GeniusRelay
EN中文Sign upConsole

Upstage: Solar Mini 4

solar-mini4

CompareAPIGet an API keyGet an API key

Upstage's compact 35B-parameter mixture-of-experts model with 3B active parameters and a 524K context window. Built for fast, cost-efficient agentic tasks, with strong Korean and English support.

Modalities

Text → Text

Input / output price

$0.065 / $0.260 per 1M

Context

524K · max output 131K

Capabilities

Tool callingLong context

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$0.065
Output$0.260
Cached input$0.0065

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00040
Per day
$0.2015
Per month (30 days)
$6.04

Solar Mini 4: input $0.065/M · output $0.26/M · cached input $0.0065/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": "solar-mini4", "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 solar-mini4.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "solar-mini4",
    "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 Solar Mini 4 billed?
Input is $0.065 and output is $0.260 per million tokens; cached input is $0.0065. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
524K 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.