Anthropic SDK

The official Anthropic SDK (Python or TypeScript) speaks the Anthropic Messages protocol, which MirAPI implements on the bare API origin. To switch from Anthropic to MirAPI, change only the base URL and API key; request and response shapes stay the same.

What you need

Element	Value
Base URL	`https://api.mirapi.ai` (bare origin, no `/v1`)
API key	`MIRAPI_API_KEY`
Model	`deepseek-chat`

The SDK authenticates with the x-api-key header by default. MirAPI accepts both x-api-key and Authorization: Bearer on /v1/messages.

Install

pip install anthropic

npm install @anthropic-ai/sdk

Configure

Python

import os
from anthropic import Anthropic

client = Anthropic(
    base_url="https://api.mirapi.ai",
    api_key=os.environ["MIRAPI_API_KEY"],
)

TypeScript

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

const client = new Anthropic({
  baseURL: "https://api.mirapi.ai",
  apiKey: process.env.MIRAPI_API_KEY,
});

The SDK sends the anthropic-version header by default; MirAPI accepts it like any other header.

Verify with a message

message = client.messages.create(
    model="deepseek-chat",
    max_tokens=200,
    messages=[{"role": "user", "content": "Reply with exactly: connected to MirAPI"}],
)
print(message.content[0].text)

The output should contain connected to MirAPI. The Anthropic protocol requires max_tokens, so set it on every call.

Streaming

with client.messages.stream(
    model="deepseek-chat",
    max_tokens=200,
    messages=[{"role": "user", "content": "Count from 1 to 5."}],
) as stream:
    for text in stream.text_stream:
        print(text, end="")

Streaming uses standard SSE. Reasoning content, when the model produces it, arrives before the final answer.

Prompt caching

Add cache_control to a system or messages block to mark a cache breakpoint:

message = client.messages.create(
    model="deepseek-chat",
    max_tokens=200,
    system=[
        {
            "type": "text",
            "text": "You are a helpful assistant.",
            "cache_control": {"type": "ephemeral"},
        }
    ],
    messages=[{"role": "user", "content": "Hello"}],
)

You can mark up to 4 breakpoints. "ttl": "1h" extends the cache to 1 hour and raises the write price.
The model’s vendor sets the minimum cacheable length and the TTL (Claude 1,024–4,096 tokens; OpenAI 1,024; default about 5 minutes).
To confirm a hit, check the usage.prompt_tokens_details.cached_tokens and cache_write_tokens fields. Cache reads are cheaper than normal input.

Errors and troubleshooting

Status	Meaning	What to do
401	Missing, invalid, or unknown key	Fix your credentials
403	Valid key, but rejected	Resolve the cause and retry (balance, whitelist, quota, IP allowlist)
413	Payload too large	Reduce the request size
429	Rate limited	Retry with jittered exponential backoff (1s → 2s → 4s, cap ~30s)
500	Gateway or upstream error	Idempotent requests are safe to retry

The Anthropic error envelope looks like this:

{"type":"error","error":{"type":"permission_error","message":"..."}}

Every error message ends with a request ID; include it when you open a support ticket. A 403 with a valid key usually means the model is not on your whitelist or the balance is exhausted.

Billing

A non-streaming response’s usage reports token counts only, never the amount charged. Check the amount in the Platform or with GET /api/log/token.
Text and multimodal chat are billed per token (input, output, and cache read, in USD per 1M tokens). Reasoning tokens are billed as output.
Your balance is prepaid in USD and never expires, and there is no subscription or monthly fee. When it runs out, calls fail with 403; after you top up, the same key works again immediately.

Troubleshooting

Bare base_url, no /v1. The SDK builds /v1/messages itself; adding /v1 duplicates the segment.
/v1/messages/count_tokens is not implemented and returns 404. The SDK exposes it, but you do not need to count tokens to call messages.create.
Unsupported parameters. Tool use, streaming, and thinking work only when the upstream model supports them; the upstream may ignore or reject parameters it does not support.
429 has no Retry-After header. Implement backoff in your client instead of waiting for a hint.
baseURL vs base_url. The Python SDK uses base_url; the TypeScript SDK uses baseURL.