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 speaks the OpenAI protocol, so switching to BoostRail takes about 30 seconds: change the base URL to https://api.boostrail.com/v1 and drop in one key.

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

All of these are OpenAI-protocol tools. Set the base URL to https://api.boostrail.com/v1 and the key to your BoostRail API key — the model id is any model from the catalog. Codex CLI and Claude Code are not listed yet: current Codex only speaks OpenAI's Responses protocol and Claude Code needs Anthropic's native protocol — both are on our roadmap, and each gets its section here the moment it is live rather than us claiming support we don't have.

ClineOpenCodeContinueAider

In the Cline settings panel (VS Code), pick the OpenAI-Compatible provider and fill these fields.

# 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

Declare BoostRail as a provider in opencode.json (project root or ~/.config/opencode/).

{
  "$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" }
      }
    }
  }
}

Add a model entry to ~/.continue/config.yaml with provider: openai and an apiBase override.

# ~/.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

Aider reads the standard OpenAI-compatible env vars; point them at the gateway.

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.

What you actually pay — and don't

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

Agent load at a 5% discount

Every model's agent-load traffic is billed at 95% of the published per-token price, across the whole range — not a teaser tier. The live per-request price in the console prevails.

Cache reads at 10% of input, cache writes free

Cached input tokens — the bulk of an agent's repeated context — bill at 10% of the input price. Cache writes carry no separate charge; they are billed as normal input. No $6.25/M cache-write surcharge.

No usage window, no rate wall

No ~5-hour subscription window and no per-minute API-tier throttle standing between your agent and the model. Run long sessions and heavy loops without hitting an artificial ceiling.

Coding tools FAQ

Do I need a different key per tool?

No. One BoostRail API key works across every tool here — Cline, OpenCode, Continue, Aider — because they all speak the OpenAI protocol against the same base URL.

Can I use Claude models in these tools?

Yes — the snippets above already default to claude-sonnet-5, and any catalog model works by changing the model id. What is not yet supported is the Claude Code CLI specifically, which requires Anthropic's native protocol; that is on the roadmap.

Why isn't Codex CLI listed?

Recent Codex versions dropped the Chat Completions option and only speak OpenAI's Responses protocol, which the gateway does not expose yet. A Responses endpoint is on the roadmap — Codex CLI gets its section here the day it ships.

Will switching break my existing setup?

No. You change only the base URL and the key; the tool, your prompts, and your workflow stay the same. You can point the base URL back to a provider at any time — zero lock-in.

How is agent load priced?

At 95% of the published per-token price for every model, with cached input at 10% of input and no cache-write surcharge. The Models page publishes live per-token prices.

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.