Instamodel
Sign inGet API key
The open network for specialist models

Use the best model for:specialized work across every industry.

One API designed for frontier, open-weight, and post-trained models. Every model shown publicly is backed by an enabled provider route; publishers can submit new specialist deployments.

Get API key Publish a model
Enabled models
0
Provider routes
0
API format
OpenAI
ROUTING RECEIPTConfigured deployment
NO ROUTES
LIVE CATALOG

No credentialed provider route is enabled yet. Models appear here automatically when they become callable.

01 / MODEL EXCHANGE

One catalog. Every model class.

The catalog stays empty until a provider-backed route is actually callable.

No provider-backed models are enabled yet.

GET /v1/models and this page read from the same enabled registry.

Get API key
Every enabled model class uses the same authenticated endpoint.Browse all models
02 / ONE NETWORK, TWO SIDES

Built for callers.
Built for creators.

Model ownership, inference hosting, and API access stay separate—so each party gets one clear contract, one ledger, and the right controls.

A / FOR AI TEAMS

One key. The right model for every request.

Keep the OpenAI client you already use. Choose an exact model and constrain its configured deployment by region and retention policy.

  • OpenAI-compatible, non-streaming chat completions
  • Function tools and structured output
  • Fail-closed region and retention constraints
  • Per-request provider, latency, and usage receipts
quickstart.pyPYTHON
from openai import OpenAI

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

# Returns only models with an enabled provider route
models = client.models.list()
Create an API key
B / FOR MODEL LABS

Your specialist model should earn while it works.

Bring a post-trained model or LoRA adapter. Each published version records immutable weights, pricing, and revenue-share terms while validation and deployment protect the network.

  1. 01
    ImportSafetensors, Hugging Face, or S3-compatible storage
  2. 02
    ValidateProvenance, compatibility, safety, and smoke generation
  3. 03
    DeployImmutable version served by an approved inference host
  4. 04
    AccrueAuditable royalty ledger; statement closing and cash payouts are not active yet
REQUEST ECONOMICSVERSIONED
Customer usage chargeMeasured usage
Model owner royaltyContract rate
Inference host + platformRemainder
Every price and revenue-share rate is pinned to the model revision used.
Start publishing
03 / TRUSTED CONTROL PLANE

Build toward auditable inference.

Publisher submissions snapshot immutable revisions, prices, and commercial terms. Every finalized post-trained request charges the prepaid wallet and posts usage, host cost, owner royalty, and platform margin together.

Read the routing contract
MODEL OWNER
Immutable weightsrevision sha256:8f2…
Commercial termsroyalty · price · license
INSTAMODEL
Gateway receiptrequest · provider · region
Ledger schematokens · charge · royalty
INFERENCE NETWORK
Approved hostcapacity · health · retention
Provider usagerequest · units · latency
01No silent alias changeThe requested public model ID is preserved on every response.
02Scoped data accessDirect routes use their host; OpenRouter routes pass through OpenRouter to its selected downstream provider.
03One canonical requestIdempotency reserves a customer request before dispatch.
04Versioned economicsPublisher pricing and royalty terms are stored as immutable versions.
THE MODEL NETWORK AFTER PRETRAINING

One key. A marketplace
of models.

Create one API key and call frontier, open-weight, and post-trained models through one OpenAI-compatible endpoint.

Get API key Publish a model