Access Google Gemini 3.6 Flash—also searched as Gemini 3.6— through EvoLink's unified chat API. Test coding, multi-step agents, tool use before integrating.
Google·Text Generation·Available
From $0.675 / 1M input tokens$1.500 official priceLimited time-55%
Multimodal reasoningTool useStructured outputPrompt cachingChat + Gemini API
Production routeThis rate reflects platform-side availability — only confirmed server errors (HTTP 500 / empty response) count as failures. User-side issues (content moderation, invalid params, cancellation) plus rate limits, timeouts and auth errors are excluded. Before real traffic arrives, empty buckets may display as available.Live
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
Model ID
gemini-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
$0.675 / 1M-55%
45.9 cr / 1M$1.500official price
Cache read
$0.068 / 1M-55%
4.6 cr / 1M$0.150official price
Output
$3.375 / 1M-55%
229.5 cr / 1M$7.500official price
All rates are per 1M tokens, shown in USD and credits, and reflect your account's current pricing.
Gemini 3.6 Flash pricing
Estimate what one Gemini 3.6 Flash request costs before you integrate. The calculator uses your account's current rates, with official pricing as a reference.
Limited-time offer — the rates below reflect Google’s introductory pricing and run through December 31, 2026 (UTC+8). From January 1, 2027, our usual discount applies to Google’s standard price ($1.500 input / $7.500 output per million tokens).
Request calculator
Enter the token mix for one request and the number of Google Search queries.
Estimated request cost
Gemini 3.6 Flash
USD$0.0018
Credits0.1158
Official estimate $0.0038 · save $0.0021 (55%)
Input tokens0.0459 cr
Cache read tokens0.001 cr
Output tokens0.0689 cr
Google Search0 cr
Minimum charge: 0.01 credits per request.
Budget guide
Approximate requests using the current token mix and search queries.
Gemini 3.x bills each nonempty search query, even if no sources are returned. One request may run multiple queries. Search fees are added separately after the token minimum charge.
Google Search$0.014/ query·0.952 cr / query
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 $1.500 / $7.500 per million input / output tokens.
Gemini 3.6 Flash is served on EvoLink under the model ID gemini-3.6-flash through Chat Completions · Gemini native API, with the same API key and balance you use for every other model. It offers a 1.05M context window and up to 65.5K output tokens, plus coding, multi-step agents, tool use.
Gemini 3.6 Flash specs and capabilities
Numbers come from the EvoLink route configuration; capabilities are what the API exposes today.
Context window
1.05M tokens
Max output
65.5K tokens
Input
Text + images
Output
Text · JSON (structured output) · tool calls
Reasoning
Configurable reasoning effort
Tool use
Function calling with multi-step tool sequences
Prompt caching
Automatic cache reads at a lower rate
Server-side tools
Google Search, billed per search query
Protocols
Chat Completions · Gemini native API
Model ID
gemini-3.6-flash
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.
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.
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 $7.500 per million versus $9.000 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.
Two ways to use Gemini 3.6 Flash: EvoLink API or Agent
Use the EvoLink API for product backends and batch jobs, or call Gemini 3.6 Flash from Codex, Claude, or Gemini for coding and analysis workflows. Both paths share the same EvoLink API key, balance, model ID, and request history.
Option 1
Integrate with the EvoLink API
Best for: product backends, batch jobs, automated pipelines
Send Gemini native generateContent requests to EvoLink and control the model ID, system instruction, output budget, tools, and structured output.
1Create an EvoLink API key in the console
2Call the generateContent endpoint on the EvoLink base URL with the model ID shown above in the request path
3Send one representative request and read usageMetadata for input, cached, and output tokens
4Set maxOutputTokens and retries per task; keep function-call parts and their results across turns
Best for: coding, review, and analysis tasks in Codex, Claude, and Gemini
Give the Agent the task, the inputs to include, and the acceptance criteria. It assembles the request, calls Gemini 3.6 Flash through EvoLink, and returns the answer with token usage.
1Set EVOLINK_API_KEY in your local environment; never put it in code or a prompt
2Describe the task, the inputs to include, and the expected output format
3Ask the Agent to call Gemini 3.6 Flash through EvoLink and show the request before sending
4Let the Agent report the answer, token usage, and any error body
Gemini 3.6 Flash API code example and error handling
This example shows the shortest runnable request: a Gemini native generateContent call with a system instruction, a user message, and an output budget. Open the API tab for the complete parameter and response reference.
# Gemini native API
curl -X POST "https://api.evolink.ai/v1beta/models/gemini-3.6-flash:generateContent" \
-H "Authorization: Bearer $EVOLINK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"systemInstruction": { "parts": [{ "text": "You are a precise assistant. Answer in JSON when asked." }] },
"contents": [
{ "role": "user", "parts": [{ "text": "Classify the sentiment of each review below and return a JSON array:\n<reviews>" }] }
],
"generationConfig": {
"maxOutputTokens": 1024,
"temperature": 0.1
}
}'
# For streaming, call streamGenerateContent?alt=sse with the same body.
# The response includes candidates[0].content.parts and usageMetadata
# (prompt, cached, thinking, and output token counts).
Invalid request or unsupported parameter
Check the model ID, the contents array, and parameter ranges against the API reference; remove fields this route does not support.
Authentication or balance issue
Check the Authorization bearer token and confirm the available balance in the console.
Context length exceeded
Prompt tokens exceed the Gemini 3.6 Flash context window. Trim or retrieve only the relevant evidence and reuse cached prefixes.
Rate limited (429)
Back off and retry with jitter; batch or queue requests instead of sending parallel bursts.
Content or tool call rejected
Review sensitive content, malformed tool-call arguments, and JSON schema mismatches before retrying.
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
Prompt caching for repeated long context
Automatic cache reads use a dedicated lower rate when stable repository instructions, reference documents, and tool schemas can be reused.
1M-token context with a 65K default output limit
Keep connected code, specifications, documents, and agent state in one working context. Treat the limit as capacity rather than a target: retrieve relevant evidence and set task-appropriate output budgets.
Compare Gemini 3.6 Flash 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 Gemini 3.6 Flash with 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.
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.
The cheapest, fastest 3.5-class route for classification, extraction, and high-throughput subagents — escalate hard work to 3.6 Flash.
Step up to the Pro tier when a task needs deeper reasoning than the Flash line can deliver.
Gemini 3.6 Flash
Input / output$0.675 / $3.375
Context1.05M
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.
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 $7.500 vs $9.000 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.
How long does the Gemini 3.6 Flash introductory price last?
Google lists $0.750 input and $3.750 output per million tokens as an introductory price through December 31, 2026, with standard rates of $1.500 and $7.500 from January 1, 2027. See the pricing section on this page for the current EvoLink 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.
