One API for every model open-weights ready

Ship, sell, and scale AI models on a single marketplace.

Buyers call thousands of models and datasets through one gateway, billed per token. Vendors publish in minutes and earn on every request — metering, billing, and payouts handled for you.

$ Buyers — pay-per-use, no commitments
$ Vendors — list free, earn per token
infer.sh 38 ms
# one key. every model.
curl https://api.modelmarket.dev/v1/infer \
-H "Authorization: Bearer mk_live_•••" \
-d '{ "model": "llama-3.1-70b",
"prompt": "Explain RLHF" }'
▸ 200 OK · 142 tokens · $0.00006
"RLHF aligns a model to human
preference by training a reward…"

OPEN-WEIGHTS & PROPRIETARY MODELS, READY TO CALL

Llama 3.1 Mistral Whisper SDXL Qwen2 Embed-v3 Phi-3
Integrate in minutes

One endpoint. Every model. Billed per token.

Swap models without rewriting code. The Rust inference gateway authenticates, meters, and routes every call — so you only think about prompts.

Drop-in SDKs for Python & TypeScript, with streaming support.
Scoped API keys with per-listing spend caps & quotas.
Itemised usage — every request, token, and cent accounted for.
Read the API reference
from modelmarket import Client

mm = Client(api_key="mk_live_•••")

# call any listing by id
resp = mm.infer(
    "llama-3.1-70b",
    prompt="Summarise this contract…",
    stream=True,
)

for chunk in resp:
    print(chunk.text, end="")
gateway · rust/axum ▸ p50 latency 41ms
Live catalogue

Thousands of models. Already running.

Browse open-weights releases the moment they drop, alongside specialised models and curated datasets from independent vendors — every one callable through the same key.

Lm Open

Llama 3.1 70B

Meta · open weights

Flagship open instruction model. Strong reasoning, 128K context, fully self-hostable.

text-gen128K ctxchat
$0.40 / 1M tokens 4.9
Mi Vendor

Mistral Large

Mistral AI

Top-tier proprietary model for complex reasoning, coding, and multilingual tasks.

text-gencodemultilingual
$2.00 / 1M tokens 4.8
Wh Open

Whisper Large v3

OpenAI · open weights

Robust speech-to-text across 99 languages with timestamping and diarisation.

speech→text99 langs
$0.006 / min 4.9
SD Open

Stable Diffusion XL

Stability · open weights

High-resolution text-to-image generation with fine-grained style control.

text→image1024px
$0.002 / image 4.7
Fs Vendor

FinSentiment v2

Northgate Labs

Specialised financial-news classifier tuned on 12M annotated market headlines.

classifyfinance
$0.10 / 1K reqs 4.6
Em Open

Embed v3 Multilingual

Model Market · open

1024-dim embeddings for retrieval and semantic search across 100+ languages.

embeddingsRAG
$0.013 / 1M tokens 4.8
Da Vendor

Common Crawl Curated

Dataset · 2.4 TB

Deduplicated, licence-filtered web text in Parquet — provenance docs included.

parquetpretrain
$0.15 / GB 4.7
Qw Open

Qwen2 7B Instruct

Alibaba · open weights

Compact, fast open model with strong coding and tool-use performance.

text-gentools
$0.08 / 1M tokens 4.6
Mx Vendor

MedImage-Seg

Helix Bio

Radiology segmentation model with audited provenance and licence agreement.

segmentationmedical
$0.05 / image 4.5
How it works

Two sides, one platform.

Whether you're consuming models or monetising them, you're live in three steps.

01

Discover

Search the catalogue by modality, task, licence, or price. Compare model cards, benchmarks, and sample outputs before you spend a cent.

02

Get a key

Generate a scoped API key with built-in spend caps and quotas. Top up prepaid credits or get invoiced monthly.

key mk_live_•••••••• · cap $250/mo
03

Call & pay per use

Point the SDK at any listing and ship. You're billed only for the tokens you actually consume — itemised to the request.

For vendors

You set the price. We meter the tokens. You keep the rest.

List for free and pay nothing until your models earn. Our platform fee is a small, transparent charge on the tokens your buyers actually consume — never a flat subscription, never a surprise.

Token-based fee You're only charged on consumed usage — when your models earn, so do we.
Automated payouts Stripe transfers, platform fee deducted, invoices generated — hands-off.
Real-time analytics Revenue per listing, latency, error rates, and buyer cohorts — live.
TOKENS SERVED / MONTH 500M
YOUR PRICE PER 1M TOKENS
$0.40· adjustable per listing
Gross revenue $200
Platform fee · 8% on tokens −$16
Your monthly payout $184
Pricing

Pay for what flows through.

No seats to buy, no platform to license. Both sides pay on real usage — measured token by token.

For buyers

Pay per use

$0 / month to start

Bring a card, get a key, and pay only for the tokens and downloads you consume — at each vendor's listed rate.

  • Prepaid credits or monthly invoicing
  • Per-listing spend caps against runaway costs
  • Itemised, per-request invoices
  • Multi-seat team accounts & shared billing
Get an API key
For vendors list free

Token-based platform fee

8% on consumed tokens

Publish at no cost. We take a small percentage of the usage your buyers consume, then pay out the rest automatically.

  • No fee until you earn — usage-based only
  • Set any pricing model per listing
  • Automated Stripe payouts & invoicing
  • Lower rates at volume via vendor plans
Start selling

Dataset downloads billed per-file or per-GB · Training compute billed per GPU-hour (T4 · A100 · H100)

Get started free

Build with every model.
Or sell to everyone.

Join the marketplace where AI models, datasets, and compute meet usage-based billing — live in minutes.