New Sign up free, 10 calls on us. Up to $1, no card needed.

Gemini 3.6 Flash

Released 2026-07-21

chatVisionCodeTool callingPrompt cachingReasoning

Gemini 3.6 Flash is a generally available model that Google's documentation positions as sustained frontier-level intelligence for the agentic era, optimized for higher speed and lower cost.

Input
text image video audio $1.5/M
Output
text $7.5/M
Audio input
$5/M
Cache read
$0.15/M
Context
1M
vs GPT-4o
~70% cheaper
Knowledge cutoff
2026-03

Benchmarks

Above averageNo peer higher5 / 191 / 19
Gemini 3.6 Flash other models measured peer average no peer scored higher
Terminal-Bench 2.1
78%
BioMysteryBench hard
41.2%
OSWorld 2.0
33.8%
GDPval-AA v2 Elo · 1422-1598 per Google · 2026-08-25
1422
Harvey Lab-AA
85.1%
HLE-Verified
51.2%
AutomationBench
17%
LVBench
84.2%

Vendor-published: Alibaba (Qwen) Anthropic DeepSeek Google Moonshot OpenAI Tencent Z.ai

Price in context

Where the price sits among 65 comparable models

Input$1.5/M
$0.05 · Qwen3 VL Flash GPT-5.4 Pro · $30
Output$7.5/M
$0.275 · DeepSeek V4 Flash GPT-5.4 Pro · $180
Cached read$0.15/M
$0.0028 · DeepSeek V4 Flash GPT-5.4 Pro · $15

The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.

Specs & limits

Tokens

Context window (vendor spec) 1,048,576
Max output (vendor spec) 65,536
Knowledge cutoff 2026-03

Prompt caching

How it caches automatic + explicit
Min prefix 4,096

Thinking

Vendor control thinkingLevel
Accepted values minimal · low · medium · high
Default medium applied when the request sets nothing
Can be turned off No
Thinking behaviour Shares the 3.5 Flash thinking profile, with medium by default and high as the dynamic setting; thinking tokens bill as output tokens and thought signatures should be returned unmodified across turns.
Parameter reasoning_effort
Values minimal · low · medium · high the gateway's parameter surface - the vendor mapping above applies

Model

Modalities text + image + video + audio → text
  • GA
  • 1,048,576-token context, 65,536 max output
  • thinking plus the full built-in tool suite including Computer Use
  • officially positioned as stronger on complex agentic and multimodal tasks with lower token usage than 3.5 Flash. Note: temperature/top_p/top_k are deprecated and ignored from this generation. Knowledge cutoff comes from the DeepMind model card (the API page dropped the row): March 2026, and the card adds that some domains remain limited to January 2025

per Google official docs ↗

One prompt, measured through the gateway

PROMPT Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. CHECK exactly 3 sentences

Gemini 3.6 Flash passed · 3 sentences

Enabling reasoning causes the model to generate thousands of internal "thinking" tokens behind the scenes to process logic before delivering the final response. Because our vendor bills us for every token generated—including these intermediate processing steps—our billable output volume per query surged significantly. Since output tokens carry a much higher unit cost than input tokens, this jump in processing volume directly doubled our overall spend.

out 893 tok (+816 thinking) latency 4.7 s

Instruction following (exactly three sentences - countable), audience shaping (CFO register), and the hidden-thinking billing gap the token meters below expose.

PROMPT This function is supposed to return the longest run of consecutive equal items, but callers report it is off by one on single-element inputs and misses runs that end at the last index. Fix it and explain the bug in one paragraph. CHECK fix passes tests

Gemini 3.6 Flash passed · 8/8 cases

Here is the fixed function along with an explanation of the bugs: ```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 else: cur = 1 best = max(best, cur) return best ``` ### Explanation The original function initialized `cur` and `best` to `0` and incremented `cur` on matching adjacent items, which meant it was counting identical adjacent *pairs* rather than the total number of *elements* in a run. This caused single-element inputs to skip the loop and return `0` instead of `1`, and undercounted all run lengths by 1 (for example, a run of two items at the end of the list resulted in `cur = 1`). […]

out 2034 tok (+1768 thinking) latency 10.0 s

Whether the fix is actually correct (runnable), explanation density, and token efficiency on a bounded task.

PROMPT Extract a JSON object with fields {company, quarter, revenue_usd_m, growth_pct, guidance} from this text. Use null for anything not stated; add no other fields. CHECK valid JSON, schema exact

Gemini 3.6 Flash passed · 5/5 fields, guidance "withheld"

```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": null, "guidance": "withheld" } ```

out 2843 tok (+2783 thinking) latency 13.1 s

Schema obedience (no invented fields), hallucination pressure (guidance is explicitly withheld), and structured-output path differences.

PROMPT Write a 120-word product announcement for an API gateway feature that caches prompts across providers. Forbidden words: "seamless", "unlock", "game-changer", "revolutionize", "empower". Exactly one sentence must be a question. CHECK 120 words, 0 banned words

Gemini 3.6 Flash missed · 60 words, 0 banned, 0 questions

72: reducing 73: your 74: monthly 75: token 76: spend. S6 (21): 77: You 78: can 79: easily 80: set 81: custom 82: expiration 83: rules, 84: configure 85: TTL 86: settings, 87: and 88: manage 89: cache 90: invalidation 91: across 92: all 93: vendors 94: from 95: one 96: centralized 97: dashboard. S7 (23): 98: Start 99: optimizing […]

out 4092 tok (+3929 thinking) latency 16.3 s

Constraint obedience (word budget, banned-word list, the single question), style fingerprint, and length control.

Use Gemini 3.6 Flash in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="gemini-3.6-flash",
    messages=[{"role": "user", "content": "Summarize this diff"}],
)
print(resp.choices[0].message.content)

About Gemini 3.6 Flash

  • The docs say it delivers stronger performance on complex agentic and multimodal tasks while reducing token usage, at a lower price point than 3.5 Flash.
  • Google calls out code generation, agentic execution, and spatial reasoning as its strengths and names rapid agentic loops involving complex coding cycles and iterations as what it is best for; the model card frames it as the workhorse tier with better token efficiency than 3.5 Flash.
  • It supports thinking and the full built-in tool suite including Computer Use, function calling, structured outputs, code execution, Search and Maps grounding, URL context, file search, context caching, the Batch API, and Flex and Priority inference.
  • Input covers text, image, video, and audio across a 1M-token context window with 65,536 output tokens. thinking_level accepts minimal, low, medium, and high and defaults to medium, with minimal a floor rather than an off switch.
  • The knowledge cutoff is March 2026.
  • The model page also flags an API change: temperature, top_p, and top_k are deprecated and ignored from this generation onward, with Google warning that future models will return HTTP 400 for them.
  • Synthorai serves it through its OpenAI-compatible chat endpoint.

FAQ

Is the Gemini 3.6 Flash API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $1.5/M input tokens, that credit alone covers roughly 83 requests of ~8K tokens against Gemini 3.6 Flash.

What is Gemini 3.6 Flash best at?

Frontier intelligence at higher speed, lower cost; lower token usage than 3.5 Flash per Google docs; 1M context with Computer Use built in. See the About section for the full picture from the vendor's own release notes.

How much does Gemini 3.6 Flash cost?

Gemini 3.6 Flash costs $1.5 per million input tokens and $7.5 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.15/M.

Does Gemini 3.6 Flash support prompt caching?

Yes: automatic caching is on by default, with an explicit mode for guaranteed savings. Cached input tokens bill at $0.15/M vs $1.5/M uncached; prompts need a 4,096-token stable prefix to cache. Prompt caching guide →

How do I get access to Gemini 3.6 Flash?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gemini-3.6-flash", and you're done. One API key covers every model on the gateway.

What is Gemini 3.6 Flash's knowledge cutoff?

Gemini 3.6 Flash's knowledge cutoff is 2026-03, per the vendor's official documentation (as of 2026-07-22).

Related models

Compare

Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.

Get your API key Compare your cost →