> Inference.net
Inference.net is a unified LLM gateway, observability and fine-tuning platform rather than an image or video vendor. Its pay-as-you-go tier is $0 + usage and includes 1M gateway requests and 1M tracing spans per month, 14-day data retention, one seat and a 30 req/min rate limit. Growth is $250/month with a $50 one-time opening credit, 50M gateway requests and tracing spans per month, unlimited seats and a 250 req/min limit. The catalog lists 60 models from OpenAI, Anthropic, Google and open-source labs billed per token, from Schematron V2 Turbo at $0.03/$0.15 to Claude Opus 5 and GPT-6 Astra at $5.00-$10.00 input and $25.00-$50.00 output per 1M tokens.
// pros
- Per-token rates for 60 models are published in a single table including cache-read pricing, for example Claude Opus 5 at $5.00 input, $0.50 cached read and $25.00 output per 1M tokens.
- The $0 tier is usable without a card and includes 1M gateway requests plus 1M tracing spans per month, enough for evaluation and pre-production testing.
- Cheap open-weight endpoints anchor the low end of the catalog: Schematron V2 Turbo at $0.03/$0.15 and GLM-5.3 Flash at $0.15/$0.50 per 1M tokens.
- Growth raises the rate limit from 30 to 250 req/min, removes the seat cap, extends retention from 14 days to unlimited and includes a $50 one-time opening credit.
- Routing, tracing, evaluation and fine-tuning sit behind one API key on an OpenAI-compatible serverless endpoint with no commitment.
// cons
- The free allowance is denominated in gateway requests and tracing spans, not dollars, so its monetary value cannot be calculated from published data.
- There is no cheap paid tier between the $0 plan and $250/month Growth, which is steep for a small team that outgrows 30 req/min.
- The $0 tier's 14-day data retention rules out long-horizon trace analysis, and the 30 req/min limit excludes production traffic.
- The catalog is text and vision LLMs only - no image, video or audio generation endpoints are listed - so generative media workflows cannot be served here.
Use Inference.net when you want one OpenAI-compatible key across OpenAI, Anthropic, Google and open-weight models with tracing and evaluation attached to the same account. Start on the $0 tier to benchmark models per task, then move to Growth only once sustained throughput justifies $250/month, since the jump from free to paid is large.
written by Mike Fleming, Uprouter editorial · verified against official sources September 16, 2026
Free tier present — value not quantified
This provider offers a free tier, but its terms don’t convert cleanly into a USD figure (e.g. request-count limits or capacity-dependent pools). We refuse to print a misleading zero here. See the note below and the official pricing page for the exact limits.
note: No free dollar credit: the $0 pay-as-you-go tier includes 1M gateway requests and 1M tracing spans per month, while the $50 one-time opening credit is listed only on the $250/month Growth plan (checked 2026-09-16).
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Free tier (source-reported) | free | — | — | — | ~$1 credits on sign up, +$25 more after replying to an email survey; free tier limited to ~30 req/min (paid ~250/min). Converts to paid after credits are spent. |
| Pay-as-you-go | payg | — | $0.040 | $0.100 | Rate for Schematron-8B; Llama 3.1 70B also available at competitive rates. |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Meta-Llama-3.1-70B-Instruct | — | — | 131k |
$ Does Inference.net have a free tier?
Yes — Inference.net offers a free tier. Always confirm current limits on Inference.net's official pricing page — free tiers change without notice.
$ How much does Inference.net cost per 1M tokens?
Inference.net does not publish simple per-1M-token pricing (it may bill per request, per output, or via a subscription plan). Check their official pricing page for exact figures.
$ Is Inference.net safe to use?
Uprouter rates Inference.net as medium risk. Low to moderate. Pricing is per token and published across the whole catalog, the entry tier is free and needs no card, and enterprise terms are explicitly contact-only rather than hidden. The practical risks are commercial rather than policy-based: the free allowance has no stated dollar value, the first paid tier is $250/month, and the platform serves LLMs only, so it is a routing and observability layer rather than a generative-media provider. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.
Raw community sentiment, shown unblended. Votes never feed into objective data fields like price, risk, or status — and never into sort order.
No published reviews yet — be the first.
// more_informationprice history · live status · risk & confidence · code snippets
price_history
No recorded changes yet.
live_status
current: upNo probes recorded yet.
Uprouter runs its own probes; best-effort, not a guarantee. Probe results depend on our network location and cadence — for production, always use the provider’s own status page.
risk_&_confidence
Low to moderate. Pricing is per token and published across the whole catalog, the entry tier is free and needs no card, and enterprise terms are explicitly contact-only rather than hidden. The practical risks are commercial rather than policy-based: the free allowance has no stated dollar value, the first paid tier is $250/month, and the platform serves LLMs only, so it is a routing and observability layer rather than a generative-media provider.
Confidence reflects how much verifiable evidence (official docs, probe history, community reports) backs this entry. Risk is our editorial assessment of operator reliability and terms — not financial advice.
code_snippets
# Inference.net's own API — get a key from their dashboard
curl https://YOUR-PROVIDER-ENDPOINT/chat/completions \
-H "Authorization: Bearer THEIR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "meta-llama-3-1-70b-instruct",
"messages": [{ "role": "user", "content": "Hello" }]
}'Direct to the provider — Uprouter receives nothing; verify their current pricing before purchasing.
Ranked by neutral similarity signals only — live status, free-tier shape and free-credit proximity. Commercial relationships never influence this list.