5claude-opus-5Opus 5 for complex coding and agents that need careful reasoning.In $5.00$4.47Out $25.00$22.33/1M
  • Claude Opus 4.8claude-opus-4-8Opus 4.8 for teams whose prompts are tuned to the Opus 4 line.In $5.00$4.47Out $25.00$22.33/1M
  • Claude Opus 4.7claude-opus-4-7Opus 4.7 for workflows pinned to that release.In $5.00$4.47Out $25.00$22.33/1M
  • Claude Sonnet 4.6claude-sonnet-4-6Sonnet 4.6 for workflows pinned to the previous Sonnet.In $3.00$2.68Out $15.00$13.40/1M
  • Claude Haiku 4.5claude-haiku-4-5Fast, low-cost Claude for quick edits, subagents and high-volume calls.In $1.00$0.89Out $5.00$4.47/1M

About Claude Code

Claude Code is Anthropic's agentic coding tool. It runs in your terminal and in VS Code and JetBrains, reads your codebase, edits files, runs commands and works through multi-step changes. Developers use it to build features, fix bugs and refactor across a whole repository from one prompt.