Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Google / Gemini

Gemini 3 Flash preview

Multimodal language model offered through the Gemini API.

Language models (LLMs)
previewClosed weightsText generationCodingDocument analysisReasoningAgents
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
22 of 28 specification fields collected
Input token limit1.05M1,048,576 tokens
Maximum output65.5K65,536 tokens
Input / 1M tokens$0.50Google Gemini API
Output / 1M tokens$3.00USD · observed 12 Oct 2026

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Input token limit
1,048,576 tokensSource for Input token limit (opens in a new tab)

Provider input-token limit.

Maximum output
65,536 tokensSource for Maximum output (opens in a new tab)
Input modalities
Text, Image, Video, Audio, PDFSource for Input modalities (opens in a new tab)

Text, Image, Video, Audio, and PDF

Output modalities
TextSource for Output modalities (opens in a new tab)

Text

Reasoning
SupportedSource for Reasoning (opens in a new tab)

Supported

Tool calling
SupportedSource for Tool calling (opens in a new tab)

Supported

Structured output
SupportedSource for Structured output (opens in a new tab)

Supported

Streaming
Not collected
Batch processing
SupportedSource for Batch processing (opens in a new tab)

Supported

Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
2025-12-17Source for Release date (opens in a new tab)
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Audio generation
Not supportedSource for Audio generation (opens in a new tab)

Not supported

Context caching
SupportedSource for Context caching (opens in a new tab)

Documented on at least one recorded endpoint. See Caching for host, lifecycle and billing restrictions.

Code execution
SupportedSource for Code execution (opens in a new tab)

Supported

Computer use
SupportedSource for Computer use (opens in a new tab)

Supported

File search
SupportedSource for File search (opens in a new tab)

Supported

Google Maps grounding
SupportedSource for Google Maps grounding (opens in a new tab)

Supported

Image generation
Not supportedSource for Image generation (opens in a new tab)

Not supported

Live API
Not supportedSource for Live API (opens in a new tab)

Not supported

Search grounding
SupportedSource for Search grounding (opens in a new tab)

Supported

URL context
SupportedSource for URL context (opens in a new tab)

Supported

Flex inference
SupportedSource for Flex inference (opens in a new tab)

Supported

Priority inference
SupportedSource for Priority inference (opens in a new tab)

Supported

Model card updated
December 2025Source for Model card updated (opens in a new tab)

Card update month, not a release date.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Google Gemini API

Provider source (opens in a new tab)
API model ID
gemini-3-flash-preview
Access
Google AI Studio / Gemini API account; region, tier and quota restrictions apply.
Regions
See Google supported-region and account requirements; region-specific availability not yet collected.
INPUT / 1M TOKENS$0.50
OUTPUT / 1M TOKENS$3.00

Standard paid-tier text rates; output includes thinking tokens. Audio input, storage and tool charges may differ; see usage rates and the source. Cached input price: $0.05 / 1M tokens (base tier).

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Audio tokensInput1$1.001M audio tokens
Audio tokensCached input2$0.101M audio tokens
Explicit cacheCache storage3$1.001M tokens / hour
Audio tokensCached input4$0.101M audio tokens

Rate conditions

  1. Standard paid-tier audio input; not the text-input rate.
  2. Cached audio input; storage charged separately.
  3. GenerateContent explicit cache storage, standard paid tier. Retention duration multiplies storage cost. This is additional to generation and cache-read charges.
  4. Standard paid-tier cached audio input. Text/image/video cached rates differ. Storage and output are separate.
Pricing source (opens in a new tab)Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Perplexity Agent API · default

Provider source (opens in a new tab)
API model ID
google/gemini-3-flash-preview
Access
Perplexity API key; POST https://api.perplexity.ai/v1/agent (compatibility alias: /v1/responses). Set service_tier=default. auto or an omitted tier also selects default processing.
Regions
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Context caching
SupportedSource for Context caching (opens in a new tab)
Service tier
defaultSource for Service tier (opens in a new tab)
INPUT / 1M TOKENS$0.50
OUTPUT / 1M TOKENS$3.00

Perplexity Agent API default processing; USD per million tokens. Tool calls are charged separately when used. Rates are host-specific, not the model developer’s direct-API prices. Unknown cache-write charges are not treated as zero. Cached input price: $0.05 / 1M tokens (base tier).

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Tool add-onWeb search1$0.0025invocation
Tool add-onFast search2$0.001invocation
Tool add-onImage search3$0.0025successful invocation
Tool add-onURL fetch4$0.0005invocation
Tool add-onPeople search5$0.005invocation
Tool add-onFinance search6$0.005invocation
Tool add-onCode sandbox7$0.03container session
Tool add-onSearch inside sandbox8$0.0025SDK search request

Rate conditions

  1. Standard web search. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  2. web_search with search_type=fast. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  3. Image search bills successful invocations. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  4. Fetch and extract URL content. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  5. People search tool. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  6. Financial search tool. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  7. Up to 20 minutes of active use per billing window; this is not a runtime cap. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  8. Additional SDK search calls made inside a sandbox. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Google Gemini API

gemini-3-flash-preview
Documented

Documented on at least one recorded endpoint. See Caching for host, lifecycle and billing restrictions.

Support evidence (opens in a new tab)
How it works
Implicit caching; explicit cache objects on eligible GenerateContent calls.Source for How it works (opens in a new tab)
Minimum reusable input
Not collected
Lifetime & refresh
Explicit objects default to 1 hour; set ttl or expire_time, update or delete the object. The implicit cache lifetime is not specified in this guide.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Interactions supports implicit caching only. For explicit caching, create a cache with the GenerateContent API and pass its name as cached_content.Source for How to enable it (opens in a new tab)
Usage fields
Interactions: usage.total_cached_tokens. GenerateContent: usage_metadata reports cached tokens.Source for Usage fields (opens in a new tab)
Billing rules
Reads use the cached-input rate. Explicit cache storage is billed per million tokens per hour, in addition to generation. Free-tier eligibility and audio rates vary by model.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Cached content is a prompt prefix and counts toward the input limit. Implicit hits are not guaranteed. Explicit caching uses GenerateContent v1beta; API and model eligibility must match.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.05 / 1M tokensPricing evidence (opens in a new tab)
Cached input2Audio tokens$0.10 / 1M audio tokensPricing evidence (opens in a new tab)
Cache storage3Explicit cache$1.00 / 1M tokens / hourPricing evidence (opens in a new tab)
Cached input4Audio tokens$0.10 / 1M audio tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Standard paid-tier text rates; output includes thinking tokens. Audio input, storage and tool charges may differ; see usage rates and the source.
  2. Cached audio input; storage charged separately.
  3. GenerateContent explicit cache storage, standard paid tier. Retention duration multiplies storage cost. This is additional to generation and cache-read charges.
  4. Standard paid-tier cached audio input. Text/image/video cached rates differ. Storage and output are separate.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Perplexity Agent API · default

google/gemini-3-flash-preview
Documented
Support evidence (opens in a new tab)
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected

Do not inherit the model developer’s direct-API retention policy onto the Perplexity endpoint.

How to enable it
Not collected
Usage fields
Not collected
Billing rules
Published discounted cache-read rates apply to this default service tier. Write charges, minimum cacheable input, retention and cache controls have not been verified for this host.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Not collected
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.05 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Perplexity Agent API default processing; USD per million tokens. Tool calls are charged separately when used. Rates are host-specific, not the model developer’s direct-API prices. Unknown cache-write charges are not treated as zero.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Google-documented proprietary hosted release in the Gemini API model catalog. No public weights identified for this release in the reviewed documentation; public-weight Gemma models are excluded.

Classification evidence (opens in a new tab)

Lifecycle dates

Gemini API release17 Dec 2025Source (opens in a new tab)

Sources reviewed