Gemini 3.5 Flash - Kyma API

Overview

gemini-3.5-flash is Google’s newest Flash-tier model on Kyma. It pairs a 1M-token context window with multimodal input (text, image, audio, and video) and fast reasoning, making it a strong pick for long-context and mixed-media workloads that still need low latency.

Specs

Field	Value
Model ID	`gemini-3.5-flash`
Best for	Long context, multimodal input, fast reasoning
Context window	1M
Max output tokens	8K
Input modalities	Text, image, audio, video
Output modalities	Text
Tool calling	Yes
Structured outputs	Yes
Reasoning	Yes
Vision	Yes
Prompt caching	Yes
Speed	Fast
Cost band	Premium
Release stage	Stable

Use this when

You need a very large (1M) context window for long documents, transcripts, or codebases.
Your input mixes text with images, audio, or video.
You want fast responses without dropping to a weaker model.
You build agents that need tool calling and structured JSON outputs.

Pick something else when

You want the cheapest long-context option: use gemini-2.5-flash.
You need the strongest tool-heavy agent behavior: use kimi-k2.6.
You want top reasoning over speed: use deepseek-v4-pro.

Example

from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")

response = client.chat.completions.create(
    model="gemini-3.5-flash",
    messages=[
        {"role": "user", "content": "Summarize this 200-page contract and flag unusual clauses."}
    ]
)

Agent query example

curl "https://kymaapi.com/v1/models?recommended_for=long-context&vision=true&quality_tier=frontier-open"

MiniMax M2.7 Gemini 2.5 Flash

​Overview

​Specs

​Use this when

​Pick something else when

​Example

​Agent query example