Create a message

curl https://api.pipellm.ai/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: $PIPELLM_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

import os
import anthropic

client = anthropic.Anthropic(
    api_key=os.environ["PIPELLM_API_KEY"],
    base_url="https://api.pipellm.ai",
)
message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)

{
  "id": "<string>",
  "type": "<string>",
  "role": "<string>",
  "content": [
    {}
  ],
  "stop_reason": "<string>",
  "usage": {}
}

POST

messages

curl https://api.pipellm.ai/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: $PIPELLM_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

import os
import anthropic

client = anthropic.Anthropic(
    api_key=os.environ["PIPELLM_API_KEY"],
    base_url="https://api.pipellm.ai",
)
message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)

{
  "id": "<string>",
  "type": "<string>",
  "role": "<string>",
  "content": [
    {}
  ],
  "stop_reason": "<string>",
  "usage": {}
}

Use x-api-key: $PIPELLM_API_KEY and anthropic-version: 2023-06-01. Native /v1/messages only routes to Anthropic-compatible platforms.

curl https://api.pipellm.ai/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: $PIPELLM_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

import os
import anthropic

client = anthropic.Anthropic(
    api_key=os.environ["PIPELLM_API_KEY"],
    base_url="https://api.pipellm.ai",
)
message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)

string

required

Anthropic model ID from GET /v1/models.

array

required

Conversation messages. Roles are user or assistant.

Show messages[]

string

required

user or assistant.

string | array

required

Plain text, or an array of content blocks.

Show content blocks

string

required

Usually text. Image blocks use image.

string

Required when type is text.

object

Required when type is image. Typically { "type": "base64", "media_type": "image/png", "data": "..." } or a URL source.

integer

required

Maximum output tokens.

string | array

System prompt.

number

Sampling temperature, 0–1.

number

Nucleus sampling.

integer

Top-k sampling.

boolean

If true, return server-sent events.

string[]

Custom stop sequences.

array

Tool definitions. See Tool Use.

Show tools[]

string

required

Tool name.

string

When Claude should call this tool.

object

required

JSON Schema for the tool input.

Endpoint

POST https://api.pipellm.ai/v1/messages

This free route accepts Anthropic Messages requests and routes only to Anthropic-compatible platforms. To keep the Anthropic format while calling OpenAI or Gemini models, use the Anthropic Format Converter.

Install SDKs

Python
Node.js
Go

pip install anthropic

npm install @anthropic-ai/sdk

go get github.com/anthropics/anthropic-sdk-go

Code Examples

cURL
Python
Node.js
Go

curl https://api.pipellm.ai/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: $PIPELLM_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d @- << 'EOF'
{
  "model": "claude-sonnet-4-5-20250929",
  "max_tokens": 1024,
  "messages": [
    {"role": "user", "content": "Why is the sky blue?"}
  ]
}
EOF

import os
import anthropic

client = anthropic.Anthropic(
  api_key=os.getenv('PIPELLM_API_KEY'),
  base_url='https://api.pipellm.ai'
)

message = client.messages.create(
  model='claude-sonnet-4-5-20250929',
  max_tokens=1024,
  messages=[
    {'role': 'user', 'content': 'Why is the sky blue?'}
  ]
)

print(message.content[0].text)

import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic({
  apiKey: process.env.PIPELLM_API_KEY,
  baseURL: 'https://api.pipellm.ai'
});

const message = await client.messages.create({
  model: 'claude-sonnet-4-5-20250929',
  max_tokens: 1024,
  messages: [
    { role: 'user', content: 'Why is the sky blue?' }
  ]
});

console.log(message.content[0].text);

package main

import (
  "context"
  "os"
  "github.com/anthropics/anthropic-sdk-go"
  "github.com/anthropics/anthropic-sdk-go/option"
)

func main() {
  client := anthropic.NewClient(
    option.WithAPIKey(os.Getenv("PIPELLM_API_KEY")),
    option.WithBaseURL("https://api.pipellm.ai"),
  )

  message, _ := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
    Model:     anthropic.F("claude-sonnet-4-5-20250929"),
    MaxTokens: anthropic.Int(1024),
    Messages: anthropic.F([]anthropic.MessageParam{
      anthropic.NewUserMessage(anthropic.NewTextBlock("Why is the sky blue?")),
    }),
  })
}

Response Format

{
  "id": "msg_xxx",
  "type": "message",
  "role": "assistant",
  "content": [
    {"type": "text", "text": "The sky appears blue because..."}
  ],
  "model": "claude-sonnet-4-5-20250929",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 10,
    "output_tokens": 50
  }
}

string

Message ID.

string

Always message.

string

Always assistant.

array

Output blocks. Text replies use { "type": "text", "text": "..." }. Tool calls use tool_use blocks.

string

end_turn, max_tokens, or tool_use.

object

input_tokens and output_tokens.

Errors

Same envelope as Errors. Native /v1/messages also returns 400 when the body is not Anthropic format.

400 invalid_request_error

Missing model, messages, or max_tokens, or a protocol mismatch.

{
  "error": {
    "type": "invalid_request_error",
    "code": "400",
    "message": "The 'model' field is required but was not provided in the request"
  }
}

401 authentication_error

Missing or invalid x-api-key.

{
  "error": {
    "type": "authentication_error",
    "code": "401",
    "message": "Incorrect API key provided. Please visit https://console.pipellm.ai/account/api-keys to find your API key."
  }
}

402 insufficient_balance

{
  "error": {
    "type": "insufficient_balance",
    "code": "402",
    "message": "Insufficient balance. Please recharge your account at https://console.pipellm.ai/billing."
  }
}

429 rate_limit_error

See Rate Limits.

{
  "error": {
    "type": "rate_limit_error",
    "code": "429",
    "message": "Rate limit exceeded. Your current limit is 120 requests per minute (approximately 2.00 requests per second). Please visit https://console.pipellm.ai/billing to upgrade your plan for higher limits."
  }
}

Routing & Protocols

Native-route constraints and converter routes

Anthropic Overview

Headers, models, and route family overview

Anthropic Format Converter

Keep Anthropic format while calling other providers

API Guides

API Reference

Create a message

Endpoint

Install SDKs

Code Examples

Response Format

Errors

Routing & Protocols

Anthropic Overview

Anthropic Format Converter

​Endpoint

​Install SDKs

​Code Examples

​Response Format

​Errors

​Related Docs

Routing & Protocols

Anthropic Overview

Anthropic Format Converter

Endpoint

Install SDKs

Code Examples

Response Format

Errors

Related Docs