docs
agents · plugin · x402

Give your agent every model.

One install. 229 models at list price, on one key. Every prompt buys back a token you pick.

229models, one MCP server
11AI clients, one command each
117image, video and audio models
1sign-in, then a daily cap
Every agent, one key, every modelClaude Code, Codex, Cursor, Gemini CLI, OpenCode and 6 more AI clients send their calls down one wire each into a single junction: one key, one MCP server. From it a fan reaches the 229 models of 39 makers, OpenAI, Google, Alibaba, xAI and more. An agent with its own wallet pays for image, video and audio calls per call in USDC with x402.Claude Code> chat GPT OSS 120BCodex> chat Gemini 2.5 FlashCursor> chat Qwen 3 MaxGemini CLI> chat Grok 4.20 Multi-AgenOpenCode> chat Claude Fable 5agent + wallet · x402> generate_imageOpenAIGoogleAlibabaxAIRecraftAnthropicBlack Forest LabsByteDanceMeta+ 30 more makers+ 6 more clients1 KEYmcp · /v1
  • 11 clients Claude Code, Codex, Cursor and more
  • 1 key one sign-in, a daily cap you pick
  • 229 models text, image, video and audio
  • x402 media paid per call in USDC, from a wallet with limits
select your agent

One command. Every model.

Pick your client, paste one line. Source: github.com/xavadao/xinf-plugin.

Paste this in your terminal.

terminal
claude plugin marketplace add xavadao/xinf-plugin && claude plugin install xinf@xinf --config base_url=https://zinf.ai && claude mcp login plugin:xinf:xinf

Then sign in: The command ends by opening your browser: sign in, pick a daily cap, Allow. Done. If Claude Code ever says the server needs authentication: /mcp, pick plugin:xinf:xinf, Authenticate.

More setup for Claude Code →

your agent, our models

Use Claude Code with your key.

Point the agent itself at us: every request runs on our models at list price, from your balance. Two lines, no plugin needed.

Claude Code

terminal (or your shell profile)
export ANTHROPIC_BASE_URL=https://zinf.ai
export ANTHROPIC_AUTH_TOKEN=$XINF_API_KEY
claude

Claude Code sends its usual model ids (claude-opus-..., claude-sonnet-..., claude-haiku-..., dated or -latest): each maps to the same model in our catalog, billed at list price. Pick one with ANTHROPIC_MODEL (and ANTHROPIC_DEFAULT_HAIKU_MODEL for background tasks), e.g. claude-haiku-4-5. ANTHROPIC_API_KEY works too.

Codex

~/.codex/config.toml
[model_providers.xinf]
name = "Xava Inference"
base_url = "https://zinf.ai/v1"
env_key = "XINF_API_KEY"
wire_api = "responses"

[profiles.xinf]
model_provider = "xinf"
model = "openai/gpt-5.4-mini"

# then: codex --profile xinf

OpenAI models only on this API; bare ids such as gpt-5.4-mini work too.

Gemini CLI

terminal (or your shell profile)
export GOOGLE_GEMINI_BASE_URL=https://zinf.ai
export GEMINI_API_KEY=$XINF_API_KEY
gemini -m gemini-2.5-flash

Choose "Use Gemini API key" when Gemini CLI asks how to sign in. Gemini model ids map to our catalog; any other chat model works by its full id. Token counts are estimates; cached content and the file API are not supported.

No key yet? Create one, or run the device login from your agent's setup above: it saves one to ~/.xinf/credentials. Details: agent docs.

x402

Pay per call, from a wallet with limits.

For agents that already have a wallet provider with spending policies, such as a hosted agent wallet.

  1. 01Your agent asks

    For an image, a clip or a voice.

  2. 02It gets a price

    One exact price, in USDC.

  3. 03It pays and gets it

    Through its wallet provider, within its limits.

Using Claude Code, Codex, Cursor or another coding agent? Sign in instead (the step under your agent above): it covers images, video and audio too, paid from your balance within the daily cap you pick. We never ask you to create a wallet or keep a private key on your computer.

Building an agent that already pays through a wallet service with spending limits? Point its x402 client at our media endpoints: it gets one exact price in USDC per request, its wallet provider signs within its limits, and the result comes back with a receipt.

Works for 117 media models. soon Endpoints and headers: x402 docs.

agentic apps

Build agentic apps with one key.

Your own code, any OpenAI-compatible SDK.

python
from openai import OpenAI

client = OpenAI(
    base_url="https://zinf.ai/v1",
    api_key="xk_live_...",  # your Xava Inference key
)

r = client.chat.completions.create(
    model="openai/gpt-5.4",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(r.choices[0].message.content)
faq

Short answers.

What does the plugin do?
It lets your AI agent use every model we offer: it can write, make images, video and audio, check prices and see your balance, all from inside the agent you already use. Details are in the agent docs.
Do I need an account?
Yes, and it takes one click: sign in once from your agent. It opens your browser, you sign in (a free account is created the first time), pick a daily spending cap and click Allow. No key to copy, and nothing secret is stored on your computer by us.
What is x402?
A way for software to pay for things on the web by itself: the agent asks for an image, sees the exact price, and pays it in USDC through its wallet provider. It is for agents that already have a wallet service with spending limits, like a hosted agent wallet. For Claude Code, Codex, Cursor and the other coding agents, sign in instead.
Can my agent overspend?
No. A signed-in agent can spend at most the daily cap you picked when you allowed it. With x402, the agent's wallet provider enforces its own spending limits, and the agent asks you before going over your cap.
Do I need to create a wallet or keep a private key on my computer?
No, never. Our plugin does not create, read or store private keys. Sign in instead: your agent spends your account balance within your daily cap.
Which agents are supported?
Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI, OpenCode, Kimi, Pi, Cline, Windsurf, Any OpenAI SDK. Any other MCP client works too; see the MCP docs.
Where does my key live?
With browser sign-in there is no key to handle: your agent keeps its own token, and you can see and revoke every connected app in your dashboard under API keys. If you use a key or the device login instead, it lives in the XINF_API_KEY environment variable or ~/.xinf/credentials on your computer, never in a file you share.
Can a connected app spend my whole balance?
Only up to the daily cap you picked when you allowed it (default $5 a day). Change the cap or disconnect the app any time in your dashboard under API keys, Connected apps.
Do you keep my prompts?
No. We never store your prompts or replies; we keep billing details only: model, amount and time. Zero data retention end to end on models marked ZDR supported; uploaded references and generated files auto-delete after 24 hours. On a model marked ZDR supported, neither we nor the model provider store your prompts or outputs; on other models the model provider's own retention policy applies.
docs

The rest is in the docs.