solar-mini
Efficient model for low-latency assistance, extraction, and routine automation.
- Capability
- —No ECI score yet
- Input
- $0.15per 1M tokens
- Output
- $0.15per 1M tokens
- Context
- 33K4K max output
What it costs
- Input
- $0.15per million tokens
- Output
- $0.15per million tokens
- Blended (3:1)
- $0.15cheaper than 83% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.375 |
| Team assistant25M input + 5M output tokens | $4.50 |
| Production app250M input + 50M output tokens | $45.00 |
Official Upstage API price, as listed on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for solar-mini yet.
The details
- Lab
- Upstage
- Released
- Jun 12, 2024
- Knowledge cutoff
- Sep 2024
- Context window
- 32,768 tokens
- Max output
- 4,096 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- No
- Weights
- Proprietary
- API model ID
solar-minion Upstage- Availability
- 1 API providerlisted on models.dev
More from Upstage
About solar-mini
How much does solar-mini cost?
solar-mini costs $0.15 input / $0.15 output per million tokens (official Upstage API price). At a 3:1 input-to-output mix that is $0.15 per million tokens, cheaper than 83% of the 360 priced models we track.
What is the context window of solar-mini?
solar-mini accepts up to 32,768 tokens per request and can write up to 4,096 tokens in one response.
How good is solar-mini?
Epoch AI has not published a Capabilities Index score for solar-mini yet.
Is solar-mini open source?
No. solar-mini is proprietary; you use it through Upstage’s API or partner platforms.
What inputs does solar-mini support?
solar-mini accepts text and replies in text. It is not a dedicated reasoning model, supports tool calling.
When was solar-mini released?
Upstage released solar-mini on Jun 12, 2024. Its training data runs to Sep 2024.
What are the best alternatives to solar-mini?
The closest current models from other labs on capability, price and release date are Pixtral 12B (Mistral AI, $0.15 / $0.15), Llama-3.2-3B (Meta, $0.10 / $0.335), Phi-4-mini (Microsoft, $0.075 / $0.30) and Command R (Cohere, $0.15 / $0.60).