API Reference

API Documentation

Build with Klawd's unified LLM proxy. One API, every model. OpenAI-compatible from day one.

Get started free

OpenAI CompatibleSSE StreamingMulti-ProviderImage Generation

Quickstart

Get from zero to your first API call in under 5 minutes.

Create your account

Install an SDK (optional)

Use any OpenAI-compatible client. The official openai package works out of the box.

Make your first call

Hit the chat completions endpoint with your key and model of choice.

First API call

bash

curl https://api.klawd.studio/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Authentication

All requests require a valid API key sent via the Authorization header.

Header format

bash

Authorization: Bearer YOUR_API_KEY

Rate Limits by Plan

Plan	Requests/Day	Requests/Min
Free	100	10
Pro ($29/mo)	10,000	100
Enterprise	Custom	Custom

Common Auth Errors

401

Invalid or missing API key. Check your Authorization header.

429

Rate limit exceeded. Back off and retry with exponential delay.

500

Internal server error. Retry after a short delay.

Endpoints Reference

Klawd exposes OpenAI-compatible endpoints plus image generation. Base URL for chat & models: https://api.klawd.studio/v1 — Image endpoints use https://api.klawd.studio/api

Create a chat completion using OpenAI-compatible request/response format. Supports streaming via SSE.

Request Example

POST body

json

{
  "model": "klawd/auto",
  "messages": [
    { "role": "system", "content": "You are a concise coding assistant." },
    { "role": "user", "content": "Write a TypeScript debounce function." }
  ],
  "temperature": 0.7,
  "max_tokens": 600,
  "stream": false
}

Body Parameters

Parameter	Type	Required	Description
`model`	`string`	required	Model ID to use (e.g. "anthropic/claude-opus-4")
`messages`	`array`	required	Array of message objects with role and content
`temperature`	`number`	optional(1)	Sampling temperature (0-2)
`max_tokens`	`integer`	optional(4096)	Maximum tokens in the response
`stream`	`boolean`	optional(false)	Enable SSE streaming
`top_p`	`number`	optional(1)	Nucleus sampling threshold
`stop`	`string \| array`	optional	Stop sequences

Response

200 OK

json

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1707500000,
  "model": "anthropic/claude-opus-4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 9,
    "total_tokens": 21
  }
}

Streaming (SSE)

Set stream: true to receive Server-Sent Events. Each event is a data: line with a JSON chunk. The stream ends with data: [DONE].

Streaming example

javascript

const response = await fetch("https://api.klawd.studio/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "anthropic/claude-opus-4",
    messages: [{ role: "user", content: "Tell me a story" }],
    stream: true,
  }),
});

const reader = response.body?.getReader();
const decoder = new TextDecoder();

while (reader) {
  const { done, value } = await reader.read();
  if (done) break;

  const chunk = decoder.decode(value);
  const lines = chunk.split("\n").filter(line => line.startsWith("data: "));

  for (const line of lines) {
    const data = line.replace("data: ", "");
    if (data === "[DONE]") break;
    const parsed = JSON.parse(data);
    const content = parsed.choices?.[0]?.delta?.content;
    if (content) process.stdout.write(content);
  }
}

List all available models with metadata and pricing hints.

Generate one or more images from a prompt. Requires Pro or Enterprise plan.

Available Models

Route to any model through a single API. Pricing is per million tokens unless noted otherwise.

Model	Provider	Context	Cost (input/output)
`klawd/auto` Smart routing	Klawd	Varies	Varies
`klawd/standard`	Klawd	Varies	Varies
`anthropic/claude-opus-4` Most capable	Anthropic	200K	$15 / $75
`anthropic/claude-sonnet-4` Best value	Anthropic	200K	$3 / $15
`openai/gpt-4-turbo`	OpenAI	128K	$10 / $30
`google/gemini-2.0-flash` Largest context	Google	1M	$0.075 / $0.30
`replicate/seedream-4.5` Image gen	Replicate	N/A	$0.02/image

Costs listed are per million tokens (per image for image generation). Actual billing reflects usage via your plan.

Code Examples

Copy-paste these examples to get started. Replace YOUR_API_KEY with your actual key from Mission Control.

cURL

bash

curl https://api.klawd.studio/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Rate Limits & Pricing

Free

$0/mo

100 req/day

10 req/min

Pro

$29/mo

10,000 req/day

100 req/min

Enterprise

Custom

Custom limits

Need more details? View full pricing page

Error Handling

All errors return a JSON body with an error object containing type and message fields.

Code	Type	Description	Retryable
400	`invalid_request`	Malformed request body or missing required parameters	No
401	`authentication_error`	Invalid, expired, or missing API key	No
429	`rate_limit_exceeded`	Too many requests. Check Retry-After header	Yes
500	`internal_error`	Unexpected server error	Yes
503	`service_unavailable`	Upstream provider temporarily unavailable	Yes

Retry with Exponential Backoff

For retryable errors (429, 500, 503), implement exponential backoff with jitter. Here is a reference implementation:

Retry logic

typescript

async function callWithRetry(body: object, maxRetries = 3) {
  for (let attempt = 0; attempt < maxRetries; attempt++) {
    const res = await fetch("https://api.klawd.studio/v1/chat/completions", {
      method: "POST",
      headers: {
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
      },
      body: JSON.stringify(body),
    });

    if (res.ok) return res.json();

    if (res.status === 429 || res.status >= 500) {
      const delay = Math.pow(2, attempt) * 1000 + Math.random() * 500;
      console.log(`Retry ${attempt + 1}/${maxRetries} in ${delay}ms`);
      await new Promise(r => setTimeout(r, delay));
      continue;
    }

    // Client error — do not retry
    const error = await res.json();
    throw new Error(`API error ${res.status}: ${error.error?.message}`);
  }
  throw new Error("Max retries exceeded");
}

Webhooks

Coming Soon

Webhooks let you receive real-time notifications about events in your account. Configure your endpoint URL in Mission Control.

Event Types

Event	Description
`usage.updated`	Fired when your usage metrics are updated (hourly)
`billing.invoice.paid`	Fired when a subscription payment is successfully processed

Signature Verification

Every webhook includes an X-Klawd-Signature header. Verify it using HMAC-SHA256 with your webhook secret:

Verify webhook signature

typescript

import crypto from "crypto";

function verifySignature(payload: string, signature: string, secret: string): boolean {
  const expected = crypto
    .createHmac("sha256", secret)
    .update(payload)
    .digest("hex");
  return crypto.timingSafeEqual(
    Buffer.from(signature),
    Buffer.from(expected)
  );
}

Support

We are here to help you build. Reach out via any channel below.

support@klawd.ai

Get in touch

Status Page

status.klawd.studio

Pricing & Plans

View plans and upgrade

Ready to start building?

Get started free

API Reference

API Documentation

Build with Klawd's unified LLM proxy. One API, every model. OpenAI-compatible from day one.

Get started free

OpenAI CompatibleSSE StreamingMulti-ProviderImage Generation

Quickstart

Get from zero to your first API call in under 5 minutes.

Create your account

Install an SDK (optional)

Use any OpenAI-compatible client. The official openai package works out of the box.

Make your first call

Hit the chat completions endpoint with your key and model of choice.

First API call

bash

curl https://api.klawd.studio/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Authentication

All requests require a valid API key sent via the Authorization header.

Header format

bash

Authorization: Bearer YOUR_API_KEY

Rate Limits by Plan

Plan	Requests/Day	Requests/Min
Free	100	10
Pro ($29/mo)	10,000	100
Enterprise	Custom	Custom

Common Auth Errors

401

Invalid or missing API key. Check your Authorization header.

429

Rate limit exceeded. Back off and retry with exponential delay.

500

Internal server error. Retry after a short delay.

Endpoints Reference

Klawd exposes OpenAI-compatible endpoints plus image generation. Base URL for chat & models: https://api.klawd.studio/v1 — Image endpoints use https://api.klawd.studio/api

Create a chat completion using OpenAI-compatible request/response format. Supports streaming via SSE.

Request Example

POST body

json

{
  "model": "klawd/auto",
  "messages": [
    { "role": "system", "content": "You are a concise coding assistant." },
    { "role": "user", "content": "Write a TypeScript debounce function." }
  ],
  "temperature": 0.7,
  "max_tokens": 600,
  "stream": false
}

Body Parameters

Parameter	Type	Required	Description
`model`	`string`	required	Model ID to use (e.g. "anthropic/claude-opus-4")
`messages`	`array`	required	Array of message objects with role and content
`temperature`	`number`	optional(1)	Sampling temperature (0-2)
`max_tokens`	`integer`	optional(4096)	Maximum tokens in the response
`stream`	`boolean`	optional(false)	Enable SSE streaming
`top_p`	`number`	optional(1)	Nucleus sampling threshold
`stop`	`string \| array`	optional	Stop sequences

Response

200 OK

json

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1707500000,
  "model": "anthropic/claude-opus-4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 9,
    "total_tokens": 21
  }
}

Streaming (SSE)

Set stream: true to receive Server-Sent Events. Each event is a data: line with a JSON chunk. The stream ends with data: [DONE].

Streaming example

javascript

const response = await fetch("https://api.klawd.studio/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "anthropic/claude-opus-4",
    messages: [{ role: "user", content: "Tell me a story" }],
    stream: true,
  }),
});

const reader = response.body?.getReader();
const decoder = new TextDecoder();

while (reader) {
  const { done, value } = await reader.read();
  if (done) break;

  const chunk = decoder.decode(value);
  const lines = chunk.split("\n").filter(line => line.startsWith("data: "));

  for (const line of lines) {
    const data = line.replace("data: ", "");
    if (data === "[DONE]") break;
    const parsed = JSON.parse(data);
    const content = parsed.choices?.[0]?.delta?.content;
    if (content) process.stdout.write(content);
  }
}

List all available models with metadata and pricing hints.

Generate one or more images from a prompt. Requires Pro or Enterprise plan.

Available Models

Route to any model through a single API. Pricing is per million tokens unless noted otherwise.

Model	Provider	Context	Cost (input/output)
`klawd/auto` Smart routing	Klawd	Varies	Varies
`klawd/standard`	Klawd	Varies	Varies
`anthropic/claude-opus-4` Most capable	Anthropic	200K	$15 / $75
`anthropic/claude-sonnet-4` Best value	Anthropic	200K	$3 / $15
`openai/gpt-4-turbo`	OpenAI	128K	$10 / $30
`google/gemini-2.0-flash` Largest context	Google	1M	$0.075 / $0.30
`replicate/seedream-4.5` Image gen	Replicate	N/A	$0.02/image

Costs listed are per million tokens (per image for image generation). Actual billing reflects usage via your plan.

Code Examples

Copy-paste these examples to get started. Replace YOUR_API_KEY with your actual key from Mission Control.

cURL

bash

curl https://api.klawd.studio/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Rate Limits & Pricing

Free

$0/mo

100 req/day

10 req/min

Pro

$29/mo

10,000 req/day

100 req/min

Enterprise

Custom

Custom limits

Need more details? View full pricing page

Error Handling

All errors return a JSON body with an error object containing type and message fields.

Code	Type	Description	Retryable
400	`invalid_request`	Malformed request body or missing required parameters	No
401	`authentication_error`	Invalid, expired, or missing API key	No
429	`rate_limit_exceeded`	Too many requests. Check Retry-After header	Yes
500	`internal_error`	Unexpected server error	Yes
503	`service_unavailable`	Upstream provider temporarily unavailable	Yes

Retry with Exponential Backoff

For retryable errors (429, 500, 503), implement exponential backoff with jitter. Here is a reference implementation:

Retry logic

typescript

async function callWithRetry(body: object, maxRetries = 3) {
  for (let attempt = 0; attempt < maxRetries; attempt++) {
    const res = await fetch("https://api.klawd.studio/v1/chat/completions", {
      method: "POST",
      headers: {
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
      },
      body: JSON.stringify(body),
    });

    if (res.ok) return res.json();

    if (res.status === 429 || res.status >= 500) {
      const delay = Math.pow(2, attempt) * 1000 + Math.random() * 500;
      console.log(`Retry ${attempt + 1}/${maxRetries} in ${delay}ms`);
      await new Promise(r => setTimeout(r, delay));
      continue;
    }

    // Client error — do not retry
    const error = await res.json();
    throw new Error(`API error ${res.status}: ${error.error?.message}`);
  }
  throw new Error("Max retries exceeded");
}

Webhooks

Coming Soon

Webhooks let you receive real-time notifications about events in your account. Configure your endpoint URL in Mission Control.

Event Types

Event	Description
`usage.updated`	Fired when your usage metrics are updated (hourly)
`billing.invoice.paid`	Fired when a subscription payment is successfully processed

Signature Verification

Every webhook includes an X-Klawd-Signature header. Verify it using HMAC-SHA256 with your webhook secret:

Verify webhook signature

typescript

import crypto from "crypto";

function verifySignature(payload: string, signature: string, secret: string): boolean {
  const expected = crypto
    .createHmac("sha256", secret)
    .update(payload)
    .digest("hex");
  return crypto.timingSafeEqual(
    Buffer.from(signature),
    Buffer.from(expected)
  );
}

Support

We are here to help you build. Reach out via any channel below.

support@klawd.ai

Get in touch

Status Page

status.klawd.studio

Pricing & Plans

View plans and upgrade

Ready to start building?

Get started free

API Documentation

Quickstart

Authentication

Rate Limits by Plan

Common Auth Errors

Endpoints Reference

Request Example

Body Parameters

Response

Streaming (SSE)

Available Models

Code Examples

Rate Limits & Pricing

Error Handling

Retry with Exponential Backoff

Webhooks

Event Types

Signature Verification

Support

Ready to start building?

Preparing your workspace...

API Documentation

Quickstart

Authentication

Rate Limits by Plan

Common Auth Errors

Endpoints Reference

Request Example

Body Parameters

Response

Streaming (SSE)

Available Models

Code Examples

Rate Limits & Pricing

Error Handling

Retry with Exponential Backoff

Webhooks

Event Types

Signature Verification

Support

Ready to start building?