LLM API | Basic Completions - LLM API

INFO

Discount

PiAPI also provides different LLM API at cost effective pricing, sometimes at 25%~75% of their official pricing.

Availability

Given the steep discount, we sometimes face availability issues thus we always recommend developers to always have another back up API source ready - take advantage of our low pricing when you can, and when availability becomes a problem switch to a higher cost solution to maintain overall system up-time.

model name	pricing	Notes
gpt-4o gpt-5 gpt-5.2	50% of OpenAI's official pricing	50% of OpenAI's official pricing
gpt-4o-mini gpt-4.1 gpt-4.1-mini gpt-4.1-nano	75% of OpenAI's official pricing	75% of OpenAI's official pricing
claude-opus-4-6	input 1M tokens = $3.75 output 1M tokens = $18.75	75% of Anthropic's official pricing
claude-sonnet-4-6	input 1M tokens = $2.25 output 1M tokens = $11.25	75% of Anthropic's official pricing
gpt-image-1	same as openai official	see openai-official-pricing
gemini-2.5-flash-nothinking	input 1M tokens = $0.075 output 1M tokens = $0.625	25% of Gemini's official pricing
gpt-5.6-sol	input 1M tokens = $0.50 cached input 1M tokens = $0.05 output 1M tokens = $3.00	Limited-time promotional pricing (10% of OpenAI's official pricing)
gpt-5.6-terra	input 1M tokens = $0.20 cached input 1M tokens = $0.02 output 1M tokens = $1.20	Limited-time promotional pricing (10% of OpenAI's official pricing)
gpt-5.6-luna	input 1M tokens = $0.02 cached input 1M tokens = $0.002 output 1M tokens = $0.12	Limited-time promotional pricing (10% of OpenAI's official pricing)
gpt-6-astra	input 1M tokens = $2.00 cached input 1M tokens = $0.20 output 1M tokens = $10.00	Limited-time promotional pricing (20% of OpenAI's official pricing)

Note:

OpenAI's input and output tokens, where 1k token roughly equals to 750 words. Thus 1 token roughly equates to 0.75 word.

The definition of minimum charge: if the actual token (input+output) usage for that particular completion is less than that value, we will round it that value.

Long-context pricing for gpt-6-astra: when the input context of a request exceeds 272,000 tokens, the entire request is billed at 2x the input and cached-input price and 1.5x the output price - input 1M tokens = $4.00, cached input 1M tokens = $0.40, output 1M tokens = $15.00. This mirrors OpenAI's own long-context pricing.

Request

Header Params

Body Params application/json

Example

//Request Example - No Streaming

curl https://api.piapi.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [
     {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'


  //Request Example - Streaming
  curl https://api.piapi.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
   ],
    "stream": true
  }'

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

Responses

🟢200OK

application/json

Bodyapplication/json

Examples

Success- No StreamingSuccess-Steaming

{
    "id": "chatcmpl-83jZ61GDHtdlsFUzXDbpGeoU193Mj",
    "object": "chat.completion",
    "created": 1695900828,
    "model": "gpt-3.5-turbo",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "Hello! How can I assist you today?"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 19,
        "completion_tokens": 9,
        "total_tokens": 28
    }
}

🟠400Bad Request

🟠401Unauthorized

🔴500Server Error

LLM API | Basic Completions

Discount#

Availability#

Request

Request Code Samples

Responses

Discount

Availability