Claude api price: API documentation

Authentication and API keys

Generate your key instantly via Google or email. Send it in the Authorization header to access https://api.claudeapiprice.com/v1.

Chat completions endpoint

Send text to get text. Our model handles context windows up to 100,000 tokens. Use the standard chat format to receive responses.

Copycurl https://api.claudeapiprice.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the current pricing for each model tier"}]
  }'

Streaming responses and token usage

Enable streaming for low-latency output. Token usage details appear in the final chunk of the stream, ensuring you track costs accurately in real time.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Function calling and tools

Define tools to let the model perform actions. Use tool_choice for strict mode or auto for automatic selection. This enables complex workflows without manual parsing.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.claudeapiprice.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

JSON mode and parameters

Force structured output using response_format. Adjust temperature or top_p to control creativity. This ensures consistent results for code generation or data extraction tasks.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.claudeapiprice.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Rate limits and quotas

You get 300 requests per minute per key. Errors like 401 (invalid key) or 402 (no credit) do not consume tokens. Handle 429 errors by waiting before retrying.