Gemini 3.5 Flash
GoogleReleased May 19, 2026
Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...
- Context window
- 1.0M tokens
- Max output
- 66K tokens
- Input
- text, image, video, file, audio
- Output
- text
- Tokenizer
- Gemini
- Knowledge cutoff
- Jan 1, 2025
- Released
- May 19, 2026
- Reasoning
- always on
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | $1.50 | $0.045 | $1.54 |
| Output | $9.00 | $0.270 | $9.27 |
| Cache read | $0.150 | $0.0045 | $0.154 |
| Cache write | $0.083 | $0.0025 | $0.086 |
Benchmarks
Artificial Analysis
- Intelligence index
- 50.2
- Coding index
- 70.1
- Agentic index
- 37.4
Design Arena
| Category | Elo | Win rate | Rank |
|---|---|---|---|
| agenticgamedevagents | 1217 | 55.1% | #3 |
| agentichtmlslidesagents | 1162 | 45.8% | #7 |
| agenticslidesagents | 1244 | 57.5% | #4 |
| agenticslides(html)agents | 1162 | 45.7% | #7 |
| agenticslides(python-pptx)agents | 1242 | 57.8% | #3 |
| androidnativeagents | 1261 | 54.9% | #5 |
| Full-stackagents | 1267 | 58.1% | #6 |
| htmlslidesagents | 1183 | 49% | #9 |
| Mobile appsagents | 1263 | 57.2% | #2 |
| pptxslidesagents | 1244 | 57.7% | #3 |
| python-pptxslidesagents | 1247 | 57.4% | #4 |
| Web appsagents | 1262 | 54.2% | #5 |
| 3Dmodels | 1310 | 60.3% | #14 |
| ASCII artmodels | 1314 | 62.4% | #5 |
| Codemodels | 1306 | 58.5% | #12 |
| Data vizmodels | 1267 | 55.1% | #23 |
| Game devmodels | 1330 | 59.4% | #8 |
| SVGmodels | 1311 | 63.4% | #3 |
| UI componentsmodels | 1314 | 59.7% | #11 |
| Websitesmodels | 1299 | 57.6% | #14 |
Head-to-head preference voting. How we filter and rank
Supported parameters
- include_reasoning
- max_tokens
- reasoning
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model google/gemini-3.5-flash.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-3.5-flash",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="google/gemini-3.5-flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "google/gemini-3.5-flash",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);Questions
- How much does Gemini 3.5 Flash cost via API?
- Through OpenKey, Gemini 3.5 Flash costs $1.54 per 1M input tokens and $9.27 per 1M output tokens. That is the provider price ($1.50 / $9.00) plus a flat 3% fee — nothing else.
- What is Gemini 3.5 Flash's context window?
- Gemini 3.5 Flash accepts up to 1.0M tokens of context and returns up to 66K tokens per request.
- Is Gemini 3.5 Flash OpenAI-compatible?
- Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "google/gemini-3.5-flash" using any OpenAI SDK — only the base URL and API key change.
- What inputs does Gemini 3.5 Flash support?
- Gemini 3.5 Flash accepts text, image, video, file, audio input and produces text output. Its knowledge cutoff is Jan 1, 2025.
More from Google
All Google models →Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...
ctx 66Kin $0.258out $1.54
Nano Banana Pro (Gemini 3 Pro Image)
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...
ctx 66Kin $2.06out $12.36
Nano Banana 2 (Gemini 3.1 Flash Image)
Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...
ctx 131Kin $0.515out $3.09
Gemini 3.1 Flash Lite
Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...
ctx 1.0Min $0.258out $1.54