Gemini 3.6 Flash - Kyma API

Overview

This is Google’s latest Flash-tier model, optimized for handling text, image, audio, and video inputs while producing text outputs. It supports tool calling and reasoning, making it suitable for workflows that require parsing long documents or analyzing media streams. On Kyma, requests route through an OpenAI-compatible endpoint with automatic failover to maintain uptime. Prompt caching is enabled, billing repeated prefixes at 10% of the standard input rate. Responses include exact request costs in usage.cost and report the active model via the X-Kyma-Model header. The model caps output at 8,192 tokens and does not support structured output formats. It operates in the premium cost tier, though output tokens are priced lower than the previous 3.5 Flash iteration.

Specs

Field	Value
Model ID	`gemini-3.6-flash`
Best for	High-volume multimodal work at 1M context
Context window	1.048576M
Max output tokens	8K
Input modalities	Text, Image, Audio, Video
Output modalities	Text
Tool calling	Yes
Structured outputs	Yes
Prompt caching	Yes
Speed	Fast
Cost band	Premium
Release stage	Stable

Pricing

	Per 1M tokens
Input	$2.02
Output	$10.13

Use this when

Document Analysis Pipeline — Ingests long reports or manuals up to 1M tokens and extracts key insights or summaries.
Multimedia Content Review — Processes video frames and audio tracks alongside text prompts to generate descriptive reports.
High-Volume Chat Routing — Handles concurrent conversational requests with tool calling and reasoning at fast throughput speeds.
Automated Content Drafting — Generates text drafts from mixed media inputs while keeping output costs lower than prior tiers.

Not ideal for

Do not use this model if your application requires strict JSON or structured output formatting, as that capability is not supported.

Pick something else when

You need guaranteed structured JSON outputs: use qwen-3.7-plus or gpt-5.6-terra.
You need lower-cost text-only generation: use gemini-3.5-flash-lite or deepseek-v4-flash.
You need faster reasoning for code tasks: use qwen-3-coder or kimi-k3.

Example

from openai import OpenAI

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

response = client.chat.completions.create(
    model="gemini-3.6-flash",
    messages=[{"role": "user", "content": "..."}],
    tools=[...],  # function calling supported
)

Agent query example

Ask the API which models fit, instead of hardcoding an id:

curl "https://kymaapi.com/v1/models?recommended_for=chat&tools=true&quality_tier=frontier-open"

FAQ

Does this model support structured output formats like JSON mode? No, Gemini 3.6 Flash does not support structured outputs. You will need to parse the text response manually or route to a model that explicitly supports that feature. How does prompt caching affect billing on Kyma? Repeated prompt prefixes are billed at 10% of the standard input rate, which reduces costs for long-context or repetitive workflows. What happens if the serving path experiences latency or downtime? Kyma automatically reroutes your request to a healthy serving path, ensuring requests complete without requiring retry logic in your code.

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ