Every free model hosting tier that clears our bar in 2026: 4 offers meet the criteria and 3 offers are demoted with a named reason. Our membership test: you supply or select a model and the platform serves it behind an endpoint on hardware you choose. We could not confirm today's terms for 2 of them, and on all 2 our own read did not confirm them. Each row says why.
Serverless platform for running CPU and GPU workloads. The Starter plan has no monthly fee and includes $30 of compute per month (GPU, CPU and memory), 3 workspace seats, 100 containers and 10 GPU concurrency. Usage beyond the $30 is billed per second: T4 $0.000164 per second; H100 $0.001097 per second. Since 2026-09-01, Shared Endpoints are billed per token from the first request and are not covered by the $30. Since 2026-10-01, network egress beyond 1 TiB a month is billed at $0.04 per GiB. Team is $250 per month with $100 of compute included. Note — 2026-10-01: Since October 1, 2026, Modal charges for network egress: the Starter plan includes 1 TiB a month, Team 10 TiB and Enterprise 100 TiB, and egress beyond that costs $0.04 per GiB. Source ↗
Listed in AI / ML, and on this page because we labelled it model_hosting. We read that on 2026-10-31 from https://modal.com/pricing, where it says: “Serve LLMs, image, video, and audio models, from real-time to batch”. How we use this
Computer vision platform for labeling, training and deploying models. On September 18, 2026 Roboflow announced a free tier for its Core plan: 10 credits that refresh every month, private projects and models, and model weight download. More credits can be bought. Credits pay for storage, labeling, training and cloud deployment; running models on your own hardware with Roboflow Inference uses none. Core's data licensing and model training setting is on by default, including for private projects; a workspace can turn it off. Public plan workspaces are moving to the Core free tier. The page we cite for Roboflow states in words that it is free, which confirms the price — the limits stated here come from our own record rather than from that page. Note — 2026-07-30: Roboflow's free Public plan went from "$60/mo free credits" to "15 credits / month" between the Internet Archive's 2026-06-23 and 2026-07-30 captures of its pricing page. Roboflow states no dollar value for a credit; its Core plan sells 50 credits for $99 a month. Source ↗
Listed in AI / ML, and on this page because we labelled it model_hosting. We read that on 2026-09-01 from https://roboflow.com/pricing, where it says: “Data labeling suite w/ AI features Model training Workflow builder Cloud hosted deployment”. How we use this
ML model hub. Since 2026-10-07, free accounts get no included Inference Providers credits: free users buy credits or upgrade to PRO to call Inference Providers, which serves 200+ models. PRO ($9/month) gets $2.00 a month. Free accounts get 100GB of private storage and best-effort public storage; substantial storage needs PRO, Team or Enterprise. Note — 2026-10-07: Hugging Face stopped giving free accounts included monthly Inference Providers credits; free users now have to buy credits or upgrade to PRO to call Inference Providers. Source ↗
Listed in AI / ML, and on this page because we labelled it model_hosting. We read that on 2026-09-01 from https://huggingface.co/docs/inference-providers/pricing, where it says: “Inference Endpoints (dedicated)”. How we use this
ML platform (Gradient Notebooks, Workflows and Deployments) from Paperspace, now part of DigitalOcean. The Free plan is $0 with public projects, 5 GB of storage and free machines for Notebooks in your private workspace (Free CPU C4 and Free GPU M4000; free machines shut down after at most 6 hours). Other machines are billed per hour. Pro is $8/month for individuals and $12/month for teams; Growth is $39/month. DigitalOcean says new customers can still sign up but recommends its own GPU products instead.
Listed in AI / ML, and on this page because we labelled it model_hosting. We read that on 2026-09-01 from https://www.paperspace.com/pricing, where it says: “Deployments (inference) - Model Repository”. How we use this
ML model hosting and inference. A new account can run the models in Replicate's Try for Free collection without buying credit, for a limited number of runs that Replicate does not state; after that you add billing and buy credit. Replicate says these models are not free forever. Most models bill by the second for the hardware they run on, such as $0.000025/sec on CPU Small and $0.001525/sec on one H100. Official models bill per output instead, such as FLUX 1.1 Pro at $0.04 per image; per million input/output tokens: DeepSeek-R1 $3.75/$10.
Listed in AI / ML, and on this page because we labelled it model_hosting. We read that on 2026-09-01 from https://replicate.com/pricing, where it says: “Thousands of open-source machine learning models have been contributed”. How we use this
Inference platform for open models, with serverless per-token pricing and on-demand GPU deployments billed per GPU second. Fireworks offers $1 in free credits to get started. Accounts with no payment method, or with no credits, are limited to 10 requests per minute, and an account without a payment method is suspended when the $1 credit runs out until one is added. Serverless prices: OpenAI GPT OSS 120B $0.15/$0.60 (per 1M tokens); MiniMax M3 $0.30/$1.20 (per 1M tokens); GLM 5.3 $1.40/$4.40 (per 1M tokens); Kimi K3 $3.00/$15.00 (per 1M tokens); Kimi K3.1 Pro $2.00/$10.00 (per 1M tokens). Batch inference costs 50% of serverless prices. Image generation and audio inference were deprecated on June 10, 2026. Fireworks removed these models from serverless in 2026, so serverless requests for them fail (dedicated deployments are unaffected), according to its changelog (docs.fireworks.ai/updates/changelog): DeepSeek V4 Pro (0813) (accounts/fireworks/models/deepseek-v4-pro-0813) on 2026-09-25, replaced by DeepSeek V4.1 Flash $0.30/$1.20 (deepseek-v4p1-flash); DeepSeek V4 Flash (0731) (deepseek-v4-flash-0731) on 2026-09-25, replaced by DeepSeek V4.1 Flash; GLM 5.2 (glm-5p2) on 2026-09-25, replaced by GLM 5.3 (glm-5p3); Kimi K2.6 (kimi-k2p6) on 2026-09-25, replaced by GLM 5.3 or Kimi K3 (kimi-k3); Kimi K2.7 Code (kimi-k2p7-code) on 2026-09-25, replaced by GLM 5.3 or Kimi K3; Muse Glimmer 30B (muse-glimmer-30b) on 2026-09-25, replaced by NVIDIA Nemotron 3.5 Lightning 30B A3B $0.05/$0.20 (nemotron-lightning-3p5-30b-a3b); GPT OSS 20B (gpt-oss-20b) on 2026-08-27, replaced by GPT OSS 120B or Qwen3 8B; MiniMax M2.7 (minimax-m2p7) on 2026-08-27, replaced by MiniMax M3; Kimi K2.5 (kimi-k2p5) on 2026-06-26; Qwen 3.6 Plus (qwen3p6-plus) on 2026-06-26, replaced by Qwen 3.7 Plus; MiniMax M2.5 (minimax-m2p5) on 2026-06-17. Fireworks serverless serves Kimi K3 (kimi-k3) at $3.00/$15.00 and Kimi K3.1 Pro (kimi-k3p1-pro) at $2.00/$10.00. When we last read the page we cite for this offer, on 2026-10-28, we found the same terms as an earlier read we had declined to record, so we cannot confirm these terms today.
Listed in AI / ML, and on this page because we labelled it model_hosting. We read that on 2026-09-01 from https://fireworks.ai/pricing, where it says: “priced per GPU hour (billed per second), at the same price as Fireworks on-demand deployments”. How we use this
ML model deployment platform. New workspaces receive credits for testing and deployment; Baseten does not state the amount. Basic plan: $0 per month, pay as you go. Dedicated deployments bill per minute. Model APIs bill per 1M tokens: GLM-5.3 $1.40/$4.40. GLM-5.3-Flash $0.15/$0.50. When we read the page we cite for this offer on 2026-09-10, we found a change we could not reconcile with the terms we publish, and we have read it again since, on 2026-10-29, without confirming them, so we cannot confirm these terms today.
Listed in AI / ML, and on this page because we labelled it model_hosting. We read that on 2026-09-01 from https://www.baseten.co/pricing/, where it says: “You can deploy open source and custom models on Baseten”. How we use this
| Vendor | Free Tier | Key Limits | Durability | Read / catalogue date |
|---|---|---|---|---|
| Modal | Free | Serverless platform for running CPU and GPU workloads. The Starter plan has no monthly fee and includes $30 of compute p... | volatile effective 2026-10-01 |
2026-11-08 / 2026-09-22 |
| Roboflow | Free | Computer vision platform for labeling, training and deploying models. On September 18, 2026 Roboflow announced a free ti... not confirmed · page states a free price · 2026-11-02 | watch effective 2026-07-30 |
2026-11-02 |
| Hugging Face | Free | ML model hub. Since 2026-10-07, free accounts get no included Inference Providers credits: free users buy credits or upg... | watch effective 2026-10-07 |
2026-10-30 / 2026-10-05 |
| paperspace | Free | ML platform (Gradient Notebooks, Workflows and Deployments) from Paperspace, now part of DigitalOcean. The Free plan is ... | stable | 2026-11-06 |
We publish no ranking of these. Nothing we record measures popularity or generosity, so naming a best or a top few would be our preference rather than our data. We hold 4 free model hosting offers that clear our bar, each listed with the terms we publish and the date we last read them. Our ranking rule is published at /criteria.
4 offers meet our criteria on this page. Of those, 1 carries no recorded change to the terms we publish, and 3 a recorded narrowing. The Durability column below says which offer is in which group, and links the dated record behind every change. We do not rank these by how much you get, because the limits are not comparable without reading each vendor's page.