xKiroxKiro
    HomePricingDocsStatusContact
    Sign in
    Start free
    • Home
    • Pricing
    • Docs
    • Status
    • Contact

    Start free

    20+ free models · No credit card

    Start free

    Already have an account?Sign in

    xKiroxKiro

    AI tokens for agents, at a better price.

    Product

    • Models
    • Pricing
    • Docs

    Developers

    • API Reference
    • Quickstart
    • Usage Limits

    Company

    • About
    • Contact
    • Terms
    • Privacy

    © 2026 xKiro. All rights reserved.

    Contents

    Quick start

    xKiro is OpenAI & Anthropic compatible — use the official SDK, just change base_url.

    Step 1 — Get your API key

    No API key found for your account.Create API key

    Step 2 — Install SDK

    Step 3 — Make your first call

    Run in Playground

    Step 4 — Expected response

    Authentication

    The OpenAI SDK sends your key as Authorization: Bearer. Point base_url at xKiro and your existing OpenAI code just works.

    Never expose your API key in client-side code or public repositories. Use environment variables or a server-side proxy.

    Manage your API keys

    Models

    xKiro supports 120+ models from leading providers. Pass the model ID in your request. The model ID is case-sensitive.

    ModelProviderContextInput / 1MOutput / 1MID
    Claude Sonnet 4.5Anthropic200K$3.00$15.00
    GPT-4oOpenAI128K$2.50$10.00
    Gemini 2.0 FlashGoogle1M$0.10$0.40
    Llama 3.3 70BMeta128K$0.59$0.79
    DeepSeek R1DeepSeek64K$0.55$2.19
    View all 120+ models

    Chat completions

    ParameterTypeDefaultDescription
    modelrequiredstring—Model ID to use (case-sensitive).
    messagesrequiredarray—Array of message objects with role and content.
    temperaturenumber1Randomness — 0 is deterministic, 2 is very random.
    max_tokensintegernullMaximum tokens in the response. Null = model default.
    top_pnumber1Nucleus sampling: consider tokens with top_p probability.
    streambooleanfalseStream tokens via SSE as they are generated.
    stopstring|arraynullUp to 4 stop sequences. Generation halts when hit.

    Streaming

    Set stream: true to receive tokens as they are generated instead of waiting for the full response.

    Error handling

    StatusCodeMeaningHow to handle
    400invalid_requestMalformed JSON or missing required fieldFix request payload before retrying
    401unauthorizedMissing or invalid API keyCheck Authorization header format
    403forbiddenRequest IP is not in the key's allowlistAdd your IP to the key's allowlist, or remove the restriction
    404model_not_foundModel ID does not exist or is unavailableVerify model ID from /dashboard/models
    429rate_limit_exceededToo many requests or tokensBack off exponentially; check Retry-After
    500internal_errorUnexpected server-side errorRetry once with backoff; report if persistent
    503service_unavailableProvider temporarily unavailableRetry with exponential backoff

    Rate limits

    Rate limits apply per API key. When you exceed one, the request is rejected with HTTP 429 — nothing is charged.

    A 429 response includes these headers:

    Retry-Afterseconds to wait before retrying
    X-RateLimit-Scopewhich limit was hit
    X-RateLimit-Windowthe limit's time window
    Upgrade your plan for higher limits

    On this page