Solar Mini 4
API request failed. The model was not evaluated.
UpstageLanguage modelActive
Solar Mini 4 has no overall index value yet because there are too few independent benchmark results.
n/aOverall indexhigher is better
n/ano measurement yet
Input $0.10 · Output $0.40
$0.18per 1M tokenslower is better
512Ktokens in context≈ 770 A4 pages
n/ano search or usage data
It is cheap: $0.18 per 1M tokens (input and output blended); a typical model costs $1.50.
Solar Mini 4 combines a 512K context window with an MoE model that activates just 3 of its 35 billion parameters per token. For local deployment, the provider specifies a single H100 with 80 GB of memory when using quantized weights.
The model can generate up to 128K output tokens. Upstage offers it through the Console API, Solar Chat, and OpenRouter, as well as for on-premises deployment.
On this page
1 offer, prices in US dollars per 1M tokens, blended from 3 parts input and 1 part output.
| Provider | Input | Output | Cache read | Blended |
|---|---|---|---|---|
| Upstagedirect | $0.10 | $0.40 | $0.01 | $0.18 |
Direct price according to the developer, checked Oct 25, 2026. Open the LLM price index
No subscription access recorded in Germany.
One SVG task with the same fixed settings for every model, without hidden thinking.
API request failed. The model was not evaluated.
The response reached the token limit. No complete recording is available.
Prompt
Generate an SVG of a pelican riding a bicycle
Oct 5, 2026 · 74 s · $0.0016
Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.
Every published result with its source, test setup and comparison models.
Page 1 of 11
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
Page 1 of 11
More models of the same kind as Solar Mini 4, chosen by model line, developer, size, price and release date.
1,000 requests with 2,000 input and 500 output tokens cost $0.4000 with Solar Mini 4.
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
Through the API $0.10 per 1M input tokens and $0.40 output. That is cheap.
512,000 tokens. Separate limits may apply to input and output.
No. Upstage does not publish the weights.
Stated by Upstage
Through the API. Subscription access is not documented in the available plan data.
$0.10 input, $0.40 output per 1M tokens.
Which independent evaluators tested this model. This is coverage, not a quality ranking.
| Evaluator | Test series | Composite indices | Recorded active measurements |
|---|---|---|---|
| Artificial Analysis | 2 | 0 | 3 |
Without vendor claims and historical or disputed results; those stay labelled in the single values.