Skip to main content

​
1. What should I enter for the API base URL?

Depending on the protocol, there are several options: Note: If you encounter a 404 error, check whether there is an extra /v1 at the end of the URL. Different tools have different path concatenation logic.

​
2. What should I do if I get a 401 “invalid token” error?

  1. Confirm the API Key has been correctly created: https://myrouter.ai/settings/key-management
  2. Confirm the Authorization header format is: Bearer sk_xxxxxx
  3. If using Claude Code, the environment variable should be set as ANTHROPIC_AUTH_TOKEN=sk_xxxxx (no need to add the Bearer prefix; the tool adds it automatically)

​
3. How do I troubleshoot a 404 “page not found” error?

Common causes:
  • Incorrect URL: e.g., typo in /v3/glm-asr
  • Model routing error: e.g., Codex models need to use /v1/responses instead of /v1/chat/completions
  • Tool auto-concatenation issue: Some tools (e.g., cc-switch) automatically append /chat/completions, in which case the Base URL should not include that path

​
4. How do I configure Myrouter in Claude Code?

Set the environment variables as follows: Windows cmd: 
set ANTHROPIC_BASE_URL=https://api.myrouter.ai/anthropic
set ANTHROPIC_AUTH_TOKEN=sk_your_api_key
set ANTHROPIC_MODEL=claude-opus-4-1-20250805
set ANTHROPIC_SMALL_FAST_MODEL=claude-sonnet-4-20250514
Mac/Linux bash: 
export ANTHROPIC_BASE_URL=https://api.myrouter.ai/anthropic
export ANTHROPIC_AUTH_TOKEN=sk_your_api_key
export ANTHROPIC_MODEL=claude-opus-4-1-20250805
export ANTHROPIC_SMALL_FAST_MODEL=claude-sonnet-4-20250514
Reference documentation: https://docs.myrouter.ai/docs/integration/claudecode

​
5. How do I resolve Claude Code forcing login/requiring verification?

The latest version of Claude Code may require mandatory login. Solutions:
  • Use the Cline plugin as an alternative (search in the VSCode plugin marketplace)
  • Or use forwarding tools like cc-switch

​
6. How do I call GPT-5.1 / Codex models? Why am I getting a 400 error?

The GPT-5.1 series (including Codex) requires the OpenAI Responses API, not Chat Completions: 
curl "https://api.myrouter.ai/openai/v1/responses" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <API Key>" \
-d '{
    "model": "gpt-5.1-codex",
    "input": [...],
    "max_output_tokens": 64000
  }'

​
7. What should I do about “thinking block” errors with Claude 4.5?

The error typically says: Expected ‘thinking’ or ‘redacted_thinking’, but found ‘text’. This is because after enabling the Thinking feature for Claude 4.5, the context must include a specific thinking block format. Suggestions:
  • Clear conversation history and start over
  • Or disable the Thinking feature (if not needed)
  • Use the native Anthropic protocol instead of the OpenAI compatible protocol (the latter may have incomplete Thinking support)

​
8. Getting an “input too long” error when calling the Claude API?

Claude models have input length limits (typically max_tokens supports up to 64000). Please check:
  • Input text length
  • Base64 image size (compress large images first)
  • Accumulated conversation history context length
Contact Support If the above FAQ does not resolve your issue, please contact technical support through the following channels:
  • Email: support@myrouter.ai
  • Please provide the following information:
    • Problem description + screenshots
    • Account ID (UUID)
    • Trace ID (if available, usually found in the error message)
    • Request parameters (with sensitive data redacted)