API

sympy.ai exposes its verified math agent over an Anthropic-compatible Messages API. If you already use the Anthropic SDK, point its base_url at sympy.ai and use a sympy.ai API key — the request and response shapes match POST /v1/messages.

Authentication

Create an API key on your dashboard (shown once). Send it in the x-api-key header (or Authorization: Bearer mv_…). Usage is billed against your plan's token balance.

curl

curl https://api.sympy.ai/v1/messages \
  -H "x-api-key: $SYMPY_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "sympy-solve",
    "max_tokens": 1024,
    "messages": [
      { "role": "user", "content": "Integrate x^2 from 0 to 1" }
    ]
  }'

Anthropic SDK (Python)

from anthropic import Anthropic

client = Anthropic(
    api_key="mv_your_key",
    base_url="https://api.sympy.ai",
)

message = client.messages.create(
    model="sympy-solve",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Integrate x^2 from 0 to 1"}],
)
print(message.content[0].text)

Anthropic SDK (TypeScript)

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

const client = new Anthropic({
  apiKey: "mv_your_key",
  baseURL: "https://api.sympy.ai",
});

const message = await client.messages.create({
  model: "sympy-solve",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Integrate x^2 from 0 to 1" }],
});
console.log(message.content[0].text);

Response

A standard Anthropic message object. The answer is a single text block; usage reports input/output tokens.

{
  "id": "msg_…",
  "type": "message",
  "role": "assistant",
  "model": "sympy-solve",
  "content": [{ "type": "text", "text": "The integral equals 1/3." }],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": { "input_tokens": 812, "output_tokens": 143 }
}

Streaming

Set "stream": true to receive the Anthropic SSE sequence — message_start → content_block_start → content_block_delta → content_block_stop → message_delta → message_stop. The Anthropic SDK's streaming helpers consume it unchanged.

Models

Any model string is accepted; names signalling a stronger tier (containing pro, opus, reasoner, r1) route to the higher-effort verification pipeline, all others to the fast pipeline.

Errors & limits

Errors use the Anthropic envelope { "type": "error", "error": { "type", "message" } }: authentication_error (401), invalid_request_error (400), rate_limit_error (429, with retry-after), and billing_error (403) when your token balance is exhausted. Per-key rate limits follow your plan.