Google AI Studio / Gemini Developer API
A recurring no-cost API allowance covering 22 cataloged models.
https://generativelanguage.googleapis.comModels mentioned
gemini-3.8-flashgemini-3.7-flashgemini-3.6-flashgemini-3.5-flashgemini-3.5-flash-litegemini-3.1-flash-litegemini-2.5-flashgemini-2.5-flash-litegemini-3.5-live-translate-previewgemini-3.1-flash-live-previewgemini-3.1-flash-tts-previewgemini-2.5-flash-native-audio-preview-12-2025gemini-3.5-transcribe-livegemini-3.5-transcribegemini-3-flash-previewgemini-2.5-progemini-2.5-flash-preview-ttsgemini-embedding-2gemini-embedding-001gemini-robotics-er-2-previewgemini-robotics-er-2-streaming-previewgemini-robotics-er-1.6-previewEquivalent paid value
How this was valued: Modeled best-case rate-limit envelope for gemini-2.5-pro, a current free-tier model with a historical first-party numeric free-quota table. Google's current rate-limits page states quotas are project/dashboard-specific, so this uses the last captured official limits of 2 RPM, 125,000 input TPM, and 50 RPD. A request cannot exceed the 125,000 input-token minute bucket, so each of 50 daily requests uses at most 125,000 input plus the model's 65,536 maximum output. Because the prompt stays at or below 200K, current paid rates are $1.25/M input and $10/M output. Assumes uninterrupted saturation; other current free models without a captured numeric quota are excluded.
Partial because the RPM/TPM/RPD inputs are archived first-party values rather than a current public guarantee; the signed-in AI Studio dashboard governs and may be lower.
Limits and terms
- Dimensions
- requests per minutetokens per minuterequests per day
- Public Fixed Numbers
- Not documented
- Source Of Truth
- AI Studio project rate-limit dashboard
- Reset
- Daily request quotas reset at midnight Pacific time.
What happens to your prompts?
Unpaid-service inputs and outputs may be retained and used to improve and train Google models.
- Plan Scope
- Gemini Developer API and Google AI Studio unpaid quota; paid services and EEA, Switzerland, or UK treatment differ.
- Prompt Retention
- Unpaid-service content may be retained and used for product and model improvement. Abuse-monitoring data is retained for 55 days. Feature-specific storage includes grounding data for 30 days and optional or stateful logs with configurable retention.
- Response Retention
- Generated responses follow the same unpaid-service, abuse-monitoring, and feature-specific rules.
- Ordinary Logging
- Google may log prompts, context, and outputs for abuse monitoring. Paid-project user logs are optional except stateful features and default to a maximum 55-day retention.
- Model Training
- Unpaid-service inputs and outputs may be used to improve and train Google models. Paid-service content is not used for product improvement without permission; EEA, Swiss, and UK unpaid use receives the paid-service data treatment.
- Product Improvement
- Allowed for unpaid services outside the stated regional exception. Paid logging datasets can be voluntarily shared for improvement and training.
- Human Or Operator Access
- Authorized human reviewers may read, annotate, and process unpaid-service content and content flagged for abuse review; Google says identifiers are disconnected before improvement review.
- Subprocessors And Routing
- Google and its service infrastructure process content; grounding and other integrations introduce feature-specific handling under the additional terms.
- Deletion Controls
- Paid-project logs can use 7, 14, 28, or 55-day retention; datasets persist without a fixed period, files remain until deletion or expiry, and stateful features require explicit configuration for zero-retention behavior.
- Caveat
- The free tier has materially different data-use terms from the paid tier, and users are told not to submit sensitive, confidential, or personal information to unpaid services.
Governing documents
- Service Specific Terms
- https://ai.google.dev/gemini-api/terms
- Privacy Policy
- https://policies.google.com/privacy
- Prohibited Use Policy
- https://policies.google.com/terms/generative-ai/use-policy
Eligibility
- Account Required
- Yes
- Payment Method Required
- No
- Geographic Availability Applies
- Yes
- API Key Transition
- As of September 2026, use an AI Studio Auth key or a standard Google API key restricted to the Generative Language API; unrestricted standard keys are rejected.
Primary sources
Before you build with Google AI Studio / Gemini Developer API
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 22 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://generativelanguage.googleapis.com, 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”: Unpaid-service inputs and outputs may be retained and used to improve and train Google models. 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 14 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.