Back to Models
solar-mini4

Solar Mini 4

Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...

9/23/2026
524,288 tokens
Input: ¥8.935/M
Output: ¥35.74/M

Specifications

Modalities

Input
text
Output
text

Supported Parameters

frequency_penalty
include_reasoning
max_tokens
parallel_tool_calls
presence_penalty
reasoning
reasoning_effort
response_format
structured_outputs
temperature
tool_choice
tools
top_p

Max Output Tokens

131,072

Reasoning Configuration

Default
Thinking off
Selectable effort levels
max
xhigh
high
medium
low
minimal
none
Turning thinking off
Possible (reasoning.enabled: false)

How to control thinking, and what it costs

Data policy

Prompt retention
Unknown — we could not confirm
Training
Not used for training

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "solar-mini4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Solar Mini 4 actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

Sure! Let’s count the letter **'r'** in the word **'strawberry'** step by step. **Step 1: Write out the word and its letters** `s t r a w b e r r y` **Step 2: Go through each letter one by one and check if it is 'r'** 1. `s` → not 'r' 2. `t` → not 'r' 3. `r` → **yes** (1st 'r') 4. `a` → not 'r' 5. `w` → not 'r' 6. `b` → not 'r' 7. `e` → not 'r' 8. `r` → **yes** (2nd 'r') 9. `r` → **yes** (3rd 'r') 10. `y` → not 'r' **Step 3: Tally the total** Total 'r' count = 3 **Final answer:** There are **3** letter 'r's in the word **'strawberry'**.
2.5s response239 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

This error occurs because the `users` prop being passed to your `UserList` component is `undefined` (or the component is rendered without that prop), and your code tries to call `.map()` on it. ### 🔍 Why this happens In JavaScript, `undefined.map` is not a function, so calling it throws: ``` TypeError: Cannot read properties of undefined (reading 'map') ``` This commonly happens when: - The parent component doesn't pass the `users` prop at all - The parent passes `users` as `undefined`, `null`, or a non-array value (like a promise, object, or string) - Data hasn't finished loading yet (e.g., fetched from an API asynchronously) ### ✅ How to fix it The most robust solution is to provide a…
9.2s response701 output tokens

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

Here’s a reviewed version of your function, followed by a breakdown of the improvements: ```python import time import requests from requests.adapters import HTTPAdapter from urllib3.util.retry import Retry def get_data(url: str, retries: int = 3) -> list[dict]: """ Fetch JSON from a URL and return a list of active items with name/id. Args: url: The endpoint to request. retries: Number of retry attempts on failure. Returns: A list of dicts matching {'name': str, 'id': any} for active items. """ if retries < 1: raise ValueError("retries must be at least 1") session = requests.Session() retry_strategy = Retry( total=re…
10.8s response1278 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Solar Mini 4 API cost?
On FastMetal, Solar Mini 4 is billed per token in yen: ¥8.94 per 1M input tokens and ¥35.74 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Solar Mini 4 with the OpenAI SDK?
Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "solar-mini4" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Solar Mini 4?
524,288 tokens, shared between the prompt and the response.
What do I need to try Solar Mini 4?
Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Try Solar Mini 4 right now

Solar Mini 4 is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.