Solar Mini 4
by Upstage · upstage/solar-mini4 · #37 cheapest of 457 paid models
Prices updated Nov 18, 2026, 12:28 AM UTC · refreshed nightly
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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.05
per 1M tokens
Output
$0.20
per 1M tokens
Blended (3:1)
$0.087
3 input : 1 output
Cache read
$0.0050
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Solar Mini 4 with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.087 | $0.0053 | — |
| 50% | $0.071 | $0.00305 | −42% |
| 90% | $0.057 | $0.00125 | −76% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $8.50e-5 | $0.085 |
| Document summary | 8,000 | 1,000 | $0.0006 | $0.6 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0019 | $1.90 |
| Long-context analysis | 150,000 | 5,000 | $0.0085 | $8.50 |
Performance
Intelligence Index
—
AA composite quality
Coding Index
—
Math Index
—
Agentic Index
—
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,140 |
| UI components | 1,078 |
| Data viz | 1,124 |
| 3D | 1,081 |
| Game dev | 1,095 |
| Code categories | 1,123 |
Specs
Context window
524K
tokens
Max output
131K
tokens
Input modalities
text
Tokenizer
Other