Google Gemini Developer API

Google Gemini Developer API supplies hosted language models with token-based billing. The calculator keeps model rates and limits in a versioned pricing snapshot.

Categories
LLM
Models and endpoints
3
Guide reviewed
Sep 24, 2026

Models, translated into money

Choose a budget and compare what each model delivers. Every estimate includes its assumptions and pricing sources.

TaskBudget · USD
Compare3 models
Task
Budget USD

Gemini 3.5 Flash-Lite

Google

Expired

Pricing is unavailable for this model.

Where it fits

Based on independent evidence
ChatGood fit

Conversation quality and instruction following.

SupportGood fit

Instruction following and multi-turn conversations.

CodingLimited fit

Coding tasks and web development. Compare alternatives.

DocumentsGood fit

Long queries and document work.

ResearchNo data

Not enough current evidence to assess this task.

How we calculated thisPricing unavailable
Typical chat assumption2,000 input · 500 output tokens per request

Official pricing

google-gemini-3-5-flash-lite-standard · Current · Standard billing

Standard text
$0.30 input · $2.50 output / 1M tokens

Verified Sep 26, 2026

Model details

Model ID
gemini-3.5-flash-lite
Tool calling
true
Structured output
true
context Window
1,048,576
max Output Tokens
65,536
modality
text
processing Tier
standard
thinking Tokens Included
Yes

Task evidence

General chat: 84 / 100 · good fit

Support chat: 84 / 100 · good fit

Coding help: 67 / 100 · limited fit

Document work: 82 / 100 · good fit

Research agent: No current score

Catalog 2026-10-08-7b05c4ce

Gemini 3.8 Flash

Google

Expired

Pricing is unavailable for this model.

Where it fits

Based on independent evidence
ChatStrong fit

Conversation quality and instruction following.

SupportStrong fit

Instruction following and multi-turn conversations.

CodingGood fit

Coding tasks and web development.

DocumentsStrong fit

Long queries and document work.

ResearchStrong fit

Hard prompts, agents, and factual accuracy.

How we calculated thisPricing unavailable
Typical chat assumption2,000 input · 500 output tokens per request

Official pricing

google-gemini-3-8-flash-standard-2026 · Until Dec 31, 2026 · Standard billing

Standard text
$0.75 input · $3.75 output / 1M tokens

Verified Sep 26, 2026

google-gemini-3-8-flash-standard-2027 · Starts Jan 1, 2027 · Standard billing

Standard text
$1.50 input · $7.50 output / 1M tokens

Verified Sep 26, 2026

Model details

Model ID
gemini-3.8-flash
Tool calling
true
Structured output
true
context Window
1,048,576
max Output Tokens
65,536
modality
text
processing Tier
standard
thinking Tokens Included
Yes

Task evidence

General chat: 98 / 100 · strong fit

Support chat: 98 / 100 · strong fit

Coding help: 88 / 100 · good fit

Document work: 98 / 100 · strong fit

Research agent: 91 / 100 · strong fit

Catalog 2026-10-08-7b05c4ce

Gemini 3.1 Pro Preview

Google

Expired

Pricing is unavailable for this model.

Where it fits

Based on independent evidence
ChatStrong fit

Conversation quality and instruction following.

SupportStrong fit

Instruction following and multi-turn conversations.

CodingGood fit

Coding tasks and web development.

DocumentsGood fit

Long queries and document work.

ResearchLimited fit

Hard prompts, agents, and factual accuracy. Compare alternatives.

How we calculated thisPricing unavailable
Typical chat assumption2,000 input · 500 output tokens per request

Official pricing

google-gemini-3-1-pro-preview-standard · Current · Standard billing

Standard text
$2.00 input · $12.00 output / 1M tokens
Above 200,000 input tokens per request
$4.00 input · $18.00 output / 1M tokens

Verified Sep 26, 2026

Model details

Model ID
gemini-3.1-pro-preview
Tool calling
true
Structured output
true
context Window
1,048,576
max Output Tokens
65,536
modality
text
processing Tier
standard
thinking Tokens Included
Yes

Task evidence

General chat: 96 / 100 · strong fit

Support chat: 96 / 100 · strong fit

Coding help: 73 / 100 · good fit

Document work: 79 / 100 · good fit

Research agent: 62 / 100 · limited fit

Catalog 2026-10-08-7b05c4ce

About Google Gemini Developer API

Coverage, billing details, and what to check before you build.

Google Gemini Developer API is included as a hosted language-model provider. The catalog focuses on paid API usage for an application, not consumer Gemini plans and not bundled cloud commitments. This keeps the estimate tied to an exact endpoint and a reproducible input/output workload.

Where Gemini fits

The catalogued Gemini model can cover chat, generation, extraction, and research-oriented language calls. A complete AI product may also require web search, page retrieval, image generation, or video generation. Those services are modeled separately because their billing units and compatibility rules differ from language tokens.

The scenario builder translates product activity into billable work. For example, monthly users and messages per user produce chat calls, while research tasks can produce multiple language calls plus search and scraping demand. Exact mode is available when the team already knows monthly request and token totals.

Token pricing without hidden averaging

Input and output tokens are priced independently. Chat and research remain separate rows through context-band selection, even when both use the same model. This is important because a large prompt can be billed or constrained differently from a small one. The engine calculates each row with decimal arithmetic and rounds only for display.

The live offer section above supplies the exact model ID, current public plan, limits, capabilities, verification date, and official source links. These details are rendered from the current catalog snapshot. The article explains the decision model but does not hard-code prices that could become stale.

Only the billing path described by the active plan is included. Free tiers, batch processing, caching, priority modes, experimental endpoints, and negotiated agreements are excluded unless represented by a separate verified offer. An estimate should not assume that a free allowance repeats every month unless the user explicitly enables a catalogued recurring allowance.

Compatibility also matters. The calculator checks minimum context, tool-calling support, structured output, and model limits. Unknown support fails closed for required capabilities. This can remove an offer from a recommendation even when a price is known.

Use the verified offer

Select the offer above to open the calculator with Chat enabled and the model locked. The rest of the stack remains comparable, so search, scraping, image, and video providers can still change independently. This is useful for answering a narrow question such as “What would this application cost if Gemini handled every language call?”

The estimate excludes taxes, infrastructure, storage, retries, and development costs. Check the displayed source and verification date before using the result for a production decision.