---
title: Use jusInfer with Claude Code
description: Point Claude Code at jusInfer for cheaper, model-agnostic inference without changing your workflow.
tldr: Set ANTHROPIC_BASE_URL=https://api.jusinfer.com and ANTHROPIC_AUTH_TOKEN=jinf_... in your shell. jusInfer speaks the Anthropic Messages API natively at /v1/messages — Claude Code's default — and routes every call to the cheapest capable model under the hood.
slug: claude-code
order: 1
updated: 2026-05-29
---

# Use jusInfer with Claude Code

[Claude Code](https://claude.com/claude-code) is Anthropic's terminal-native coding agent. It speaks the Anthropic Messages API (`POST /v1/messages`) by default. jusInfer exposes that exact surface — so Claude Code points at `api.jusinfer.com` with one env-var change and everything else (tool use, streaming, thinking, system prompts) keeps working unchanged. Under the hood, jusInfer routes each call to the cheapest capable model.

## Why route through jusInfer?

- **Cost.** We pick the most cost-effective model that meets the bar for each call — frontier when you need it, smaller when you don't. Same API, lower bill.
- **No vendor lock-in.** Your code only ever talks to `api.jusinfer.com`. We swap models behind the scenes as the market moves.
- **One bill.** Credits roll over, never expire. Per-user soft caps. No surprise overages.
- **Same DX.** Your existing Claude Code workflow doesn't change — just the endpoint.

## 30-second setup

### 1. Get a jusInfer API key

```sh
# Sign in at https://jusinfer.com/login (Google or Microsoft)
# Then visit https://jusinfer.com/developer → Keys tab → "Mint key"
# Copy the jinf_… token. You'll only see it once.
```

### 2. Point Claude Code at jusInfer

Claude Code uses two environment variables for OpenAI-compatible mode:

```sh
export ANTHROPIC_BASE_URL="https://api.jusinfer.com"
export ANTHROPIC_AUTH_TOKEN="jinf_your_key_here"
```

Add those to your shell profile (`~/.zshrc`, `~/.bashrc`) and reload:

```sh
source ~/.zshrc
```

### 3. Verify

```sh
claude --version
claude  # should start a normal session
```

Inside Claude Code, ask it anything — say, "summarize this directory". The call is routed through jusInfer. Verify the spend on your [dashboard](https://jusinfer.com/developer).

## Per-project override

If you only want jusInfer for one repo:

```sh
# Create .envrc in your repo (with direnv) or a shell alias:
alias claude-jusinfer='ANTHROPIC_BASE_URL=https://api.jusinfer.com \
  ANTHROPIC_AUTH_TOKEN=jinf_... claude'
```

## What jusInfer picks

jusInfer routes every request through three filters:

1. **Capability** — does the task need hard reasoning, long context, or tool use?
2. **Cost** — per-token rate, cache hit rate, retry cost
3. **Fit** — task type, codebase size, your spend profile

The chosen model is opaque by default. You can inspect any call's actual upstream model from the [Usage tab](https://jusinfer.com/developer) if you want to.

## Limits and gotchas

- **Streaming works.** Server-sent events are forwarded transparently.
- **Tool use works.** Both Anthropic-style and OpenAI-style tool calls are normalized.
- **System prompts work.** No magic — they pass through untouched.
- **Image inputs** route to a vision-capable model automatically.
- **Rate limits**: 60 RPM per key, 600 RPM per tenant. Bump in the dashboard if you need more.

## Troubleshooting

| Symptom | Likely cause | Fix |
|---|---|---|
| `401 INVALID_KEY` | Key was revoked or never minted | Mint a fresh key in the dashboard |
| `403 SEAT_REQUIRED` | Tenant has >1 member with no seat sub | Subscribe in Billing tab |
| `429 RATE_LIMIT` | Burst hit the per-key 60 RPM | Wait 60s or raise the limit |
| `502` | Upstream model temporarily unavailable | Retry; jusInfer automatically falls back |

## Related

- [Use jusInfer with OpenCode](/docs/opencode/)
- [OpenAI-compatible drop-in for any harness](/docs/openai-drop-in/)
- [API reference](/docs/api-reference/)

---

*This page is also available as raw markdown for AI agents to consume directly:* [/docs/claude-code.md](/docs/claude-code.md)