Upstage · Released Dec 12, 2023SOLAR 10.7B Instruct v1.0
Upstage depth-upscaled 10.7B instruction model for single-turn chat.
- Capability
- —No ECI score yet
- Input
- —No listed price
- Output
- —No listed price
- Context
- 4K4K max output
What it costs
No per-token price is published for this model yet.
No per-token price is listed for this model on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for SOLAR 10.7B Instruct v1.0 yet.
The details
- Lab
- Upstage
- Released
- Dec 12, 2023
- Context window
- 4,096 tokens
- Max output
- 4,096 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- No
- Structured output
- No
- Weights
- Open weights · CC-BY-NC-4.0
More from Upstage
About SOLAR 10.7B Instruct v1.0
How much does SOLAR 10.7B Instruct v1.0 cost?
SOLAR 10.7B Instruct v1.0 has no published per-token API price on models.dev yet.
What is the context window of SOLAR 10.7B Instruct v1.0?
SOLAR 10.7B Instruct v1.0 accepts up to 4,096 tokens per request and can write up to 4,096 tokens in one response.
How good is SOLAR 10.7B Instruct v1.0?
Epoch AI has not published a Capabilities Index score for SOLAR 10.7B Instruct v1.0 yet.
Is SOLAR 10.7B Instruct v1.0 open source?
Yes. Upstage publishes the weights under the CC-BY-NC-4.0 licence, so it can be downloaded and self-hosted.
What inputs does SOLAR 10.7B Instruct v1.0 support?
SOLAR 10.7B Instruct v1.0 accepts text and replies in text. It is not a dedicated reasoning model, does not support tool calling.
When was SOLAR 10.7B Instruct v1.0 released?
Upstage released SOLAR 10.7B Instruct v1.0 on Dec 12, 2023.
What are the best alternatives to SOLAR 10.7B Instruct v1.0?
The closest current models from other labs on capability, price and release date are Qwen Plus Character (Japanese) (Alibaba (Qwen), $0.50 / $1.40), Hermes 2 Pro Llama 3 8B (Nous Research, $0.14 / $0.14), Vision Large (Vispark, $7.37 / $22.11) and Codestral (Mistral AI, $0.30 / $0.90).