--- title: "AI Horde free inference" description: "Community-supplied inference across 26 models; capacity varies and throughput is not guaranteed." canonical_url: "https://freeinferencing.com/provider/ai_horde/" md_url: "https://freeinferencing.com/provider/ai_horde.md" last_updated: "2026-09-19" --- # AI Horde > Community-supplied inference across 26 models; capacity varies and throughput is not guaranteed. ## Classification - **Directory:** Current - **Free access:** Community capacity - **Status:** Available now - **Confidence:** High - **Payment card:** No - **Account:** Not required - **Equivalent paid value:** Not quantifiable - **API endpoint:** `https://aihorde.net/api/v2` ## Models mentioned - `aphrodite/SicariusSicariiStuff/Impish_LLAMA_4B` - `aphrodite/TheDrummer/Behemoth-X-123B-v2.1` - `aphrodite/TheDrummer/Behemoth-128B-v3-NVFP4` - `aphrodite/TheDrummer/Cydonia-24B-v4.3` - `aphrodite/TheDrummer/Skyfall-31B-v4.2` - `koboldcpp/Angelic_Eclipse-12B` - `koboldcpp/Judas-Uncensored-3.2-1B.Q8` - `koboldcpp/L3-8B-Stheno-v3.2-Q5_K_M` - `koboldcpp/gemma-4-31B-it-heretic` - `koboldcpp/gemma-4-E2B-it-qat-UD-Q4_K_XL.gguf` - `koboldcpp/Gemma-4-E4B-it-Ultra-Uncensored-Heretic` - `koboldcpp/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M` - `koboldcpp/L3-8B-Stheno-v3.2` - `koboldcpp/L3-8B-Stheno-v3.2-Q8_0` - `koboldcpp/Llama-3.2-1B-Instruct` - `koboldcpp/Llama-3.2-3B` - `koboldcpp/Llama-3.2-3B-Instruct-Q4_K_M` - `koboldcpp/Qwen2.5-1.5B` - `koboldcpp/Qwen3-4B-Nymphaea-RP.i1-Q4_K_S` - `koboldcpp/Qwen3.8-27B-Uncensored` - `koboldcpp/Qwen_Qwen3-0.6B-IQ4_XS` - `koboldcpp/Qwen/Qwen3.5-0.8B` - `koboldcpp/ReadyArt/Forgotten-Safeword-22B` - `koboldcpp/debug-L3-8B-Stheno-v3.2` - `koboldcpp/mini-magnum-12b-v1.1` - `meta-llama/Llama-3.2-3B-Instruct` ## Limits and terms ```yaml mechanism: Nonmonetary kudos and queue priority rather than a fixed request quota. anonymous_priority: lowest load_shedding: Anonymous use can be restricted during load. monetary_purchase: Kudos cannot be bought or sold. ``` ## What happens to your prompts? **Partially private.** The coordinator is transient, but volunteer workers can inspect or retain plaintext requests outside a uniform contractual control. Privacy is audited separately from price. Review the current governing terms before sending sensitive or regulated data. ## Data governance and agreements ```yaml data_governance: review_status: reviewed plan_scope: AI Horde's central queue plus independently operated volunteer workers for text and image generation. prompt_retention: The central Horde says prompts and generations are held transiently in memory and deleted shortly after delivery or cancellation. A worker operator can technically modify open-source worker software to view and save every prompt. response_retention: Same central transient retention, with no enforceable guarantee that a volunteer worker did not save its generated result. ordinary_logging: The service stores account identifiers and operational queue, kudos, request, worker, and safety data; the public FAQ does not publish a single retention schedule for all metadata. model_training: The central service says it does not store prompt or generation details, but there is no contractual mechanism preventing a volunteer worker from saving or reusing received content, including for training. product_improvement: No central content-based improvement program is disclosed; safety filters inspect requests and workers can independently modify their software. human_or_operator_access: Each selected worker receives the full prompt and generates the output. Official documentation explicitly says technically capable worker operators can spy on and save both. subprocessors_and_routing: Requests are distributed to community-run computers outside AI Horde's direct physical or contractual control; workers do not receive the requester's ID or IP but do receive content. deletion_controls: Central prompt and generation state is deleted shortly after completion or cancellation. No central deletion control can retract data a worker operator may have copied. caveat: Treat every request as if posting to a public forum. The coordinator's transient storage does not make an untrusted volunteer-compute network suitable for confidential or personal data. agreements: terms_of_service: https://aihorde.net/terms/ privacy_policy: https://aihorde.net/privacy ``` ## Eligibility ```yaml account_required: false payment_method_required: false ``` ## API compatibility and modalities - **Compatibility:** Native Asynchronous REST; Submit Text Generation Then Poll Status. Not OpenAI Compatible. - **Modalities:** Text generation ## Before you build with AI Horde ### Read the classification narrowly This record describes the bounded offer supported by evidence on 2026-09-19; it does not guarantee permanence, production suitability, uptime, latency, model quality, or access from every account and region. “Community capacity” should be interpreted together with the Current directory placement, High confidence, No payment-card status, and the plan-specific sources below. ### Resolve the live model route The snapshot records 26 model IDs. Match the exact ID against the provider's current catalog before using it in code because zero-price routes, aliases, context limits, and feature support can rotate while an older documentation page remains online. ### Match the quota to the workload shape Translate the allowance into peak requests per minute, input and output tokens, concurrency, retries, and every daily or monthly ceiling that applies to the intended account. The first limit reached by the workload is the practical ceiling. A large token pool can still fail interactive bursts, and a high request limit can still fail long-context work. Include tool calls and retry traffic, test the largest realistic payload, and treat research, experimental, and community access as conditional on their eligibility and fair-use terms. ### Preserve billing and privacy boundaries The recorded payment-card requirement is No, and account access is not required. Confirm both in the live signup flow, set provider-side budgets when charges are possible, and observe the balance or usage fields after a complete request. The prompt-handling classification is **Partially private** because The coordinator is transient, but volunteer workers can inspect or retain plaintext requests outside a uniform contractual control. Re-read the terms for the exact route and plan before sending sensitive, regulated, or proprietary content. ### Follow the evidence, then re-check it This record links 8 first-party sources covering the offer, catalog, limits, pricing, terms, privacy, or adoption evidence available to the audit. Prefer the newest and most specific governing document or live catalog when sources disagree. A dated finding can become stale even when the page remains online, so retain the source and snapshot that supported the decision and submit a correction when a provider changes a material term. ### Plan fallback without policy drift A fallback should preserve modality, context length, streaming, structured output, tools, safety controls, and data terms, not only API syntax. Decide which errors may retry, cap retry storms, and prevent an exhausted free route from silently switching to a billable model. Rotating aliases and free pools can change behavior without changing the endpoint, so retain the response model field and test at least one substitute route before the primary offer becomes unavailable. ### Monitor the offer as a dependency Capture the model ID, response model, rate-limit headers, usage fields, latency, HTTP status, and provider request identifier. Watch authorization failure, quota exhaustion, catalog removal, policy revision, and balance movement as separate failure modes. Re-check the live catalog and governing sources on a schedule proportionate to the workload's importance, and keep an owner and exit path for any production dependency on volatile free capacity. ### Test one complete request before scaling Start with the smallest permitted request using the exact credential, model ID, endpoint, region, and account type intended for deployment. Record the status, headers, usage fields, response model, latency, and dashboard balance movement. Then exercise an invalid model, quota exhaustion, or rate limit so failure is explicit and cannot silently switch to a paid route. Validate streaming, structured output, and tool calls separately because a free model can expose fewer features than its paid counterpart. Keep a budget ceiling outside the application whenever billing is possible, and do not send sensitive data until the observed route matches the reviewed agreement. ## Primary sources - [AI Horde](https://github.com/Haidra-Org/AI-Horde): Official Repository - [Integration guide](https://github.com/Haidra-Org/AI-Horde/blob/main/README_integration.md): Official Integration Docs - [Live text models](https://aihorde.net/api/v2/status/models?type=text): Live Catalog - [AI Horde Terms of Service](https://aihorde.net/terms/): Official Terms - [AI Horde Privacy Policy](https://aihorde.net/privacy): Official Privacy - [AI Horde FAQ](https://github.com/Haidra-Org/AI-Horde/blob/main/FAQ.md): Official Docs - [AI Horde public text-generation totals endpoint](https://aihorde.net/api/v2/stats/text/totals): Official Statistics - [PyPI download stats for horde\_sdk](https://pypistats.org/packages/horde_sdk): Package Registry Stats ## Sitemap See the full [semantic sitemap](/sitemap.md) for every page and markdown mirror.