GeniusRelay
EN中文Sign upConsole

Google: Gemma 4 31B Split-Untied

gemma4-31b-splituntied

CompareAPIGet an API key

Blazed-Forge's Split-Untied is a text-only Gemma 4 31B community finetune with an untied BF16 output head, built for creative writing, roleplay, expressive dialogue, and tool use.

Modalities

Text → Text

Input / output price

$0.130 / $0.390 per 1M

Context

33K · max output 33K

Capabilities

RoleplayTool callingOpen weights

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$0.130
Output$0.390
Cached input$0.065

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00070
Per day
$0.3510
Per month (30 days)
$10.53

Gemma 4 31B Split-Untied: input $0.13/M · output $0.39/M · cached input $0.065/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gemma4-31b-splituntied", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to gemma4-31b-splituntied.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma4-31b-splituntied",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is Gemma 4 31B Split-Untied billed?
Input is $0.130 and output is $0.390 per million tokens; cached input is $0.065. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
33K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.