Lucidity Composite
Operated by Lucidity.sh
A recurring no-cost API allowance covering 28 cataloged models.
https://composite.lucidity.sh/v1Models mentioned
lucidityai/synth-2.5-flash:freelucidityai/synth-2.5-pro:freeinclusionai/ling-3.0-flash:freemistralai/mistral-nemo:freeopen/deepseek-ai/deepseek-v4-flash-0731:freeopen/moonshotai/kimi-k2.6:freeopen/stepfun-ai/step-3.7-flash:freeopen/thinkingmachines/inkling:freeopen/google/diffusiongemma-26b-a4b-it:freeopen/mistralai/mixtral-8x22b-v0.1:freeopen/nvidia/nemotron-3-super-120b-a12b:freeopen/nvidia/nemotron-3-ultra-550b-a55b:freeopen/meta/llama-3.3-70b-instruct:freeopen/google/gemma-4-31b-it:freeopen/openai/gpt-oss-120b:freeopen/ibm/granite-34b-code-instruct:freeopen/deepseek-ai/deepseek-v4-flash-0731open/moonshotai/kimi-k2.6open/stepfun-ai/step-3.7-flashopen/thinkingmachines/inklingopen/google/diffusiongemma-26b-a4b-itopen/mistralai/mixtral-8x22b-v0.1open/nvidia/nemotron-3-super-120b-a12bopen/nvidia/nemotron-3-ultra-550b-a55bopen/meta/llama-3.3-70b-instructopen/google/gemma-4-31b-itopen/openai/gpt-oss-120bopen/ibm/granite-34b-code-instructEquivalent paid value
How this was valued: The published allowance or a defensible paid comparison is not precise enough to calculate.
Every account receives a recurring daily free-model request allowance, but the ordinary Free account's numeric requests per day are not published, the live catalog mixes zero and positive pricing metadata under :free aliases, and no stable finite request envelope supports a defensible paid-value calculation.
Limits and terms
- 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?
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.
- 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
- Account Required
- Yes
- Payment Method Required
- No
- 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.
Primary sources
Before you build with Lucidity Composite
Read the classification narrowly
This record has current first-party evidence for some zero-cost hosted inference. The label 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 region.
Resolve the live model route
This snapshot records 28 model IDs. Match the exact ID against the provider's live catalog before using it in code; zero-price routes and aliases can rotate while an older documentation page remains online. The recorded base endpoint is https://composite.lucidity.sh/v1, but the provider's current API reference remains authoritative for paths, authentication, and request shape.
Confirm account and billing boundaries
An account is required, so public catalog evidence cannot by itself prove the limits, balance, or billing behavior attached to your workspace. The reviewed evidence explicitly says no payment card is required. Re-check the signup flow because eligibility and billing controls can change after the snapshot. The equivalent paid value shown here prices a documented allowance where possible; it is not cash, guaranteed savings, or protection from overage.
Re-read the prompt policy for your plan
This record classifies the reviewed handling as “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. Provider policies can distinguish free, paid, enterprise, opted-in, and feature-specific traffic, so verify the governing terms for the exact account and route that will receive your data.
Follow the evidence, then re-check it
The record links 8 first-party sources covering the offer, catalog, limits, pricing, terms, privacy, or adoption evidence available to the audit. Prefer the newest governing document or live catalog when sources disagree, and submit a correction when a provider changes a material term.
Match the quota to the workload shape
Translate the published allowance into the traffic pattern you actually expect instead of comparing headline totals alone. A daily token pool can look generous while a low requests-per-minute or concurrency ceiling blocks interactive bursts; a high request limit can still fail a long-context job when input, output, or per-request tokens are capped. Separate prompt tokens from generated tokens, include retries and tool calls, and test the largest realistic payload. If the provider documents more than one limit window, the tightest window at your peak load is the practical ceiling. Research, experimental, and community access can also carry eligibility or fair-use constraints that cannot be modeled as a simple number.
Plan fallback without changing the rules
A fallback should preserve more than API syntax. Confirm that the substitute route supports the required modality, context length, streaming behavior, structured output, tools, and safety controls, then compare its prompt-retention and training terms. An OpenAI-compatible request shape does not make providers operationally or contractually equivalent. Decide which errors may trigger a retry, cap retry storms, and prevent an exhausted free route from silently switching to a billable model. If deterministic output matters, record the model revision and sampling settings; rotating aliases and free-model pools can change behavior even when the endpoint remains available.
Monitor the offer as a dependency
Capture the model ID, response model field, rate-limit headers, usage fields, latency, HTTP status, and any provider request identifier for each test. Watch for authorization failures, quota exhaustion, catalog removal, policy revisions, and dashboard balance changes as separate failure modes. Re-check the provider’s live catalog and governing pages on a schedule proportionate to the workload’s importance, and keep the dated sources that supported your decision. Free capacity is especially suitable for prototypes, evaluations, fallbacks, and bounded workloads when the application can tolerate change; a production dependency still needs observability, an exit path, and an owner responsible for re-verification.
Test one complete request before scaling
Start with the smallest permitted request using the exact credential, model ID, endpoint, and account type you intend to deploy. Record the HTTP status, response headers, usage fields, latency, and any dashboard balance change. Then exercise the failure path: an invalid model, an exhausted quota, or a rate-limit response should fail clearly without silently switching to a paid route. If the provider supports streaming or tool calls, validate those features separately because a free model can expose a narrower capability set than its paid counterpart. Keep a budget ceiling outside the application whenever billing is possible, and avoid sending sensitive data until the observed route matches the reviewed data agreement.