Skip to main content
Claude Code reads an Anthropic-shaped API. Kyma serves one at /v1/messages, so Claude Code works against Kyma with two environment variables and no plugin, proxy or wrapper.

​
Setup

ANTHROPIC_BASE_URL takes the host without /v1. Claude Code appends the path itself, so https://api.kymaapi.com/v1 becomes /v1/v1/messages and every request 404s. This is the one thing people get wrong.
ANTHROPIC_AUTH_TOKEN sends your key as a bearer token. If you would rather use the header Anthropic’s own SDK sends, ANTHROPIC_API_KEY works identically and goes out as x-api-key. Either is fine; use one, not both.

​
Making it permanent

Environment variables last as long as your shell. To keep the setting, put it in ~/.claude/settings.json:
The same block works per-project in .claude/settings.json, which is how you point one repository at Kyma and leave everything else alone. In the VS Code extension the equivalent setting is claudeCode.environmentVariables. In GitHub Actions, put both in the step’s env:. In the Agent SDK, pass them as options.env.

​
Choosing a model

Kyma serves these under Claude Code’s own naming, so /model and the ANTHROPIC_MODEL variable behave the way you expect:
Every claude-* model is outside the free tier. On a new account, which holds only the signup credit (added once your email is verified, spendable on the free tier), they return 402 model_requires_paid until your first top-up. To try Claude Code before topping up, set ANTHROPIC_MODEL="qwen-3-coder", a free-tier model with tool calling.
You are not limited to those. Anything in the catalogue that supports tool calling will drive Claude Code — kimi-k2.6, qwen-3-coder and glm-5.2 all return proper tool_use blocks through /v1/messages. Set ANTHROPIC_MODEL to any model id from the model list.
Anthropic does not support or audit third-party gateways, and says so plainly in their documentation. Running Claude Code against any gateway — Kyma included — or on a non-Claude model is outside what their support covers. It works; it is simply not their problem if it does not.

​
Checking it worked

A 200 with a content array means Claude Code will work. A 404 almost always means /v1 was left on the end of ANTHROPIC_BASE_URL. A 402 means the model is outside the free tier and the account has not been topped up yet.

​
Model discovery

Claude Code can populate its /model picker from the gateway:
Kyma’s /v1/models answers this in well under Claude Code’s timeout and issues no redirect, both of which it requires. Leave the variable unset and the picker falls back to its built-in list, which still works — you just type the model id instead of choosing it.

​
What is not there

/v1/messages/count_tokens is not implemented. It is optional in Anthropic’s API and Claude Code falls back to estimating locally, so the only effect is that the context figure in the status line is approximate rather than exact.

​
Cost

Claude Code is a heavy client — long contexts, many turns, large tool outputs. Two things matter more here than anywhere else: Prompt caching applies on models that publish a cached rate. Claude Code re-sends the system prompt and file context every turn and marks it with cache_control, which Kyma forwards. On a model with pricing.cached in /v1/models, cached input bills at that rate. /v1/messages responses do not carry a cost field; see what each request cost on the usage page or from GET /v1/auth/usage/logs. Prompt Caching covers the details. Watch the model you picked. An Opus-class model on a long agentic session costs an order of magnitude more than Haiku on the same work. /model mid-session is cheap; discovering the bill afterwards is not.