Gemini 3.7 Flash - Kyma API

Overview

Gemini 3.7 Flash is Google’s August 2026 Flash-tier release. It accepts text, image, audio, video and file input and returns text, and unlike the 3.6 tier it supports structured outputs alongside tool calling and reasoning. The practical difference from the rest of the Flash family is the output ceiling: 65,536 tokens against 8,192 on 3.6 Flash and 3.5 Flash Lite. Work that had to be chunked because the reply would not fit — full document translations, long structured extractions, whole-file rewrites — fits in one request. On Kyma it serves through an OpenAI-compatible endpoint with automatic failover to a second independent route. Prompt caching is supported and repeated prefixes bill at this model’s cached input rate. Every response carries the exact request cost in usage.cost and names the model that answered in the X-Kyma-Model header.

Specs

Field	Value
Model ID	`gemini-3.7-flash`
Best for	High-volume multimodal work at 1M context where the reply itself is long
Context window	1.048576M
Max output tokens	66K
Input modalities	Text, Image, Video, File, Audio
Output modalities	Text
Tool calling	Yes
Structured outputs	Yes
Prompt caching	Yes
Speed	Fast
Cost band	Balanced
Release stage	Stable

Pricing

	Per 1M tokens
Input	$0.51
Output	$2.53

Use this when

Long-form structured extraction — Reads a 1M-token corpus and emits tens of thousands of tokens of schema-constrained JSON in a single response.
Whole-document translation and rewriting — The 64K output ceiling fits an entire long document’s rewritten text without splitting the job into chunks.
Multimedia review — Takes video, audio and images alongside a text prompt and returns a long written analysis in one pass.
High-volume multimodal agents — Tool calling, reasoning and structured outputs on one request, at the Flash tier’s cost and latency.

Not ideal for

Do not reach for this when a short reply is all you need and cost is the deciding factor — the cheaper Flash tiers answer the same short prompts, and the large output ceiling buys nothing you will use.

Pick something else when

You need the cheapest 1M-context tier and replies stay short: use gemini-3.5-flash-lite.
You want the previous Flash generation at the same list rate: use gemini-3.6-flash.
You need reasoning tuned for code rather than for mixed media: 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-3.7-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

How is this different from Gemini 3.6 Flash? Two things: the output ceiling rises from 8,192 to 65,536 tokens, and structured outputs are supported where 3.6 Flash does not support them. Both models take a 1M-token context and both accept text, image, audio and video. Does prompt caching work on this model? Yes. Repeated prompt prefixes bill at this model’s cached input rate, and the saving is reported per request in usage.cache_discount. Can it accept file input? Yes. Alongside text, image, audio and video, this tier accepts file input — the widest input set of any model in the Gemini Flash family on Kyma.

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ