LLM API Quick Reference

Comprehensive reference for every major LLM API provider. Copy-paste ready endpoints, pricing, and code snippets.

Last updated: March 2026

import openai
client = openai.OpenAI(api_key="sk-...")
response = client.chat.completions.create(
    model="gpt-4.1",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

curl https://api.openai.com/v1/chat/completions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4.1","messages":[{"role":"user","content":"Hello"}]}'

import anthropic
client = anthropic.Anthropic(api_key="sk-ant-...")
message = client.messages.create(
    model="claude-sonnet-4-5-20250514",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(message.content[0].text)

curl https://api.anthropic.com/v1/messages \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-sonnet-4-5-20250514","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'

from google import genai
client = genai.Client(api_key="AIza...")
response = client.models.generate_content(
    model="gemini-2.5-pro",
    contents="Hello!"
)
print(response.text)

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro:generateContent?key=$GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"Hello"}]}]}'

from mistralai import Mistral
client = Mistral(api_key="...")
response = client.chat.complete(
    model="mistral-large-latest",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import openai
client = openai.OpenAI(
    api_key="sk-...",
    base_url="https://api.deepseek.com/v1"
)
response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import openai
client = openai.OpenAI(
    api_key="gsk_...",
    base_url="https://api.groq.com/openai/v1"
)
response = client.chat.completions.create(
    model="llama-3.3-70b-versatile",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import openai
client = openai.OpenAI(
    api_key="...",
    base_url="https://api.together.xyz/v1"
)
response = client.chat.completions.create(
    model="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import openai
client = openai.OpenAI(
    api_key="fw_...",
    base_url="https://api.fireworks.ai/inference/v1"
)
response = client.chat.completions.create(
    model="accounts/fireworks/models/llama-v3p1-70b-instruct",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import openai
client = openai.OpenAI(
    api_key="ollama",
    base_url="http://localhost:11434/v1"
)
response = client.chat.completions.create(
    model="llama3.2",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

curl http://localhost:11434/api/chat \
  -d '{"model":"llama3.2","messages":[{"role":"user","content":"Hello"}]}'

• Most providers (Groq, Together, Fireworks, DeepSeek) are OpenAI SDK compatible – just change base_url and api_key
• Always set max_tokens for Anthropic (required) and consider it for cost control elsewhere
• Use streaming for long responses to improve perceived latency
• Cache API keys in environment variables, never hardcode them