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

Gemini 3.5 Flash

Released 2026-05-19

chatVisionCodeTool callingPrompt cachingReasoning

Gemini 3.5 Flash is the model Google's catalog labels its most intelligent for sustained frontier performance on agentic and coding tasks, describing it as intelligence optimized for real-world tasks at higher speed and lower cost and "designed for the agentic era," excelling at sub-agent deployment, multi-step workflows, and long-horizon tasks at scale.

Input
text image video audio $1.5/M
Output
text $9/M
Audio input
$5/M
Cache read
$0.15/M
Context
1M
vs GPT-4o
~70% cheaper
Knowledge cutoff
2025-01

Benchmarks

Above averageonly 3 comparable
Gemini 3.5 Flash other models measured peer average no peer scored higher
GeneBench Pro
8.14%
GDPval-AA v2 Elo · 642-1861
1348.8
AutomationBench
14.5%

Vendor-published: Anthropic Google Moonshot OpenAI

Price in context

Where the price sits among 60 comparable models

Input$1.5/M
$0.05 · Qwen3 VL Flash GPT-5.4 Pro · $30
Output$9/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 2025-01

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 high is the dynamic setting; minimal does not guarantee thinking is off, so thinking tokens bill as output tokens on every request and thought signatures should be echoed back for multi-turn continuity.
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

1,048,576-token input / 65,536 output; code execution supported; computer use in Preview.

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 3.5 Flash passed · 3 sentences

Reasoning models do not just generate a final answer; they perform a silent, multi-step "thinking" process beforehand to ensure higher accuracy. We are billed for every single one of these invisible reasoning steps (called "thinking tokens"), which drastically increases the computational volume per query. Consequently, while our user activity remained flat, our unit costs doubled because the AI is now doing significantly more backend processing to deliver these higher-quality results.

out 1152 tok (+1065 thinking) latency 7.7 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 3.5 Flash passed · 8/8 cases

Here is the corrected version of the function: ```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 of the Bug The original code initialized `best` and `cur` to `0` instead of `1` (the minimum run length for any non-empty list), which caused it to count the number of adjacent duplicate *transitions* rather than the actual number of *elements* in a run. This resulted in an off-by-one error for all runs and caused single-element lists to incorrectly return `0`. […]

out 2386 tok (+2110 thinking) latency 12.7 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 3.5 Flash passed · 5/5 fields, guidance "withheld pending the Q4 close"

```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": null, "guidance": "withheld pending the Q4 close" } ```

out 1950 tok (+1885 thinking) latency 12.7 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 3.5 Flash missed · 50 words, 0 banned, 0 questions

thought 51: OpenAI, 52: Anthropic, 53: and 54: Cohere. 55: When 56: a 57: client 58: submits 59: a 60: matching 61: request, 62: the 63: gateway 64: retrieves 65: the 66: cached 67: result 68: instantly, 69: slashing 70: latency 71: and 72: reducing 73: your 74: monthly 75: […]

out 4092 tok (+3933 thinking) latency 19.1 s

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

Use Gemini 3.5 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-3.5-flash",
    messages=[{"role": "user", "content": "Summarize this diff"}],
)
print(resp.choices[0].message.content)

About Gemini 3.5 Flash

  • Google's model card names agentic workflows, coding tasks, and multi-week enterprise processes as its intended uses.
  • It takes text, image, video, audio, and PDF input across a 1,048,576-token context window with 65,536 output tokens, returning text.
  • Function calling, structured outputs, code execution, Search and Maps grounding, URL context, file search, context caching, the Batch API, and computer use in preview are supported; image generation, audio generation, and the Live API are not.
  • Thinking is set with thinking_level, which accepts minimal, low, medium, and high and defaults to medium, a deliberately cheaper default than the high used by the Gemini 3 preview models, though minimal is a floor rather than an off switch and still bills reasoning tokens.
  • Thought signatures apply here as on the rest of the generation.
  • It has been generally available since May 2026, and gemini-3-flash-preview is its preview alias; Google now positions 3.6 Flash above it on token efficiency.
  • Synthorai provides access through its OpenAI-compatible chat endpoint.

FAQ

Is the Gemini 3.5 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 3.5 Flash.

What is Gemini 3.5 Flash best at?

Sustained frontier performance on agentic tasks; effective for rapid agentic coding loops; computer use preview and grounding support. See the About section for the full picture from the vendor's own release notes.

How much does Gemini 3.5 Flash cost?

Gemini 3.5 Flash costs $1.5 per million input tokens and $9 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 3.5 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 3.5 Flash?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gemini-3.5-flash", and you're done. One API key covers every model on the gateway.

What is Gemini 3.5 Flash's knowledge cutoff?

Gemini 3.5 Flash's knowledge cutoff is 2025-01, per the vendor's official documentation (as of 2026-07-09).

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 →