Cartesia
A recurring no-cost API allowance covering 3 cataloged models.
https://api.cartesia.aiModels mentioned
sonic-3.6ink-2sonic-3.6-2026-08-27Equivalent paid value
How this was valued: The free plan's 20K shared credits are valued at the Pro plan's $5 per 100K-credit ratio. Sonic and Ink examples are alternative uses of the same balance, not additive allocations.
Limits and terms
- Plan Price USD Per Month
- 0
- Credits Per Month
- 20,000
- Approximate Tts Minutes Per Month
- 27
- Approximate Stt Hours Per Month
- 1.85
- Tts Concurrent Requests
- 2
- Stt Concurrent Requests
- 8
What happens to your prompts?
Default terms permit indefinite storage and perpetual use of inputs and outputs for labeling, improvement, promotion, and model training.
- Plan Scope
- Cartesia API and web services. Default consumer/developer terms differ from enterprise TTS and STT zero-data-retention arrangements.
- Prompt Retention
- Inputs and outputs may be hosted, cached, stored, reproduced, and used while stored to operate, improve, and promote the service. No default fixed retention period is published.
- Response Retention
- Outputs are covered by the same storage and use license. Enterprise ZDR can prevent retention for eligible TTS and STT payloads.
- Ordinary Logging
- Account, device, service activity, content, and safety or troubleshooting information is collected under the privacy policy.
- Model Training
- Unless otherwise agreed, Cartesia may use inputs, outputs, and interactions for labeling, classification, moderation, and model training under a perpetual license.
- Product Improvement
- Default terms expressly authorize service and model improvement and enhancement with Content.
- Human Or Operator Access
- Cartesia reserves the right to review or monitor inputs and outputs using automated and manual tools.
- Subprocessors And Routing
- Contracted service providers can receive content rights needed to operate the service; third-party services and enterprise subprocessors may separately process data.
- Deletion Controls
- Users can opt out of future training use, but the opt-out does not reverse prior uses or model improvements. Enterprise ZDR is available for eligible TTS and STT APIs.
- Caveat
- Free-tier content is training-eligible by default. The opt-out is prospective, and enterprise ZDR is neither available by default nor applicable to every product.
Governing documents
- Terms Of Service
- https://www.cartesia.ai/legal/terms
- Privacy Policy
- https://www.cartesia.ai/legal/privacy
- Acceptable Use Policy
- https://www.cartesia.ai/legal/acceptable-use
Eligibility
- Account Required
- Yes
- Payment Method Required
- not explicitly documented
- Commercial Use On Free Plan
- No
Primary sources
Before you build with Cartesia
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 3 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://api.cartesia.ai, 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”: Default terms permit indefinite storage and perpetual use of inputs and outputs for labeling, improvement, promotion, and model training. 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 9 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.