--- title: "No-free inference directory" description: "Providers whose inference API is paid-only, retired, UI-only, BYOK, nonfunctional, or otherwise not a current free hosted API." canonical_url: "https://freeinferencing.com/shame/" md_url: "https://freeinferencing.com/shame.md" last_updated: "2026-09-19" --- # The no-free inference directory > This is evidence, not outrage. A provider leaves this directory when a genuinely free hosted offer is verified. ## Classification rule This directory preserves negative knowledge: paid-only APIs, retired tiers, free chats without developer APIs, BYOK gateways, and free weights that still require paid compute. ## Records - [AI/ML API](/provider/aimlapi.md): Not a free offer. The authoritative current FAQ says the Free Tier is paused; live aliases containing :free do not override that statement. - [Ai2 Playground](/provider/ai2_playground.md): Not a free offer. Ai2 directs API users to external paid routes; its playground is not a documented general developer API. - [ALIA Spain](/provider/alia_spain.md): Not a free offer. Publishes open models and resources, but no stable public developer inference endpoint with current auth and quotas. - [Avian API](/provider/avian_api.md): Not a free offer. Current models have positive prices and credits must be prepaid; Start Free is signup wording, not a compute allowance. - [China National Supercomputing Internet Yucai 2026 promotion](/provider/scnet_yucai_2026_promo.md): Not a free offer. Slots are full and the agreement ended 2026-04-30; historical allowance was 100 accelerator-card hours, 500 GB, and 10 million model tokens. - [Chutes](/provider/chutes.md): Not a free offer. No current provider-funded inference offer was verified. - [Cosine](/provider/cosine.md): Not a free offer. Current plans start at $19/month and no direct hosted inference API, public model catalog, or automatic free developer quota is published; an OpenRouter provider slug is not a direct offer. - [CSCS inference service](/provider/cscs_inference.md): Not a free offer. Non-SwissAI use consumes project credits converted from allocated node-hours at a published CHF rate. - [Darkbloom](/provider/darkbloom.md): Not a free offer. Public alpha access is evaluation-only, but every displayed model has a positive token price. - [DeepInfra](/provider/deepinfra.md): Not a free offer. The current public catalog has positive per-token or per-execution prices and no permanent recurring free quota. - [DigitalOcean Gradient serverless inference](/provider/digitalocean_gradient_inference.md): Not a free offer. A separate prepaid inference balance is mandatory; the free router preview does not make routed model inference free. - [Duckk Africa](/provider/duckk_africa.md): Not a free offer. The live production service documents positive per-token prices, prepaid balance top-ups, and a USD 5 minimum top-up; no automatic free API allowance was found. A separate limited free web chat does not qualify as API inference. - [EuroHPC AI Factories access modes](/provider/eurohpc_ai_factories.md): Not a free offer. Application and allocation infrastructure is not an automatic shared developer inference entitlement. - [fal Model APIs](/provider/fal_ai_general_api.md): Not a free offer. Sandbox coupons cannot fund API or Workflow calls; only the application-based Builder Grant is potentially free. - [Falcon / Technology Innovation Institute](/provider/falcon_tii.md): Not a free offer. A public chat and a first-party/partner case study claim an API platform, but no stable developer base URL, authentication flow, free limits, or API reference could be verified. - [Featherless AI](/provider/featherless_ai.md): Not a free offer. The lowest current plan is paid and monthly credits belong to paid subscriptions. - [FlexAI Token Factory ordinary accounts](/provider/flexai_token_factory.md): Not a free offer. Current billing docs say new accounts receive no automatic credit; billing address and card are required for an API key and at least $5 must be added before ordinary inference. The Free label is a rate-limit tier, not zero-price inference. - [free-router.tonylee.im](/provider/free_router_tonylee.md): Not a free offer. The CLI/router aggregates upstream services such as NVIDIA and OpenRouter using user-supplied credentials; it does not fund hosted inference. - [FreeLLMAPI.co](/provider/freellmapi_co.md): Not a free offer. Users self-host the router and supply upstream provider keys. - [FriendliAI](/provider/friendli_ai.md): Not a free offer. Current docs describe promotional credits from promo codes or discretionary promotions but promise no automatic signup amount; ordinary access requires purchased credit with a $10 minimum. - [GitHub Models](/provider/github_models.md): Not a free offer. No current provider-funded inference offer was verified. - [Hugging Face Spaces / Gradio demos](/provider/huggingface_spaces_as_a_class.md): Not a free offer. Many Spaces expose callable Gradio endpoints, but there is no shared quota, catalog guarantee, authentication policy, or availability commitment; individual Spaces may sleep or disappear. - [Inference.net](/provider/inference_net.md): Not a free offer. The free plan covers gateway requests and tracing; all live model entries have positive inference prices. - [Infermatic](/provider/infermatic.md): Not a free offer. The $0 plan explicitly has no API access; API access starts on a paid plan. - [Isambard-AI inference service](/provider/isambard_ai_inference.md): Not a free offer. Research allocations exist, but the July 2026 update says the shared inference service is still being prepared. - [Krutrim Cloud AI Studio](/provider/krutrim_cloud.md): Not a free offer. Current AI Studio requires purchased credits and has no verified automatic free allowance. - [Lambda hosted Inference API](/provider/lambda_inference_api.md): Not a free offer. Lambda sunset the hosted API after 2025-09-25; the current alternative is paid GPU infrastructure. - [LatamGPT / Copuchat](/provider/latamgpt.md): Not a free offer. Public chat and downloadable open weights exist, but no documented general developer inference API was found. - [Liquid AI hosted API](/provider/liquid_ai_hosted_api.md): Not a free offer. Current free offer covers downloadable/on-device models and tooling, not operator-funded remote inference. - [LLM-jp](/provider/llm_jp.md): Not a free offer. Publishes weights, corpora, and tooling rather than a stable hosted inference API. - [MuiRouter](/provider/muirouter.md): Not a free offer. The $0 gateway subscription still requires account top-up and charges model list prices; the gateway fee alone is free. - [National University of Singapore generic AI services (unrelated name match)](/provider/national_university_of_singapore.md): Not a free offer. No current provider-funded inference offer was verified. - [NextBit](/provider/nextbit.md): Not a free offer. Current docs and terms describe prepaid positive-price API usage with no quantified automatic free allowance. - [NexusRouter.com BYOK gateway](/provider/nexusrouter_com.md): Not a free offer. The .com service is a downloadable/configurable BYOK gateway and is unrelated to the possibly qualifying hosted nexusrouter.net record. - [Nscale Serverless Inference](/provider/nscale_serverless_inference.md): Not a free offer. Current onboarding requires adding at least $5 credit. A statement that early users may receive unspecified promotional offers is neither automatic nor a quantified current free allowance. - [OpenGradient](/provider/opengradient.md): Not a free offer. Hosted inference uses x402 or OPG payment rather than a free tier. - [OpenI / Qizhi Community compute and model development](/provider/openi_china_compute_platform.md): Not a free offer. Free compute and model-development resources exist, but no stable operator-hosted general inference base, auth, quota, and service commitment were found. - [Petals public chat endpoint](/provider/petals_public_chat.md): Not a free offer. A live call returned MissingBlocksError because no peers held the required model blocks. - [Public AI old blanket-free offer](/provider/public_ai_old_blanket_free.md): Not a free offer. Starter credit followed by positive per-token wallet billing. - [Qwen OAuth free access for Qwen Code](/provider/qwen_code_oauth.md): Not a free offer. No current provider-funded inference offer was verified. - [Runpod Serverless and Public Endpoints](/provider/runpod.md): Not a free offer. Normal inference requires a positive balance; selective startup credits are recorded separately as conditional. - [Self-hosted open-weight models](/provider/self_hosted_open_weights.md): Not a free offer. The model weights may be free, but remote hosted compute is not being provided. - [SwarmLLM](/provider/swarmllm.md): Not a free offer. The public alpha exposes localhost:8800 after users install a daemon and depends on peers; it still has no stable operator-hosted public gateway or funded catalog. - [Together AI](/provider/together_ai.md): Not a free offer. Official billing docs say there are no free trials; API access requires at least a $5 credit purchase. - [TypeSafe AI](/provider/typesafe_ai.md): Not a free offer. The direct Jev API is waitlist-gated and publishes positive token pricing with no automatic free allocation. OpenCode Zen's temporary jev-1.13-free route is recorded under OpenCode rather than as a TypeSafe direct free offer. - [Wafer](/provider/wafer.md): Not a free offer. Current terms describe paid Wafer Pass and inference; third-party claims of a free route lack first-party support. - [WebInfer resource pool](/provider/webinfer_resource_pool.md): Not a free offer. First-party pages explicitly advertise a completely free community pool and document api.webinfer.dev, but that hostname and other candidate gateways did not resolve on 2026-08-29; callability, catalog, signup, and limits remain unverified. ## Sitemap See the full [semantic sitemap](/sitemap.md) for every page and markdown mirror.