GooglePay as you go

Gemini 3.5 Flash

Google's most intelligent Flash model for sustained frontier performance on agentic and coding tasks.

Model ID

google/gemini-3.5-flash
Context window
1M
tokens
Max output
66K
tokens
Input
$0.975
per 1M tokens
Output
$5.85
per 1M tokens

Cache read $0.0975 · Cache write $0.0541

Quickstart

Call Gemini 3.5 Flash in one request.

Point the SDK you already use at xKiro and pass the model ID. The same key works for every model in the catalog.

SDK guides
main.py
import osfrom openai import OpenAI client = OpenAI(    api_key=os.environ["XKIRO_API_KEY"],    base_url="https://api.xkiro.com/v1",) res = client.chat.completions.create(    model="",    messages=[        {"role": "user", "content": "Explain HTTP caching in two sentences."},    ],) print(res.choices[0].message.content)
Response · Example

✓ 200 OK

"model": "google/gemini-3.5-flash"

HTTP caching stores copies of responses so later requests can be served without contacting the origin server. Headers such as Cache-Control and ETag decide how long a copy stays fresh and how it is revalidated.

14 input · 42 output tokens · $0.00026 at this model’s rates

Create an API key in the dashboard and export it as XKIRO_API_KEY.

Pricing

What Gemini 3.5 Flash costs.

Billed per million tokens from your wallet balance, outside plan budgets.

  • $0.975

    $1.50−35%

    Input

    per 1M tokens

  • $5.85

    $9−35%

    Output

    per 1M tokens

  • $0.0975

    Cache read

    per 1M tokens

  • $0.0541

    Cache write

    per 1M tokens

Billed fairly

  • A request that fails before any output is generated is never billed
  • An identical blocking request retried within two minutes replays the first result — no double charge
  • If a stream breaks off or you cancel it, you pay only up to that point

Specifications

Limits and capabilities.

Context window
1,000,000 tokens
Max output
65,536 tokens
Input
Text · Image · Video
Output
Text
Provider
Google
Model ID
google/gemini-3.5-flash
Good for
Coding · Long context

Capabilities

  • Tool useSupported
  • VisionSupported
  • Video inputSupported
  • ReasoningSupported

Reasoning effort

  1. low
  2. medium
  3. high

Set it with reasoning_effort in the OpenAI format, or thinking in the Anthropic format.

Reasoning guide

Supported parameters

  • max_tokens
  • temperature
  • top_p
  • stop
  • frequency_penalty
  • presence_penalty
  • seed
  • stream
  • tools
  • tool_choice
  • response_format
  • structured_outputs
  • reasoning
  • include_reasoning

Compare

Similar models.

Closest in price and context window — same provider first, then alternatives from other providers.

Browse all 69 models
Gemini 3.5 Flash compared with similar models, prices per 1M tokens
ModelInput / 1MOutput / 1M
Gemini 3.5 FlashThis model−35%Pay as you goVision · Video input · Reasoning · Tool use1M$0.975$1.50$5.85$9$0.0975
Gemini 2.5 Pro−35%Pay as you goVision · Video input · Reasoning · Tool use1M$0.8125$1.25$6.50$10$0.0813
Gemini 3.1 Pro−35%Pay as you goVision · Video input · Reasoning · Tool use1M$1.30$2$7.80$12$0.13
Gemini 3 Flash−35%Pay as you goVision · Video input · Reasoning · Tool use1M$0.4875$0.75$2.44$3.75$0.0488
GPT-5.6 Terra−50%Vision · Reasoning · Tool use1M$1$2$6$12$0.125
GPT-6.1 TerraVision · Reasoning · Tool use1.05M$1$5$0.05
Nemotron 3 UltraReasoning · Tool use1M$0.6$2.40$0.12
modelgoogle/gemini-3.5-flash

Start building with Gemini 3.5 Flash.

Create a key, point your SDK at xKiro and call google/gemini-3.5-flash.

No credit card · No auto-renewal · 26 free models, free forever