Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.llmeasy.ru/llms.txt

Use this file to discover all available pages before exploring further.

​
Account and billing

LLMEasy charges by actual token usage and follows Anthropic / OpenAI pricing without adding an extra markup. Every new account gets a ¥5 trial credit.See the pricing page (https://www.llmeasy.ru/#) for details.
Paid top-ups are refundable. Trial credit is not refundable. Contact support if you need a refund.
Yes. The same API Key can be used in Claude Code, Codex, Cursor, and other tools at the same time. Usage is shared.
Log in to the dashboard to view current usage and billing records.

​
Setup and configuration

LLMEasy now uses two different endpoints by protocol:
ScenarioBase URL
Claude Code / ANTHROPIC_BASE_URLhttps://www.llmeasy.ru
Codex / OPENAI_BASE_URL / external toolshttps://www.llmeasy.ru/v1
Do not reuse one address across every tool.
It depends on your API Key group.With a Claude_* key, only set ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN. You do not need model variables.With a Codex_* key, add Claude Code model mappings through ANTHROPIC_DEFAULT_HAIKU_MODEL, ANTHROPIC_DEFAULT_SONNET_MODEL, and ANTHROPIC_DEFAULT_OPUS_MODEL. Copy the model ID from the current Codex group in the model plaza (https://www.llmeasy.ru/pricing).
Yes. Fill in a model ID copied from the Codex group in the model plaza (https://www.llmeasy.ru/pricing).See the Codex setup guide for details.
Yes. External tools such as Cursor, Cline, Zed, and OpenClaw now use the Codex group. Copy the current model ID from the model plaza (https://www.llmeasy.ru/pricing).Do not keep using hardcoded Claude model names in these tools.See the Cursor setup guide for details.
Usually not.Based on the official docs we checked, common external tools like Cursor, Cline, and Zed focus on the Base URL, API key, and model ID. OpenCode and OpenClaw do support optional headers, but their official docs describe that as custom headers or custom auth needs, not as a required LLMEasy setup step.Only add extra headers when the tool’s official docs, or your own upstream gateway, tenant routing, observability, or caching layer explicitly requires them.
Check the following:
  1. Make sure the API Key is correct and has no extra spaces
  2. Confirm Claude Code uses https://www.llmeasy.ru, while Codex / external tools use https://www.llmeasy.ru/v1
  3. Check whether old ANTHROPIC_AUTH_TOKEN, ANTHROPIC_BASE_URL, OPENAI_API_KEY, or OPENAI_BASE_URL variables are overriding the config
  4. For external tools, check whether there are additional official requirements such as version limits, model allowlists, or extra headers explicitly required by your upstream gateway
If the issue remains, contact support.

​
Reliability and rate limits

LLMEasy connects to multiple suppliers and uses the following mechanisms:
  • Multi-source supply: one supplier outage does not take down your requests
  • Dynamic routing: LLMEasy picks the fastest and most stable path in real time
  • Flagship focus: reliability work is concentrated on Claude Code and the Codex ecosystem
LLMEasy automatically handles individual supplier rate limits and timeouts. If issues continue:
  1. Check that your balance is sufficient
  2. Increase the timeout for your tool (API_TIMEOUT_MS=3000000 is recommended)
  3. Contact support to confirm the current quota status
LLMEasy is primarily built for individual developers using AI coding tools such as Claude Code and Codex. For large-scale production API workloads, evaluate it against your own requirements.

​
Privacy and security

LLMEasy acts as a relay and does not persist conversation content. See the Privacy Policy (https://www.llmeasy.ru/privacy) for details.
Log in to the dashboard immediately, delete the old key, and generate a new one. Then update every tool that uses that key.