models/Meta/DETR ResNet-50

DETR ResNet-50

image

Meta's transformer-based object detector. Returns bounding boxes + labels.

MODALITIES

image

PER IMAGE

$0.0002

DETR ResNet-50 (facebook/detr-resnet-50) is a image model from Meta. Pricing via AIgateway: $0.0002 per image. Call it via https://api.aigateway.sh/v1/images/generations — set model="facebook/detr-resnet-50". Best for: Object detection, Visual QA preprocessing, Inventory counting.

model · facebook/detr-resnet-50family · DETR

Use this model

model: facebook/detr-resnet-50

curl https://api.aigateway.sh/v1/images/generations \
  -H "Authorization: Bearer $AIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"facebook/detr-resnet-50","prompt":"a serene cyberpunk city at dusk"}'

curl https://api.aigateway.sh/v1/images/generations \ -H "Authorization: Bearer $AIGATEWAY_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"facebook/detr-resnet-50","prompt":"a cyberpunk cat"}'

Capabilities

Strengths

End-to-end object detection
Open-weight

Use cases

Object detectionVisual QA preprocessingInventory counting

Pricing

Per image$0.0002

Open-weight

You pay pass-through · 5% applied at credit top-up, not per-call.

See API example →Compare API reference See usage ranking →

Collections

More image models →More from Meta →Frontier models →Free-tier models →

API schema

Call DETR ResNet-50 from any OpenAI SDK

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

Request body

json

{
  "model": "facebook/detr-resnet-50",
  "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="facebook/detr-resnet-50",
    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 DETR ResNet-50?

Meta's transformer-based object detector. Returns bounding boxes + labels. It is a image model from Meta, accessible via AIgateway's OpenAI-compatible API at slug facebook/detr-resnet-50.

How much does DETR ResNet-50 cost via AIgateway?

$0.0002 per image. Pass-through plus a 5% platform fee applied at top-up.

How do I call DETR ResNet-50 from my code?

Point the OpenAI SDK at https://api.aigateway.sh/v1 with your AIgateway key and set model to "facebook/detr-resnet-50". The request and response shapes match OpenAI exactly.

Does DETR ResNet-50 support streaming, tool calling, vision, and JSON mode?

Streaming — no. Tool calling — no. Vision — no. JSON mode — no. Prompt caching — no.

What are the best use cases for DETR ResNet-50?

Object detection, Visual QA preprocessing, Inventory counting. Key strengths: End-to-end object detection; Open-weight.

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 waives the 5% platform fee on those calls.