# Gemma 4 31B

> Google's newest open model. Multimodal.

Human version: https://kymaapi.com/models/gemma-4-31b
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `gemma-4-31b` — pass this as `model` in the request body
- **Creator**: Google
- **Released**: 2026-04-02
- **Context window**: 128K tokens
- **Max output**: 8K tokens per response — a hard ceiling, not a default
- **Price**: $0.0702 in / $0.2006 out per 1M, cached input 10%
- **Capabilities**: tools, vision, reasoning, caching
- **Alias**: `vision` resolves to this model

## Call it

```bash
curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gemma-4-31b", "messages": [{"role": "user", "content": "Hello"}]}'
```

## Positioning

The second most-used model on Kyma and the one the `vision` alias points to — Google's newest open model, with image understanding at cheap-tier pricing.

## About

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.

On Kyma it is the platform's second most-used model, serving 18.6% of all production tokens — over 370 million — across agents like OpenClaw, Claude Code, and Hermes Agent. Requests sent with the `vision` alias resolve here. Every call gets automatic failover if a serving path degrades, and prompt caching bills repeated prompt prefixes at 10% of the 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.

## Use cases

- **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 → `qwen-3.6-plus`
- You need stronger multimodal agent behavior → `kimi-k2.6`
- You need 1M context → `gemini-2.5-flash`

## See also

- All models: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md
- Other models by Google: https://kymaapi.com/models?q=Google