Gemini 3.5 Pro

GoogleText GenerationNo verified public API

No Callable RouteModel ID UnpublishedPricing UnpublishedLaunch Alerts Open

Google Product Status

Coming soon; testing with partners

Public API Status

Not listed in the Gemini API catalog

EvoLink Access Status

No verified callable route; launch alert open

Last Verified

August 12, 2026

Is the Gemini 3.5 Pro API Actually Live?

Google lists Gemini 3.5 Pro as coming soon and says it is testing with partners. As of August 12, 2026, the public Gemini API catalog, pricing page, and release notes still do not provide a callable model ID, price, specification, or public access path. Use this page to track verified access and prepare a reversible EvoLink evaluation without guessing the API contract.

How We Verify Gemini 3.5 Pro API Availability

The status is based on first-party Google records checked on August 12, 2026, not a predicted release date or a community model label.

Not Publicly Listed

Google Developer Channels

Google's public model catalog, pricing page, and API release notes do not list Gemini 3.5 Pro, a request model ID, commercial terms, or a public access program.

No Verified Route

EvoLink API

EvoLink has no verified callable Gemini 3.5 Pro route. Use a listed current Gemini route and keep the future candidate unset until request success, returned identity, usage accounting, and billing are verified.

Google DeepMind Model Family

Displays “3.5 Pro coming soon” but does not provide a public API contract or launch date.

Gemini API Model Catalog

Lists current Gemini API endpoints but no Gemini 3.5 Pro model code or callable route.

Pricing and Release Notes

Google publishes no Gemini 3.5 Pro pricing row or API release-note entry.

This page changes from launch watch to live access only after Google publishes the API contract and EvoLink verifies a successful authenticated request, returned identity, usage, and billing.

Coming soon · Partner testing

Get the Gemini 3.5 Pro API Launch Alert

We will email you after Google publishes a developer API path and EvoLink verifies the route, returned model identity, usage, pricing, and production behavior.

Join the Gemini 3.5 Pro API alert

EvoLink product alerts only. This is not Google Early Access or an access guarantee.

Want faster updates? Join the EvoLink Discord

What the Launch Update Will Include

The update will include the verified request model ID, live EvoLink pricing, supported inputs and parameters, access limits, and a migration path that retains a current Gemini fallback.

What Can You Prepare Before Gemini 3.5 Pro Launches?

Prepare evidence, configuration, and rollback paths now so launch-day work is validation instead of a provider-specific rewrite.

Keep the Candidate Model ID in Configuration

Do not hard-code gemini-3.5-pro. Leave the candidate unset until EvoLink verifies a successful request and returned model identity.

Save Representative Evaluation Traces

Collect real coding, agent, document, multimodal, tool, and structured-output tasks with objective acceptance criteria.

Freeze Current Gemini Baselines

Record quality, latency, tool errors, token use, retries, review effort, and accepted-task cost for Gemini 3.5 Flash and 3.1 Pro.

Define Promotion Gates

Set thresholds for task success, p95 latency, total cost, incidents, policy behavior, human correction, and rollback.

Log the Full Compatibility Surface

Capture requested and returned model, parameters, inputs, tools, usage, finish reason, safety blocks, fallback chain, and billing.

Use Offline, Shadow, Canary, and Rollback Stages

Keep a measured current route serving users until the candidate proves a workload-specific improvement under controlled traffic.

What Are the Expected Gemini 3.5 Pro Characteristics?

Google confirms the model is coming, but it has not published a model card, API capability table, pricing, or benchmark set for Gemini 3.5 Pro. These are evaluation targets, not specifications.

No public Gemini 3.5 Pro API characteristic is confirmed beyond its status as an upcoming Pro model in partner testing. The useful question is whether a released route creates a measurable advantage over current Pro and Flash baselines.

User need, not a claim

A Clear Quality Gain Above Current Gemini Routes

Developers want a Pro-tier candidate that justifies higher latency or cost on difficult coding, reasoning, and knowledge work. The Pro name alone does not prove that gain.

Launch check: Replay hard repository, research, planning, and multimodal tasks with identical tools, prompts, and acceptance rubrics.

User need, not a claim

Reliable Long-Horizon Agent Behavior

Teams care about complete traces, valid tool calls, recovery, checkpoint integrity, and low reviewer intervention—not only one-shot benchmark scores.

Launch check: Measure whole-task completion, loops, failed actions, recovery, context loss, human corrections, and time to acceptance.

User need, not a claim

Better Cost per Accepted Task

A higher-capability route is valuable only when tokens, retries, latency, fallbacks, and review effort produce better economics for accepted work.

Launch check: Compare total model, tool, retry, fallback, and review cost per accepted result against Gemini 3.5 Flash and 3.1 Pro.

User need, not a claim

Predictable Compatibility and Rollout

Production adoption needs stable identity, inputs, tools, quotas, error behavior, usage records, and rollback—not a consumer-product announcement alone.

Launch check: Audit requested versus returned model, parameter errors, tool schemas, usage, billing, regions, quotas, and fallback behavior.

Gemini 3.5 Pro API Launch Checklist from Current Gemini Baselines

Use the documented Gemini 3.1 Pro and Gemini 3.5 Flash behavior to prepare checks without presenting predecessor or sibling specifications as Gemini 3.5 Pro promises.

Current Gemini 3.5 Pro answer: public model ID, pricing, limits, input contract, and EvoLink route remain unknown or unverified.

Field	Documented current Gemini reference	Verify for Gemini 3.5 Pro
Model ID	gemini-3.1-pro-preview and gemini-3.5-flash are documented endpoints	Exact Pro ID, release stage, snapshot behavior, and returned identity
Standard token price	Gemini 3.1 Pro Preview and 3.5 Flash have separate published prices	Official Pro rates and live EvoLink route pricing; never inherit either baseline
Batch, flex, priority, and caching	Support and rates vary by current Gemini endpoint and prompt size	Eligible service tiers, cache rules, storage price, and route billing
Context and output	Current 3.1 Pro and 3.5 Flash docs list 1,048,576 input and 65,536 output tokens	Pro limits, useful-context behavior, truncation, and long-context pricing
Inputs and tools	Current endpoints document multimodal inputs, thinking, tools, grounding, and structured output	Supported inputs, function schema, grounding, code execution, streaming, and errors
Quotas and data terms	Limits and data-use rules vary by tier, account, and Google channel	RPS, TPM, concurrency, regions, preview terms, retention, and 429 behavior
EvoLink route	Keep a measured current Gemini route as the fallback	Request success, returned identity, usage, capacity, billing, and rollback

Main Gemini 3.5 Pro API Parameters and Compatibility

These are the request fields teams should prepare and re-test. Current Gemini behavior is a compatibility baseline, not a Gemini 3.5 Pro specification.

Gemini 3.5 Pro parameter support is unknown. Keep the candidate model ID unset until a public API contract and verified EvoLink route exist.

Parameter or field	Current Gemini behavior	Gemini 3.5 Pro launch-day check
model	Current endpoints use documented model codes	Exact ID, release stage, aliases, and returned identity
contents	Gemini content and part objects	Roles, text, image, audio, video, PDF parts, and validation
systemInstruction	Supported by current Gemini generation endpoints	Format, precedence, token accounting, and limits
maxOutputTokens	GenerationConfig output ceiling	Maximum, defaults, truncation, and billing
temperature / topP / topK	Sampling controls vary by model and task	Accepted ranges, defaults, interactions, and errors
thinkingConfig	Thinking controls are documented for current Gemini 3 models	Supported controls, defaults, token visibility, quality, latency, and cost
tools / toolConfig	Function calling and selected built-in tools are model dependent	Schema subset, tool choice, parallel calls, and built-in tool support
responseMimeType / responseSchema	Structured output is supported on documented current routes	JSON Schema support, validation, finish reasons, and compatibility
cachedContent	Context caching is endpoint and tier dependent	Eligibility, TTL, cache identity, hit accounting, and billing
safetySettings	Request safety settings use documented harm categories	Supported categories, thresholds, blocks, and finish reasons
streamGenerateContent	Streaming is available on compatible Gemini generation routes	Chunk order, usage delivery, tool events, errors, and cancellation
usageMetadata / finishReason	Responses expose token usage and completion state	Field shape, thinking/cache accounting, blocks, and invoice reconciliation
Limits and regions	Account, service tier, channel, and region dependent	Context, output, RPS, TPM, concurrency, residency, and 429s

Pre-Launch Routing Configuration Example

Keep the candidate unset until EvoLink verifies a successful request and returned model identity. This configuration-only example does not send an API request.

const activeModel = process.env.EVOLINK_PRIMARY_MODEL
const fallbackModel = process.env.EVOLINK_FALLBACK_MODEL
const gemini35ProCandidate = process.env.EVOLINK_GEMINI_35_PRO_MODEL || null

// Keep the candidate unset until EvoLink verifies a callable route and returned identity.
export const modelRouting = {
  activeModel,
  fallbackModel,
  gemini35ProCandidate,
}

Why Use EvoLink to Prepare for Gemini 3.5 Pro?

Google develops Gemini; EvoLink's role is to make verified model access easier to compare, operate, switch, and roll back after a route is genuinely callable.

One Unified API Contract

Keep one integration, key, billing surface, and observability path while model selection changes through configuration.

Verified Route Identity and Cost

Publish access only after request success, returned identity, usage, pricing, and billing are validated.

Staged Switching with Fallback

Evaluate the candidate offline and in canary traffic while retaining a current Gemini route as the measured rollback.

Compare current Gemini models Join the Gemini 3.5 Pro API alert

Related Gemini Model Listings to Review on EvoLink

Review provider-documented current models and verify each EvoLink route before production. Compare Gemini 3.5 Pro only after identity, request, usage, and billing verification.

View all Gemini models

Gemini 3.5 Flash

Listed

The documented stable Gemini 3.5 route for agentic, coding, and multimodal evaluations. Verify the EvoLink route before production.

View model

Gemini 3.1 Pro

Listed

The documented current Pro-family baseline for complex reasoning, coding, tools, and multimodal work. Verify the EvoLink route before production.

View model

Gemini Model Family

Compare

Compare current Gemini listings by model access, price, context, production role, and workload fit.

View model

Research Gemini 3.5 Pro Before You Integrate

Use the release tracker for time-sensitive evidence and the comparison guides for current model decisions.

Gemini 3.5 Pro release date

Track what Google confirmed, the missed timing signal, public API gates, and the evidence that would change the status.

Gemini 3.5 Pro vs Gemini 3.5 Flash

Use the available Flash route now and define the matched tests a future Pro route must pass.

Gemini 3.5 Pro vs GPT-5.6

Separate the available cross-provider option from the pending Gemini route and plan a reversible evaluation.

Gemini 3.5 Pro API FAQ

Has Google officially announced Gemini 3.5 Pro?

Yes. Google DeepMind lists Gemini 3.5 Pro as coming soon, and Google says the model is testing with partners.

When will Gemini 3.5 Pro be released?

Google has not published a current release date. An earlier next-month expectation passed; the current official wording is that broader availability will come when the model is ready.

Is Gemini 3.5 Pro publicly available in the Gemini API?

No verified public API listing exists as of August 12, 2026. It is absent from Google's public model catalog, pricing page, and API release notes.

What is the Gemini 3.5 Pro API model ID?

No public request model ID is confirmed. gemini-3.5-pro is a page slug and an identifier you must not assume is callable.

How much will the Gemini 3.5 Pro API cost?

Pricing is unknown. Current Gemini 3.1 Pro and 3.5 Flash prices are baselines only, not a forecast for the unreleased Pro route.

Does Gemini 3.5 Pro have a 2M-token context window?

Google has not published a Gemini 3.5 Pro API context limit. Do not treat third-party 2M-context claims as a confirmed specification.

Will Gemini 3.5 Pro include Deep Think?

That is unconfirmed for the public API. Google has not published a Gemini 3.5 Pro capability table or model card.

Is partner testing the same as public Early Access?

No. Google has not published a public signup, eligibility policy, preview endpoint, or access guarantee for Gemini 3.5 Pro.

Is Gemini 3.5 Pro available through EvoLink?

No verified callable route is available. EvoLink will change the status only after a successful authenticated request, returned model identity, usage, pricing, and billing are verified.

Which Gemini model should I use now?

Review Gemini 3.5 Flash for a current stable 3.5 route or Gemini 3.1 Pro for a current Pro-family baseline, then verify the listed EvoLink route before production.

Should I wait for Gemini 3.5 Pro before building?

No. Keep model selection configurable, evaluate current routes, save representative traces, and maintain a measured fallback.

What should I verify before production?

Verify the official model ID, price, inputs, context and output limits, tools, thinking controls, streaming, quotas, regions, request success, returned identity, usage, and billing.