Kimi K3 is now availableExplore Kimi K3

Gemini 3.6 Flash API

Google-Text generation-from $1.350 / 1M input tokens$1.500 official price-Available
1M context65K default outputPrompt cachingChat + Gemini API
API docs
Production routeLive
Provider
Google
Model
3.6 Flash
Context window
1,048,576 tokens
Protocols
Chat + Gemini

Choose Gemini 3.6 Flash

Google’s newest Flash-tier workhorse for cost-efficient coding, agentic workflows, knowledge work, and multimodal reasoning, with improved token efficiency over Gemini 3.5 Flash and a 1M-token context window.

Gemini 3.6 Flash

Google Flash-tier workhorse model

Selected
From $1.350 / 1M input tokens$1.500 official pricegemini-3.6-flash
Best for

Production coding and full-stack refactoring, multi-step agents and orchestration, document and chart analysis, and high-volume workloads where better token efficiency lowers cost per completed task.

Input
$1.350 / 1M-10%
91.8 cr / 1M$1.500official price
Cache read
$0.136 / 1M-10%
9.2 cr / 1M$0.150official price
Output
$6.750 / 1M-10%
459 cr / 1M$7.500official price

Gemini 3.6 Flash pricing

Estimate a request with the interactive pricing calculator. All user groups use the official Gemini 3.6 Flash rate.

3.6 Flash

Token calculator

Enter the token mix for one request.

Estimated request cost

Gemini 3.6 Flash
Official rate
USD$0.0035
Credits0.2314
Input tokens0.0918 cr
Cache read tokens0.0019 cr
Output tokens0.1377 cr

Minimum charge: 0.01 credits per request.

EvoLink vs Google direct

Same token mix, default group price.
-10%
EvoLink estimate$0.0035
Google official$0.0038
You save$0.0004

Budget guide

Approximate requests using the current token mix.
Add credits
$10
About 2938 requests

For quick testing

$50
About 14693 requests

For regular development

$100
About 29386 requests

For production evaluation

Model pricing

Gemini 3.6 Flash

All context sizes
Input tokens
$1.350 / 1M-10%
91.8 cr / 1M$1.500official price
Cache read tokens
$0.136 / 1M-10%
9.2 cr / 1M$0.150official price
Output tokens
$6.750 / 1M-10%
459 cr / 1M$7.500official price

USD and credits are shown per 1M tokens. Live backend pricing takes priority over these frozen fallback rates.

Gemini 3.6 Flash API for cost-efficient coding and agent workflows

Call Google’s newest Flash-tier workhorse through EvoLink’s unified API. Gemini 3.6 Flash improves coding, knowledge work, and multimodal reasoning with better token efficiency than Gemini 3.5 Flash, plus a 1,048,576-token context window, prompt caching, structured output, and tool use — at $1.50 / $7.50 per million input / output tokens.

Gemini 3.6 Flash
Gemini 3.6 Flash use cases

Where Gemini 3.6 Flash earns a place in a production model stack

Google positions Gemini 3.6 Flash as a workhorse: better coding, knowledge work, and multimodal performance with meaningfully improved token efficiency over Gemini 3.5 Flash. Its strongest fit is production work where good-enough reasoning at a lower token cost beats paying for a premium tier.

Cost-efficient coding and refactoring

Gemini 3.6 Flash targets everyday coding, prototyping, and full-stack refactoring with fewer tokens and fewer model calls than Gemini 3.5 Flash. It is Google’s default agent model in Antigravity. Measure accepted patches and review time, not isolated snippet quality.

Agentic workflows and orchestration

It fits multi-step orchestration, tool selection, structured output, and code execution where lower per-call cost compounds across long agent runs. Preserve complete assistant messages, tool-call IDs, arguments, and tool results across turns.

Knowledge work and multimodal reasoning

Use it for document analysis, chart interpretation, and multi-element web layout generation across a 1M-token context. Retrieval and document structure still matter: a 1M window does not make irrelevant context useful.

When another route is the better choice

Trivial, latency-critical, or very high-volume classification and extraction usually belong on the cheaper Gemini 3.5 Flash-Lite. Route the hardest reasoning to a Pro-tier model. Escalate to 3.6 Flash only when its efficiency actually lowers cost per accepted task.

Launch-day signals

What early Gemini 3.6 Flash reactions suggest—and what still needs proof

Gemini 3.6 Flash launched on 2026-07-21. Treat launch-day community reactions as hypotheses to verify on your own tasks, tools, budgets, and acceptance criteria—not as settled benchmarks.

Token efficiency and lower output cost are the headline

Google and third-party API pages emphasize fewer tokens, fewer model calls, and less hedging, with output priced at $7.50 per million versus $9.00 for Gemini 3.5 Flash. On the same workload this can reduce cost per completed task even when quality is comparable.

It is a Flash-tier workhorse, not a top-end engineering model

Some launch-day discussion places it behind larger frontier models on hard software-engineering benchmarks. If your work is deep repository refactoring or long autonomous coding, benchmark it against a Pro-tier or premium model before making it the default.

Verify output discipline and formatting on your prompts

Early users report verbose or over-formatted responses on some tasks. Check completion length, instruction-following, and tool-call discipline on representative prompts so verbosity does not quietly raise output cost.

It is a closed, API-only Google model

Gemini 3.6 Flash has no open weights and cannot be self-hosted. Access is through the Gemini API and platforms such as Google AI Studio, Antigravity, and unified gateways like EvoLink—so route by cost and reliability, not by local deployment.

Core capabilities

Why Gemini 3.6 Flash can handle these workloads

Gemini 3.6 Flash is most useful when a large context window, improved token efficiency, and reusable prompt prefixes work together. Context capacity alone does not improve an answer; the workload still needs relevant evidence, clear structure, and an output budget.

A 1M-token workspace, not a target to fill

The 1,048,576-token window can keep related code, specifications, and prior tool results available without excessive chunking. Retrieval and context compaction still matter because irrelevant input competes for attention and increases processing cost.

Improved token efficiency over 3.5 Flash

Gemini 3.6 Flash aims to complete multi-step workflows in fewer turns and fewer tokens. Fewer model calls and cheaper output are where the cost advantage comes from, so track total tokens per accepted task rather than a single request price.

Prompt caching pays off when prefixes stay stable

Repository instructions, system prompts, reference material, and tool schemas create the strongest cache opportunity when their ordering stays consistent. Frequent model or prompt-structure changes can force the long prefix to be processed again.

Gemini 3.6 Flash API production checks

What to verify before routing production traffic to Gemini 3.6 Flash

A suitable workload can still fail because the integration uses the wrong identifier, sends unsupported parameters, or drops agent state between turns. Verify the request surface and conversation contract before evaluating model quality.

01

Use the exact model ID gemini-3.6-flash

Send model "gemini-3.6-flash" (with dots) on the EvoLink API route. The dashed form gemini-3-6-flash is only the page URL, not the API model parameter.

Model ID
02

Use OpenAI Chat Completions or the Gemini native API

EvoLink exposes Gemini 3.6 Flash through OpenAI-compatible /v1/chat/completions and the Gemini native generateContent endpoint. Keep the same EvoLink API key for either protocol.

Protocols
03

Mind the breaking parameter changes

Custom temperature, top-K, and top-P are ignored; custom frequency and presence penalties return an error; and a request whose last turn has the model role is rejected. Update older Gemini request builders accordingly.

Migration
04

Replay complete assistant and tool state

Multi-turn agents should retain complete assistant messages, tool-call IDs, arguments, and tool results. Keeping only the final text breaks state continuity and can make later steps fail even when the context window is large enough.

Tool state
Production economics

Compare cost per accepted task, not token price alone

Gemini 3.6 Flash wins on economics when its efficiency reduces tokens, model calls, retries, or human rework on the same workload. Evaluate identical task sets instead of comparing isolated prompt prices.

First-pass successAccepted deliverable rateRetry countOutput tokensCache-hit rateValid tool callsTime to accepted resultHuman correction and fallback rate

If Gemini 3.6 Flash produces usable results with fewer tokens and less review effort, its lower rates compound into a real cost advantage. If quality slips on your hardest tasks, escalate those to a Pro-tier model and keep 3.6 Flash for the efficient majority.

Compare leading long-context models after workload testing

EvoLink

First verify whether Gemini 3.6 Flash reduces retries and review effort on your tasks. Then compare price, context, caching, and workload fit to choose the production route.

Gemini 3.6 Flash
Input / output$1.35 / $6.75
Context1M
CachingAutomatic cache reads
Best forProduction coding and full-stack refactoring, multi-step agents and orchestration, document and chart analysis, and high-volume workloads where better token efficiency lowers cost per completed task.
Gemini 3.5 Flash Lite
Input / output$0.3 / $2.5
Context1M
CachingContext cache
Best forPro-tier Gemini for the deepest reasoning tasks the Flash line is not built to handle.
Gemini 3.1 Pro
Input / output$1.68 / $10.08
Context1M
CachingContext cache
Best forPro-tier Gemini for the deepest reasoning tasks the Flash line is not built to handle.

Other Gemini models on EvoLink

Gemini 3.5 Flash

Gemini 3.5 Flash

The previous-generation Flash workhorse that 3.6 Flash improves on for token efficiency and output cost.

View model
Gemini 3.5 Flash Lite

Gemini 3.5 Flash Lite

The cheapest, fastest 3.5-class route for classification, extraction, and high-throughput subagents.

View model
Gemini 3.1 Pro

Gemini 3.1 Pro

The Pro-tier step up when a task needs deeper reasoning than the Flash line can deliver.

View model
Gemini 3.1 Flash Lite

Gemini 3.1 Flash Lite

The lightweight 3.1 route for high-volume, cost-sensitive, and low-latency workloads.

View model

Other text models

GPT-5.6

GPT-5.6

OpenAI’s tiered frontier family (Sol/Terra/Luna) for capability, latency, and cost-routing flexibility.

View model
Claude Opus 4.8

Claude Opus 4.8

Anthropic’s premium baseline for long-running coding agents and judgment-heavy review.

View model
DeepSeek V4

DeepSeek V4

Cost-sensitive open baseline for high-volume coding, reasoning, and agent workloads.

View model
Kimi K3

Kimi K3

Moonshot’s long-context reasoning route for repository-scale coding and multi-document work.

View model

Related reading for production teams

Gemini 3.6 Flash release date & rollout

Gemini 3.6 Flash release date & rollout

What launched, the model ID, official pricing, and where the model is available.

Read guide

Gemini 3.6 Flash API FAQ

Is the Gemini 3.6 Flash API available through EvoLink?

Yes. Gemini 3.6 Flash is available as a production model with live backend pricing and official fallback rates.

What model ID should I use for the Gemini 3.6 Flash API?

Send model "gemini-3.6-flash" (with dots). The dashed gemini-3-6-flash is only the page URL, not the API model parameter.

Which protocols and SDKs work with Gemini 3.6 Flash?

Use the OpenAI-compatible Chat Completions endpoint or the Gemini native generateContent endpoint with the same EvoLink API key. There is no Anthropic Messages route for this model.

Does the Gemini 3.6 Flash API support 1M context or only 256K?

The EvoLink route records 1,048,576 tokens. Smaller limits usually come from a particular Gemini product surface or client configuration, not the API model itself.

How should I use the Gemini 3.6 Flash 1M-token context window?

Keep related code, documents, and tool results together, but use retrieval, stable cached prefixes, and context compaction instead of filling the window by default.

How is Gemini 3.6 Flash different from Gemini 3.5 Flash and 3.5 Flash-Lite?

3.6 Flash is the newer workhorse with better coding and token efficiency than 3.5 Flash (output $7.50 vs $9.00 per 1M). 3.5 Flash-Lite is the cheaper, faster route for classification and high-throughput tasks.

Why is Gemini 3.6 Flash cheaper to run than Gemini 3.5 Flash?

It targets fewer tokens and fewer model calls per task, and its output price is lower. Track total tokens per accepted task, not just the per-request rate.

What breaking changes should I handle when migrating to Gemini 3.6 Flash?

Custom temperature, top-K, and top-P are ignored; custom frequency and presence penalties return an error; and a request whose last turn has the model role is rejected.

How should I set the Gemini 3.6 Flash output budget?

Limit output according to task complexity and monitor both reasoning and final-answer tokens. The 65,536-token limit is capacity, not a routine target.

Is Gemini 3.6 Flash a good default for real-time or high-volume requests?

For the cheapest, lowest-latency classification and extraction, use Gemini 3.5 Flash-Lite. Use 3.6 Flash when its coding and reasoning quality justify a slightly higher rate.

How should I compare Gemini 3.6 Flash with GPT, Claude, GLM, or DeepSeek?

Evaluate Gemini 3.6 Flash for efficient coding and agent economics, GPT and Claude as frontier capability baselines, and GLM or DeepSeek as cost-sensitive open baselines.

What should a production Gemini 3.6 Flash evaluation measure?

Track first-pass success, accepted deliverables, retries, output tokens, cache hits, valid tool calls, time to accepted result, human correction, and fallback rate.