--- title: "Lucidity Composite free inference" description: "A recurring no-cost API allowance covering 28 cataloged models." canonical_url: "https://freeinferencing.com/provider/lucidity_composite/" md_url: "https://freeinferencing.com/provider/lucidity_composite.md" last_updated: "2026-09-19" --- # Lucidity Composite > A recurring no-cost API allowance covering 28 cataloged models. ## Classification - **Directory:** Current - **Free access:** Always-free quota - **Status:** Available now - **Confidence:** Medium High - **Payment card:** No - **Account:** Required - **Equivalent paid value:** Not quantifiable - **API endpoint:** `https://composite.lucidity.sh/v1` ## Models mentioned - `lucidityai/synth-2.5-flash:free` - `lucidityai/synth-2.5-pro:free` - `inclusionai/ling-3.0-flash:free` - `mistralai/mistral-nemo:free` - `open/deepseek-ai/deepseek-v4-flash-0731:free` - `open/moonshotai/kimi-k2.6:free` - `open/stepfun-ai/step-3.7-flash:free` - `open/thinkingmachines/inkling:free` - `open/google/diffusiongemma-26b-a4b-it:free` - `open/mistralai/mixtral-8x22b-v0.1:free` - `open/nvidia/nemotron-3-super-120b-a12b:free` - `open/nvidia/nemotron-3-ultra-550b-a55b:free` - `open/meta/llama-3.3-70b-instruct:free` - `open/google/gemma-4-31b-it:free` - `open/openai/gpt-oss-120b:free` - `open/ibm/granite-34b-code-instruct:free` - `open/deepseek-ai/deepseek-v4-flash-0731` - `open/moonshotai/kimi-k2.6` - `open/stepfun-ai/step-3.7-flash` - `open/thinkingmachines/inkling` - `open/google/diffusiongemma-26b-a4b-it` - `open/mistralai/mixtral-8x22b-v0.1` - `open/nvidia/nemotron-3-super-120b-a12b` - `open/nvidia/nemotron-3-ultra-550b-a55b` - `open/meta/llama-3.3-70b-instruct` - `open/google/gemma-4-31b-it` - `open/openai/gpt-oss-120b` - `open/ibm/granite-34b-code-instruct` ## Limits and terms ```yaml free_requests_per_day: not_public reset: daily paid_plan_free_request_increments: micro: 250 per day basic: 500 per day plus_and_higher: unlimited caveat: The ordinary Free account's numeric daily allowance is not published. ``` ## What happens to your prompts? **Not private.** Composite collects prompts and responses for model training by default, retains separately logged and moderation-flagged content without a fixed automatic deletion schedule, and routes content to OpenRouter or custom providers. 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: Lucidity Composite Free and paid plans, including Lucidity-hosted models and routes forwarded to OpenRouter or a configured custom endpoint. prompt_retention: Full prompts are collected for model training by default. Account-level training opt-out is prospective; diagnostic logging can separately store identified prompt content for a selected key, and moderation-flagged conversations may be retained even when training collection is disabled. response_retention: Full responses follow the same default training collection, key-level diagnostic logging, moderation, and prospective opt-out rules as prompts. ordinary_logging: Lucidity processes account, API-key, usage, rate-limit, IP, payment, error, and routing records. Provider errors and separately enabled key logging can associate content with the account or key. model_training: Prompt and response content is eligible for training by default unless the user disables training collection for the account; disabling it does not delete content collected earlier. product_improvement: The terms license submitted content for operating and improving the service, and the privacy policy describes default collection for training and service improvement. human_or_operator_access: Administrators may access account, usage, payment, error, diagnostic-log, and moderation-flagged records for operations, enforcement, support, and improvement. subprocessors_and_routing: Non-LucidityAI routes are generally forwarded to OpenRouter, LucidityAI routes use Lucidity infrastructure, and a user can select a custom endpoint; those upstreams receive the plaintext required to perform inference. deletion_controls: Account deletion removes the user record, cascaded API keys, and ordinary associated prompt records, but operational, diagnostic, moderation-flagged, training, payment, and backup records may remain where described or required. No fixed universal retention or automatic deletion schedule is published, and users may contact Lucidity for privacy requests. caveat: Training collection is on by default, opt-outs are prospective, diagnostic and moderation stores are separate, upstream processors receive content, and no fixed universal retention period is promised; classify not_private. ``` ## Eligibility ```yaml account_required: true payment_method_required: false discord_verification: conflicting_first_party_claims discord_conflict: The same current landing page alternately says Discord verification unlocks the free tier and that no Discord account is required. ``` ## API compatibility and modalities - **Compatibility:** OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, Gemini Generate Content, Mari - **Modalities:** Text generation ## Before you build with Lucidity Composite ### 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. “Always-free quota” should be interpreted together with the Current directory placement, Medium High confidence, No payment-card status, and the plan-specific sources below. ### Resolve the live model route The snapshot records 28 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 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 **Not private** because Composite collects prompts and responses for model training by default, retains separately logged and moderation-flagged content without a fixed automatic deletion schedule, and routes content to OpenRouter or custom providers. 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 - [Composite](https://composite.lucidity.sh/): Official Product - [Composite API documentation](https://composite.lucidity.sh/docs/): Official Docs - [Plans and credits](https://composite.lucidity.sh/plans.html): Official Pricing - [Models API](https://composite.lucidity.sh/v1/models): Live Catalog - [Models](https://composite.lucidity.sh/models.html): Official Catalog - [Terms of Service](https://lucidity.sh/terms.html): Official Terms - [Privacy Policy](https://lucidity.sh/privacy.html): Official Privacy - [Lucidity Composite statistics](https://composite.lucidity.sh/stats.html): Official Statistics ## Sitemap See the full [semantic sitemap](/sitemap.md) for every page and markdown mirror.