AI Tool Profile
Gemini API
Google’s developer inference API with separately priced models and tools.
Before you buy
Best for: Developers building creative applications who can pin the model, billing tier and project quota.
Price: US/USD: Flash 3.8 US$0.75 input / US$3.75 output per million tokens
Included: The current standard paid gemini-3.8-flash rate applies through December 31, 2026; the page also lists model-specific free, batch and other processing tiers.
Main limits: Announced January 2027 rates are higher. Caching, grounding, media, quota and data-use conditions are separate; a consumer plan is not an API balance.
What Kingy showed: The historical ChatLLM recording builds and interacts with a pixel-art app using Gemini 1.5 Pro. It does not test the native Gemini Developer API.
Buying details checked 2026-10-22 with region and currency stated above. Historical demonstrations and the broader fact ledger keep their own dates.
Check official plans · See the demonstration and disclosure · Compare these workflows
Coverage describes this profile, not a product score or a current price guarantee.
Kingy AI Product Facts
Gemini API
Current statusUnknown
- Company
- Primary job
- Not yet reviewed
- Audience
- Not yet reviewed
- API
- Available
- Evidence
- Source-backed; review due
- Latest source check
- October 23, 2026
See all tracked product factsPricing, platforms, dependencies, data claims, regions, and timeline
Sources and checks
- Coverage
- 13 of 87 tracked fields currently verified
- Sources
- 7
Source-check dates apply to the tracked facts. Editorial updates elsewhere on this page may have a different date.
Plans and pricing units
Not yet structured in this Kingy record.
Where it runs
- Availability
- Not yet reviewed
Developer access
- API access
- Available
Stack and integrations
- Model / provider dependencies
- Not yet reviewed
- Integrations
- Not yet reviewed
Data and regions
- Vendor data-use claim
- Not yet reviewed
- Vendor retention claim
- Not yet reviewed
- Regions
- Not yet reviewed
Launch and latest material update
- Launch
- Not yet reviewed
- Latest material update
- Not yet reviewed
Review history
- Gemini API — Verification refreshed
Kingy reconfirmed the published facts against the cited sources.
View published revision - Gemini API — Verification refreshed
Kingy reconfirmed the published facts against the cited sources.
View published revision - Gemini API — Verification refreshed
Kingy reconfirmed the published facts against the cited sources.
View published revision - Gemini API — Verification refreshed
Kingy reconfirmed the published facts against the cited sources.
View published revision - Gemini API — Verification refreshed
Kingy reconfirmed the published facts against the cited sources.
View published revision - Gemini API — Verification refreshed
Kingy reconfirmed the published facts against the cited sources.
View published revision - Gemini API — Verification refreshed
Kingy reconfirmed the published facts against the cited sources.
View published revision - Gemini API — Verification refreshed
Kingy reconfirmed the published facts against the cited sources.
View published revision
Which plan is worth considering
US/USD: Flash 3.8 US$0.75 input / US$3.75 output per million tokens. The current standard paid gemini-3.8-flash rate applies through December 31, 2026; the page also lists model-specific free, batch and other processing tiers. This is current API offer research plus a third-party historical model example. It establishes no native API latency, production reliability or current Flash result.
Limits that affect the purchase
Announced January 2027 rates are higher. Caching, grounding, media, quota and data-use conditions are separate; a consumer plan is not an API balance. Selected API models have a free tier with different data-use conditions and limits; free availability depends on the exact project and model. Use the exact model ID and project rate limits. Vertex AI contracts and third-party provider billing are outside this rate example.
What the existing demonstration shows
The historical ChatLLM recording builds and interacts with a pixel-art app using Gemini 1.5 Pro. It does not test the native Gemini Developer API. The retained recording was published 2024-09-24T20:14:20-07:00. Its public description and chapters support this account; no new transcript or frame audit, product test, purchase or benchmark was performed. Current offers are researched separately. Check the recording for the exact steps and commercial context. See the retained Kingy demonstration.
Sources and buying-review date
Buying details checked October 22, 2026. Plan research uses current official sources; demonstration descriptions use the retained Kingy record and any captured creator chapters. No new subscription, paid generation or checkout was performed. The buying-review date does not renew every claim in the broader facts ledger.
Check official plans · Compare related workflows
Earlier profile and dated source history
The earlier record below keeps its own dates and scope.
Kingy Product Passport · source-bound profile
Gemini API
Gemini API decisions require an exact model ID, a clear free-versus-paid data boundary and the active project’s current quota rather than an API-key assumption.
Decision snapshot
Gemini API decisions require an exact model ID, a clear free-versus-paid data boundary and the active project’s current quota rather than an API-key assumption.
Use this record when
Pin the model, billing tier and project before relying on availability, data-use or quota information.
Boundary
Gemini Developer API only; Gemini Apps, Vertex AI contracts, dashboard-specific quotas and hands-on reliability claims are excluded.
Pricing by model and processing mode
Rechecked September 21, 2026: This profile covers the Gemini Developer API. Its rates do not establish Vertex AI contract prices. Google’s pricing page separates free access to selected models from paid usage.
| Processing / tokens | Through Dec. 31, 2026 | From Jan. 1, 2027* |
|---|---|---|
| Standard input | $0.75 | $1.50 |
| Standard output | $3.75 | $7.50 |
| Batch input | $0.375 | $0.75 |
| Batch output | $1.875 | $3.75 |
*Google’s announced future rates, not current charges. Output pricing includes thinking tokens. Caching, storage, grounding and other processing modes have separate rates; this table is not a complete bill or a universal Gemini price. Recheck the exact model and billing mode before estimating cost.
This is a documentation review; Kingy made no API request or billing test. The earlier model, quota and historical-price records keep their original review scope.
Approved source-bound claims
models
Google publishes exact Gemini API model identifiers and labels them stable, preview, latest or experimental. Integrations must pin the intended identifier and must not turn a preview label into a durability claim.
Scope: Gemini API model catalog · Evidence: gemini-api-models
privacy
September 21, 2026 service-tier clarification: Google’s pricing page labels free-tier content as usable for product improvement and paid-tier content as excluded, but the Additional Terms define exceptions. In the EEA, Switzerland and UK, paid-service data rules also apply to unpaid quota. API access through a project with active billing is a Paid Service. AI Studio receives paid-service treatment when the account can access a project with active billing or is a Workspace enterprise account, even at no charge. Paid-service prompts and responses are not used to improve products; limited safety and abuse monitoring remains. Check the account, project and region rather than inferring data treatment from a zero-dollar charge.
Scope: Gemini Developer API free versus paid service tier · Evidence: gemini-api-pricing
limits
Gemini API rate limits apply per project rather than per API key, vary by model and tier, and require the active project dashboard for exact current quotas.
Scope: Gemini Developer API project limits · Evidence: gemini-api-rate-limits
Evidence gaps
- Exact authenticated quota and geography need project evidence.
- Preview models require same-day revalidation.
- No Kingy reliability, latency or output-quality test.
Official sources
- Gemini models — Google
- Gemini Developer API pricing — Google
- Gemini API rate limits — Google
- Gemini API Additional Terms — Google
Freshness and corrections
Source checked 2026-08-09. Kingy has not hands-on tested this product. Corrections are handled through the existing Kingy editorial process.
Verified model price histories
See Kingy’s AI model price stability ledger for the full editorial record and held-candidate boundary.
The Kingy Brief
Get The Kingy Brief.
AI changes, original tests and one practical thing to try. Fridays at 09:00 Vancouver time.
Free · Double opt-in · Unsubscribe anytime
Sign up for The Kingy Brief on Beehiiv.
Signup help and newsletter schedule
Signup form provided by Beehiiv. After submitting, check your inbox for "Confirm your subscription to The Kingy Brief" and open its confirmation link. Check Spam or Promotions if you cannot find it.
Fridays at 09:00 Vancouver time: source-checked AI changes, original tests and one practical thing to try. We skip a week when there is not enough verified material. Free. Unsubscribe anytime.
Alternatives
Tool Links
Related Kingy Links
Launch History
Gemini Robotics ER 1.6 deadline passed; service state unconfirmed
Google announced that gemini-robotics-er-1.6-preview will shut down on August 31, 2026, and its deprecation table names gemini-robotics-er-2-preview as the replacement.
Google's Gemini Robotics ER 1.6 shutdown date passed August 31; current service state unconfirmed. Treat the endpoint as unsupported, migrate to gemini-robotics-er-2-preview, and verify…
Google currently lists no Gemini 2.5 Pro shutdown date
Google currently lists no shutdown date or recommended replacement for the stable gemini-2.5-pro model. Kingy has withdrawn its earlier October 16 retirement claim.
Remove October 16 from plans that treated it as an official Gemini 2.5 Pro cutoff. Monitor Google’s deprecation table, and evaluate any voluntary model…
Gemini changes sampling and turn-validation rules for new models
Google deprecated temperature, top_p and top_k for Gemini 3.6 Flash, Gemini 3.5 Flash-Lite and later Gemini models. The named models ignore those parameters; future generations will return HTTP…
Google’s July 21 announcement deprecated sampling parameters for the new models released then. The moving latest-model guide now covers Gemini 3.8 Flash and its…
Google Imagen 4 API shutdown date passed on August 17, 2026
Google announced that imagen-4.0-generate-001, imagen-4.0-ultra-generate-001 and imagen-4.0-fast-generate-001 are deprecated. Its deprecations table lists August 17, 2026 as the earliest possible shutdown date and recommends gemini-nano-banana-2.1.
Google’s current lifecycle table retains August 17, 2026 as the shutdown date for three Imagen 4 API model IDs and now recommends gemini-nano-banana-2.1. Preserve…
Updated Gemini 2.5 Pro for coding and web apps
Google released early access to an updated Gemini 2.5 Pro Preview focused on coding and building rich interactive web apps.
Important for tracking the AI coding race because this update targeted web app generation directly.
Kingy coverage
Kingy AI articles about Gemini API, newest first.