Gemma 4 31B - Kyma API

Overview

Gemma 4 31B is Google’s newest open model and a cheap-tier model on Kyma that accepts images, not just text. It sits in the strong quality tier and is built for multimodal and general-purpose work: send it screenshots, photos, or document scans alongside your prompt and get text back. Coding agents drive most of its traffic here. Requests sent with the vision alias resolve to it. Every call gets automatic failover if a serving path degrades, and prompt caching bills repeated prompt prefixes at this model’s cached input rate, which matters for agents that resend the same long system prompt. The 128K-token context window combines with function calling and structured outputs, so it can read an image and return clean JSON in a single call — a complete loop for vision-driven pipelines.

Specs

Field	Value
Model ID	`gemma-4-31b`
Best for	Multimodal, vision, general
Context window	128,000
Max output tokens	8K
Input modalities	Text, Image
Output modalities	Text
Tool calling	Yes
Structured outputs	Yes
Prompt caching	Yes
Speed	Medium
Cost band	Cheap
Release stage	Stable

Pricing

	Per 1M tokens
Input	$0.08
Output	$0.22

Use this when

Image understanding — Describe, classify, or answer questions about screenshots, photos, and charts — the core workload the vision alias exists for.
Visual data extraction — Vision input plus structured outputs means it can turn receipts, forms, or UI screenshots into validated JSON in one request.
Agent tool use — It supports function calling and already runs real agent traffic in production, from OpenClaw to Claude Code to Hermes Agent.
High-volume general tasks — Cheap-tier pricing with strong-tier quality fits summarization, classification, and chat workloads where cost per call dominates.
Long-context review — The 128K window fits large documents or long agent histories — with or without images attached.

Not ideal for

Extended reasoning problems (it has no reasoning mode) or very long single generations — output is capped at 8K tokens per request.

Pick something else when

You want stronger flagship reasoning: use qwen-3.6-plus.
You need stronger multimodal agent behavior: use kimi-k2.6.
You need 1M context: use gemini-2.5-flash.

Example

from openai import OpenAI

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

response = client.chat.completions.create(
    model="gemma-4-31b",
    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=strong"

FAQ

Is Gemma 4 31B good for vision tasks? Yes — it’s the model Kyma’s vision alias resolves to, and image understanding is what it’s recommended for. It accepts text and images in, returns text out, and pairs vision with structured outputs, so you can go from a screenshot to clean JSON in a single call. When should I pick Gemma 4 31B over a bigger model? When the task involves images, or when volume makes cost the deciding factor. It sits in the cheap cost tier with strong quality, which is why it carries nearly a fifth of all production tokens on Kyma. For problems that need an extended reasoning mode or outputs longer than 8K tokens, reach for a model built for that instead. Why run Gemma 4 31B through Kyma? One OpenAI-compatible endpoint and one API key cover this and every other model on the platform. Every request gets automatic failover, prompt caching bills repeated prefixes at this model’s cached input rate, each response reports its exact cost in usage.cost, and signup includes $0.50 of free credit with no card required.

Alias	Resolves to
`vision`	`gemma-4-31b`

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ

​Related aliases