Documentation

# Two lines, no install. Point any OpenAI-compatible client at InferAll:
#   base URL  https://api.inferall.ai/v1
#   api key   your ifu_... key from inferall.ai/keys

# Python SDK
pip install inferall-ai

# TypeScript SDK
npm install @inferall/sdk

# There is also an install wizard that edits your project for you:
npx @inferall/cli init
#
# Heads up: the published wizard (0.2.0) is several releases behind and has a
# number of known problems, including a doctor command that can call a
# committed .env safe and an init that may leave your key written but not
# gitignored. All are fixed in the repo and unpublished. Until the next release
# lands, the two lines above are the reliable path.

// Native TypeScript SDK — live on npm as @inferall/sdk 0.1.0
import { Inferall } from "@inferall/sdk";

const ai = new Inferall(); // reads INFERALL_API_KEY (ifu_...)

// Text (free OSS by default)
const text = await ai.text("Explain quantum computing in two sentences");

// Chat with a specific provider/model
const reply = await ai.chat(messages, {
  provider: "anthropic",
  model: "claude-sonnet-4-6",
});

// Vision
const analysis = await ai.vision(imageBase64, "What is this?");

// Image-to-video (Veo3) — pass a source frame for persona-consistency
const talkingHead = await ai.generate({
  provider: "gemini",
  model: "veo-3.1-generate-preview",
  operation: "video-generate",
  prompt: "Talking-head shot, looking at camera",
  source_image_url: "https://example.com/persona-portrait.jpg",
});

// Prefer the official OpenAI/Anthropic SDKs instead? Point them at InferAll:
//   OPENAI_BASE_URL=https://api.inferall.ai/v1   (key: ifu_...)
//   ANTHROPIC_BASE_URL=https://api.inferall.ai   (key: ifu_...)

from inferall import Inferall

ai = Inferall()  # reads INFERALL_API_KEY from the environment

# Text generation (free via NVIDIA Llama by default)
text = ai.text("Explain quantum computing")

# Chat with any provider
reply = ai.chat(messages, provider="anthropic", model="claude-sonnet-4-6")

# Vision
analysis = ai.vision(image_base64, "What is this?")

# Generate (image or video)
video = ai.generate(
    provider="gemini",
    model="veo-3.1-fast-generate-preview",
    operation="video-generate",
    prompt="Drone shot of a city",
)

# Image-to-video (Veo3) — pass a source frame to keep the subject consistent
talking_head = ai.generate(
    provider="gemini",
    model="veo-3.1-generate-preview",
    operation="video-generate",
    prompt="Talking-head shot, looking at camera",
    source_image_url="https://example.com/persona-portrait.jpg",
)

# Already using the OpenAI SDK? Change two arguments.
from openai import OpenAI

client = OpenAI(
    base_url="https://api.inferall.ai/v1",
    api_key="ifu_your_inferall_key",
)

# Free NVIDIA NIM open models: $0 in, $0 out
resp = client.chat.completions.create(
    model="meta/llama-3.1-8b-instruct",
    messages=[{"role": "user", "content": "Explain quantum computing"}],
)
print(resp.choices[0].message.content)

# Check what actually answered.
print(resp.model)   # meta/llama-3.1-8b-instruct, the id you sent

# Reach a premium provider with a model prefix, billed from your balance
resp = client.chat.completions.create(
    model="anthropic/claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Same call, different provider"}],
)
print(resp.model)   # claude-sonnet-4-6, the prefix is routing and is stripped

# If resp.model names a model you did not ask for, the ID could not be routed
# and a free default answered instead. A bare "gpt-4o" comes back this way as
# meta/llama-3.1-70b-instruct. There is no error and no warning header when it
# happens, so resp.model is the check that catches it.

# Use Claude Code with free inference
export ANTHROPIC_BASE_URL=https://api.inferall.ai
export ANTHROPIC_API_KEY=your_inferall_key

# Run Claude Code normally — uses free NVIDIA models by default
claude

# Force a specific provider with model prefix
# anthropic/claude-sonnet-4-6  → actual Claude
# gemini/gemini-2.5-flash            → Google Gemini