Connect Roo Code to relay.fast
Roo Code is a VS Code coding agent that started as a fork of Cline. Its developers no longer maintain it. The setup below still works, but for a new install consider Kilo Code or Cline, which still receive updates.
Manual setup
- Create a relay.fast API key for this machine.
- In the Roo Code settings, choose the OpenAI Compatible API provider.
- Set the base URL to
https://relay.fast/v1, paste the key, and enter a model ID from the catalog, such asclaude-sonnet-5-5. - Save the profile and run a short task to confirm the connection.
One-command setup
The script configures Roo Code for relay.fast. It writes a settings file that Roo Code imports when VS Code, Cursor, VSCodium or Windsurf starts. Profiles Roo Code has already imported stay until you delete them. It asks for the API key inside the script, so the key never appears in the command or shell history. Every downloaded file is checked against a published SHA-256 checksum, and running it again can restore the previous settings.
Windows (PowerShell):
powershell -NoProfile -ExecutionPolicy Bypass -Command "irm https://relay.fast/downloads/setup/install-roo-code-en.ps1 | iex"macOS and Linux:
curl -fsSL https://relay.fast/downloads/setup/install-roo-code-en.sh | bashYou can read the script before running it by opening the same URL in a browser.
Keep agent costs under control
A coding agent sends the conversation, file contents and tool results with every step, so input tokens make up most of the bill. Use a mid-priced model for routine edits and a frontier model for hard tasks, prefer models with a cache-read price for long sessions, and keep auto-approve limits low until you know what a typical task costs. Current prices are in the live pricing catalog.
Troubleshooting
- 401 or invalid key: the key is wrong, revoked, or pasted with spaces. Create a new key and paste it again.
- 404 or model not found: the base URL must end with
/v1and the model ID must match the catalog exactly. - Context length errors: the task is larger than the model's context window. Start a new task or pick a model with a larger window.
Current prices of models for coding agents
Prices checked from the live catalog. "From" is the lowest price among the relay.fast sources that currently serve the model. The price you pay depends on the source your request uses and can change on any day. The pricing page always shows current values.
| Model | Model ID | Official input / output per 1M tokens | relay.fast from, input / output | Cache read from | Context |
|---|---|---|---|---|---|
| Claude Sonnet 5.5 | claude-sonnet-5-5 | $2 / $10 | $0.238 / $1.19 (−88%) | $0.0238 | 1M |
| Claude Opus 5.5 | claude-opus-5-5 | $4 / $20 | $0.111 / $0.556 (−97%) | $0.00556 | 1M |
| GPT-6.1 Sol requests above 272K input tokens cost more | gpt-6.1-sol | $2 / $10 | $0.03 / $0.15 (−98%) | $0.0015 | 1.05M |
| GLM-5.3 | glm-5.3 | $1.4 / $4.4 | $0.035 / $0.11 (−97%) | $0.0065 | 1M |
| Kimi K3 | kimi-k3 | $3 / $15 | $0.15 / $0.75 (−95%) | $0.015 | 1.05M |
| DeepSeek V4.1 Flash price depends on the time of day; the peak-hours price is shown | deepseek-v4.1-flash | $0.3 / $1.2 | $0.03 / $0.12 (−90%) | $0.0006 | 1M |
Frequently asked questions
Is Roo Code still maintained?
Its developers no longer maintain it, so it gets no new fixes. Existing installs keep working with an OpenAI-compatible endpoint; Kilo Code and Cline are maintained alternatives.
Which provider do I choose in Roo Code?
OpenAI Compatible, with the base URL https://relay.fast/v1, your relay.fast key and a model ID from the catalog.
How do I remove the imported profile?
Delete the relay.fast profile in the Roo Code settings. Running the installer again with the restore action removes the import file it wrote.