All models
Model card

Gemma 4 31B

sdn-gemma-4-31bGeneral purposeLive in the catalog

The larger Gemma in the catalog, and the one that earns a workhorse slot rather than a budget one: it reasons when asked, calls tools cleanly, and holds 256K of context at a price that still reads like a small model's. The natural step up from Gemma 4 26B once the turns have started to need real thought rather than just room to read.

Context window256K tokens
Input · per Mtok$0.14
Output · per Mtok$0.4
Served bySideren engine
Where it earns its keep[01/03]
  • 01Reasoning and tool calling at near-floor pricing
  • 02256K context for long histories and documents
  • 03The step up from Gemma 4 26B when turns need thought
Capabilities
Tool callingYes

Strict, schema-faithful tool calls, enforced by the engine on every request — safe to build an agent loop on.

ReasoningYes

Thinks before it answers. Budget max_tokens generously — hidden reasoning counts against it.

VisionNo

Text-only.

Behind the endpoint[02/03]

One endpoint. Served by our engine.

Gemma 4 31B is served through the Sideren engine — zero-downtime serving is the design target, not a status-page apology. You request it by name; everything else is our problem.

Call it by name
curl https://api.sideren.io/v1/messages \
  -H "x-api-key: sdn_your_key" \
  -H "content-type: application/json" \
  -d '{
    "model": "sdn-gemma-4-31b",
    "max_tokens": 1024,
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

OpenAI-style clients work too — send the same model name to /v1/chat/completions with a Bearer key. See the docs for both dialects.

Put your agent on real infrastructure

Your agent doesn't change.
Everything underneath does.

$export ANTHROPIC_BASE_URL=https://api.sideren.io

Start free · no card · Starter from $5/mo