models/Meta/Segment Anything Model 3
Meta

Segment Anything Model 3

image
Compare

SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.

MODALITIES
image
PER IMAGE
$0.0050

Segment Anything Model 3 (meta/sam-3-image) is a image model from Meta. Pricing via AIgateway: $0.0050 per image. Call it via https://api.aigateway.sh/v1/images/generations — set model="meta/sam-3-image".

model · meta/sam-3-image

Use this model

model: meta/sam-3-image
curl https://api.aigateway.sh/v1/images/generations \
  -H "Authorization: Bearer $AIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"meta/sam-3-image","prompt":"a serene cyberpunk city at dusk"}'
API schema

Call Segment Anything Model 3 from any OpenAI SDK

POST https://api.aigateway.sh/v1/images/generations·Content-Type: application/json·Auth: Bearer sk-aig-...

Request body

json
{
  "model": "meta/sam-3-image",
  "prompt": "A cyberpunk cat at sunset, cinematic lighting",
  "n": 1,
  "size": "1024x1024",
  "response_format": "url"   // or "b64_json"
}

Response

json
{
  "created": 1776947082,
  "data": [
    { "url": "https://media.aigateway.sh/img/abc123.png" }
    // or { "b64_json": "iVBORw0KGgoAAAANSUhEU..." }
  ]
}

Quickstart

from openai import OpenAI
client = OpenAI(base_url="https://api.aigateway.sh/v1", api_key="sk-aig-...")

r = client.images.generate(
    model="meta/sam-3-image",
    prompt="a cyberpunk cat at sunset",
    size="1024x1024",
)
print(r.data[0].url)

Errors

401authentication_errorInvalid or missing API key
402insufficient_creditsWallet empty (PAYG only)
404not_foundUnknown model or endpoint
429rate_limit_errorOver per-minute limit — see Retry-After header
500server_errorUpstream provider failed (retryable)
503service_unavailableUpstream saturated (retryable)
Full docs →API reference →OpenAPI spec →llms.txt →

Frequently asked questions

What is Segment Anything Model 3?
SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. It is a image model from Meta, accessible via AIgateway's OpenAI-compatible API at slug meta/sam-3-image.
How much does Segment Anything Model 3 cost via AIgateway?
$0.0050 per image, billed pass-through.
How do I call Segment Anything Model 3 from my code?
Point the OpenAI SDK at https://api.aigateway.sh/v1 with your AIgateway key and set model to "meta/sam-3-image". The request and response shapes match OpenAI exactly.
Does Segment Anything Model 3 support streaming, tool calling, vision, and JSON mode?
Streaming — no. Tool calling — no. Vision — no. JSON mode — no. Prompt caching — no.
Can I bring my own Meta API key (BYOK)?
Yes. Attach a Meta key in your AIgateway dashboard and this model flips to pass-through — you pay Meta directly and AIgateway adds no platform fee on those calls.