Proof, not assertion

Live

What the InferAll gateway actually serves, right now. All counts are fetched server-side from /ai/v1/models and /ai/v1/health and refreshed at most once per hour — same numbers a developer can verify with curl.

Gateway status

Healthy

Models

217

Total

119

Free

98

Paid

“Free” means the model's pricing fields are explicitly $0 — for token models that's inputPerM and outputPerM both 0. Missing pricing metadata is not counted as free.

Usage · trailing 30 days

15,500

Requests

31.6M

Tokens routed

6

Upstream providers used

Values are rounded to stable buckets server-side and refreshed every 5 minutes — see /api/public/stats. User and signup counts are deliberately not exposed (poisoned by the 2026-06-08 bot burst); consumption metrics are bot-resistant by construction.

By vendor

VendorModelsFree
google5312
nvidia4444
openai212
runway14
meta1111
mistralai1111
anthropic9
other5
ibm44
writer44
deepseek-ai33
microsoft33
qwen33
stability-ai2
black-forest-labs2
minimax2
bytedance21
minimaxai22
stepfun-ai22
kwaivgi1
sync1
devxpy1
01-ai11
abacusai11
adept11
ai21labs11
aisingapore11
baai11
bigcode11
databricks11
moonshotai11
nv-mistralai11
poolside11
sarvamai11
snowflake11
thinkingmachines11
upstage11
z-ai11
zyphra11

Vendor is the namespace in the model id (e.g. meta/llama-… meta). Many OSS models are routed through NVIDIA NIM regardless of vendor — see /docs for the routing details.

Beyond what's enumerated above: the gateway also passes any Replicate model id (owner/name) directly through to Replicate, and any NVIDIA NIM model id through to NIM — so the routable catalog is much larger than the number listed here. The counts on this page reflect what's explicitly enumerated in the registry today.

By source

173

Live (dynamic pricing pulled from upstream APIs)

44

Static (pricing pinned in the gateway registry)

Verify

Want to count for yourself? curl https://api.inferall.ai/ai/v1/models | jq 'keys | length' should equal 217 within the hour.