Solar Mini 4
Solar Mini 4 (upstage/solar-mini4) is a language model from Upstage on the OceanToken API at $0.10 per 1M input tokens and $0.40 per 1M output tokens, with a 524K-token context window and reasoning, tool calling and structured outputs.
- Context window
- 524K tokens
- Max output
- 131K tokens
- Input
- text
- Output
- text
LearnWhat Solar Mini 4 is and what it can do
What is 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.
- Per 1M input / output tokens
- $0.10 / $0.40
- Context window
- 524K
- Input
- text
Starting price
Up to 131K output per reply
Output: text
What Solar Mini 4 can do
Multi-step reasoning
Tool-using agents
Structured outputs (JSON)
CompareHow its price and specs stack up
Solar Mini 4 vs similar models: price
What you pay for Solar Mini 4 and the models most like it: the same kind of work, from the families we feature, priced within about three times of it.
Solar Mini 4Upstage
GPT-6 LunaOpenAI
Qwen3.8 FlashQwen
DeepSeek V4.1 Flash (1017)DeepSeek
GLM 5.3 FlashZ.ai
MiniMax M3MiniMax
Solar Mini 4 vs GPT-6 Luna
GPT-6 Luna costs $0.27: 1.1× the price of Solar Mini 4.
−10% at the top tier
Solar Mini 4 vs Qwen3.8 Flash
Qwen3.8 Flash costs $0.295: 1.2× the price of Solar Mini 4.
−25% at the top tier
Solar Mini 4 vs DeepSeek V4.1 Flash (1017)
DeepSeek V4.1 Flash (1017) costs $0.525: 2.1× the price of Solar Mini 4.
−40% at the top tier
Solar Mini 4 vs GLM 5.3 Flash
GLM 5.3 Flash costs $0.325: 1.3× the price of Solar Mini 4.
Solar Mini 4 vs MiniMax M3
MiniMax M3 costs $0.75: 3.0× the price of Solar Mini 4.
Solar Mini 4 specs
The technical card for Solar Mini 4, from the OceanToken catalog.
- Context window
- 524K tokens
- Max output
- 131K tokens
- Input
- text
- Output
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured outputs
- Yes
- Prompt caching
- Reads $0.01
524,288
131,072
reasoning_effort
tool_choice
response_format
official price, at every tier
Solar Mini 4 model ID and endpoint
- OceanToken model ID
upstage/solar-mini4- OpenAI-compatible base URL
https://api.oceantoken.ai/v1- Endpoint
POST /v1/chat/completions
Buy and buildWhat it costs and how to send your first request
Solar Mini 4 API pricing
Prices come from the OceanToken catalog as of November 5, 2026. You pay per use from a prepaid balance, with no subscription.
- Input
- $0.10 / 1M tokens
- Output
- $0.40 / 1M tokens
- Cached input
- $0.01 / 1M tokens
OceanToken starting price as of November 5, 2026. The console always shows the current price. How tiers work
Add credits Specs, request sample and alternatives in the docsSolar Mini 4 cost calculator
Pick a typical request or enter your own token counts. The calculator uses the starting prices on this page and shows the same workload on the models compared above.
- Per request
- $0.0076
- Per month
- $7.60
The same workload per month
At the starting price (tier 1). Cached input is billed at the cache-read price; cache writes are left out because they depend on how often your prompt prefix changes. Your console shows the rate for your tier.
What a request costs
| Request | Input tokens per request | Output tokens per request | Cost |
|---|---|---|---|
| Chat reply | 2,000 | 600 | $0.00044 |
| Agent step | 60,000 | 4,000 | $0.0076 |
| Long document summary | 400,000 | 12,000 | $0.04 |
Input and output tokens at the starting price above, with no caching.
How to use Solar Mini 4 on OceanToken
Three steps from no account to a working request. The same key and balance work for every model in the catalog.
Create an account and get an API key
Create an OceanToken account, then create a key. One key works for every model your account can use.
Add credits
OceanToken is prepaid: add credits, and each request is billed from that balance. Your console shows the rate for your tier.
Call Solar Mini 4 from your code
Point an OpenAI SDK at
https://api.oceantoken.ai/v1and use the model IDupstage/solar-mini4. The code below sends one request.Get API Key from openai import OpenAI # Your API Key from the OceanToken console client = OpenAI(base_url="https://api.oceantoken.ai/v1", api_key="YOUR_API_KEY") reply = client.chat.completions.create( model="upstage/solar-mini4", messages=[{"role": "user", "content": "Hello"}]) print(reply.choices[0].message.content)# Your API Key from the OceanToken console curl https://api.oceantoken.ai/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "upstage/solar-mini4", "messages": [{"role": "user", "content": "Hello"}]}'
Solar Mini 4 API: frequently asked questions
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.
Solar Mini 4 costs $0.10 per 1M input tokens and $0.40 per 1M output tokens. Cached input costs $0.01 per 1M tokens. These are OceanToken starting prices as of November 5, 2026, charged per use to your prepaid balance. The console always shows the current price.
Solar Mini 4 has a context window of 524K tokens (524,288 tokens).
Solar Mini 4 supports tool calling, structured outputs and reasoning. It takes text input and returns text. The catalog does not list image input (vision) for it.
Send requests to https://api.oceantoken.ai/v1/chat/completions with the model ID upstage/solar-mini4 and your OceanToken API key. The API is OpenAI-compatible, so an OpenAI SDK needs only the base URL https://api.oceantoken.ai/v1 and your key. The Responses API and the Anthropic Messages API (/v1/messages) work too. The same OceanToken API key works for every model your account can use. Full reference: docs.oceantoken.ai.
OceanToken is prepaid. Open Credits in the console, choose an amount and pay by card on Stripe's hosted checkout page (Link works too). Your balance updates a few seconds after payment. Have a trial code? Redeem it on the same page.
Purchased credits are valid for 12 months from the date of purchase. Credits from trial codes, promotions or gifts may have a shorter validity. All purchases are final and non-refundable, except where the law requires a refund. Section 6 of the Terms of Service has the details.
Not if the request never ran: a request refused for an insufficient balance or by a safety check, or one whose provider fails before returning any output, is not charged. A video job that fails releases the amount it held. If a request breaks off after the model has started producing output, for example a stream cut off part-way, you pay for the tokens that were processed and generated for it.
Sources
- OceanToken model catalog: every price, context window, input, output and parameter on this page (November 5, 2026).
By the OceanToken team, from the catalog and the sources above.
Whatever you want.