Coding tools

AI coding agents burn the most tokens of any workload — and hit provider rate walls and subscription time windows the hardest. Every tool below has a native endpoint on the gateway — Claude Code over Anthropic's Messages protocol, the rest over OpenAI — so switching to BoostRail takes about 30 seconds: point the base URL at the gateway and drop in one key.

From zero to your first call

Why route your coding agent through BoostRail

Coding agents are the heaviest token consumers in the industry: long files, tool loops, and repeated context make agent load the norm, not the exception. On official subscriptions that means hitting a ~5-hour usage window; on raw API tiers it means bumping into per-minute rate limits mid-task.

BoostRail is one OpenAI-compatible gateway across leading models. The tools you already use keep working unchanged — you only swap the base URL and key. No subscription window, no tier rate wall, and agent-load pricing that is honest about caching.

Copy-paste config, one per tool

Claude Code speaks Anthropic's native Messages protocol against the gateway's /v1/messages endpoint. The rest speak OpenAI — Codex CLI over /v1/responses, the others over chat completions. Either way it is the same key and the same catalog: set the base URL, paste your BoostRail API key, and the model id is any model from the catalog.

// ~/.claude/settings.json
{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.boostrail.com",
    "ANTHROPIC_API_KEY": "YOUR_API_KEY",
    "ANTHROPIC_MODEL": "claude-sonnet-5",
    "CLAUDE_CODE_ATTRIBUTION_HEADER": "0",
    "CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS": "1",
    "CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY": "1"
  }
}

// Verify: run claude, then /status —
// the base URL should show api.boostrail.com.
// Non-Claude models: set ANTHROPIC_MODEL to any catalog id,
// e.g. deepseek-v4-pro — the /model picker only lists claude ids.

# ~/.codex/config.toml
model = "claude-sonnet-5"
model_provider = "boostrail"

[model_providers.boostrail]
name = "BoostRail"
base_url = "https://api.boostrail.com/v1"
env_key = "BOOSTRAIL_API_KEY"
wire_api = "responses"

# shell: export BOOSTRAIL_API_KEY=YOUR_API_KEY

# Cline → Settings → API Provider
API Provider:  OpenAI Compatible
Base URL:      https://api.boostrail.com/v1
API Key:       YOUR_API_KEY
Model ID:      claude-sonnet-5

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "boostrail": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "BoostRail",
      "options": {
        "baseURL": "https://api.boostrail.com/v1",
        "apiKey": "{env:BOOSTRAIL_API_KEY}"
      },
      "models": {
        "claude-sonnet-5": { "name": "Claude Sonnet 5" }
      }
    }
  }
}

# ~/.continue/config.yaml
models:
  - name: BoostRail Claude Sonnet 5
    provider: openai
    model: claude-sonnet-5
    apiBase: https://api.boostrail.com/v1
    apiKey: YOUR_API_KEY

export OPENAI_API_BASE=https://api.boostrail.com/v1
export OPENAI_API_KEY=YOUR_API_KEY

aider --model openai/claude-sonnet-5

The snippets default to claude-sonnet-5 — the flagship most coding agents reach for. Swap the model id for any model in the catalog — claude-opus-4.8, gpt-5.4, deepseek-v4-pro, and more — without touching anything else. Same base URL, same key.

YOUR_API_KEY is a placeholder — create a key in the console and paste it in. Signed-in personalized snippets that carry your real key are coming as a follow-up.

Running OpenClaw instead? Long-running agents have their own setup page, with the provider block for openclaw.json. OpenClaw setup

Confirm it is working

Run this once after pasting the config. It separates a configuration problem from a model problem, which is the difference between a two-minute fix and an hour of guessing.

curl https://api.boostrail.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-sonnet-5","messages":[{"role":"user","content":"reply with OK"}]}'

A working setup returns a JSON body with a choices array and the model's reply inside it. Your usage and the exact price applied to that request appear in the console within a few seconds.

Agent-verified models

Every model below has passed an end-to-end agent test through this gateway using the real Claude Code client — file-reading and shell tool calls, multi-turn tool history, and streaming. What gets verified is the full tool loop, not just a chat reply. Last verification run: 2026-08-03.

The list grows as new models and sources come online. Models outside it remain available through the same endpoints — they just have not been through the agent-loop test yet.

What you actually pay — and don't

The numbers that matter for a token-heavy coding workload:

Coding tools FAQ

Point your agent at the gateway

Create a key, paste it into the tool of your choice, and keep coding — on any model in the catalog.