Skip to main content
Kode supports 25+ AI providers and ships with its own gateway at api.trykode.xyz for unified, zero-friction access to the best models across OpenAI, Anthropic, DeepSeek, Google, and OpenRouter. You configure your provider once — in kode.json or via environment variables — and Kode handles routing, streaming, and key management automatically.

​
The Kode Gateway

The Kode Gateway is the default provider. It is a routing layer that sits in front of multiple upstream providers and exposes a single OpenAI-compatible endpoint. You authenticate with one key (KODE_LLM_API_KEY) and the gateway handles dispatch to the right upstream model. The gateway is pre-configured in every kode init output:
.kode/kode.json
To authenticate, set your API key:
The gateway routes to OpenAI, Anthropic, DeepSeek, Google, and OpenRouter based on the model you select in kode.json. You do not need individual provider keys when using the gateway.

​
Gateway tiers

The Lite tier is rate-limited at the gateway level. When you exceed 20 requests per day, the gateway returns a rate limit error explaining that your daily Lite quota has been reached. Set KODE_PRO_API_KEY or upgrade at trykode.xyz/pricing to remove the limit.

​
Using a direct provider

If you prefer to call a provider’s API directly — bypassing the Kode Gateway — set model in kode.json to the provider/model string for your chosen model and export the corresponding API key environment variable.
1

Set the model in kode.json

Edit .kode/kode.json and set the model field to the provider/model string. For example, to use Claude Sonnet 4.6 directly via Anthropic:
.kode/kode.json
2

Export the provider API key

Set the environment variable corresponding to your chosen provider:
3

Run Kode

Kode picks up the key and routes directly to the provider:

​
Supported model strings

Use these strings in the model and small_model fields of your kode.json:
Run kode models to see every model string available for your configured providers, including metadata such as input and output cost per million tokens.

​
Provider management CLI

The TypeScript CLI layer exposes providers and models subcommands for managing credentials and browsing available models. These commands are forwarded automatically from the kode binary:

​
Credentials

​
Models

Credentials stored via kode providers login are saved to ~/.kode/auth.json. Environment variables (e.g. ANTHROPIC_API_KEY) are detected automatically by kode providers list and shown alongside stored credentials. Environment variables always take precedence over stored credentials at runtime.

​
Pointing Kode at a local model

You can run Kode against any OpenAI-compatible local inference server — Ollama, LM Studio, llama.cpp, vLLM, and others all work. Override the endpoint and model via environment variables:
Local models vary widely in instruction-following quality. Kode’s verification pipeline (blast-radius checks, TDD gating, SAST scanning) still runs against the output, so bad patches are caught before reaching disk — but expect more retries and self-correction cycles with smaller models.

kode.json reference

Full reference for all model, engine, and permission settings.

Environment Variables

Complete list of environment variables including all provider key names.