Solar Pro 4 with Jev
Solar Pro 4 is a model from Upstage, released 2026-08-10. It costs $0.090 per million input tokens and $0.360 per million output tokens, reads up to 524K tokens of context, and writes up to 131,072 tokens in one reply. Through llm11, set model to upstage/solar-pro4.
- Input price
- $0.090 / 1M
- Output price
- $0.360 / 1M
- Context window
- 524K tokens
- Max output
- 131K tokens
- Cached input
- $0.018 / 1M
- Released
- 2026-08-10
- Accepts
- text
Read from the provider's prompt cache
Read from the live catalogue and refreshed daily. At blended list price, 81% of the 332 priced models we can call cost more.
Using Solar Pro 4 with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Solar Pro 4 does the answering when Jev sends it work, or when you name it yourself. At list price Solar Pro 4 falls in the llm11-fast band, but no pack routes to it because Upstage is not one of the labs the packs draw from. You can still pin it: pass upstage/solar-pro4 as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for Solar Pro 4 with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00012 | $0.117 |
| Question over retrieved documents | 4,000 / 500 | $0.00054 | $0.540 |
| Long document summary | 30,000 / 1,000 | $0.00306 | $3.06 |
Cheaper models to try
The catalogue has no benchmark score for Solar Pro 4, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Meta Llama 3.3 70B Instruct | $0.100 | $0.320 | 131K | |
| Qwen Qwen3 235B A22B Instruct 2507 | $0.087 | $0.350 | 262K | |
| Google Gemma 4 31B | $0.090 | $0.340 | 262K | |
| Mistral Ministral 3 8B 2512 | $0.150 | $0.150 | 262K |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="upstage/solar-pro4",
messages=[{"role": "user", "content": "Hello"}],
)More from Upstage
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Solar Mini 4 | $0.050 | $0.200 | 524K | |
| Solar Pro 3 | $0.150 | $0.600 | 131K |
Questions
- What is Solar Pro 4 with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Solar Pro 4 does the answering when Jev sends it work, or when you name it yourself. At list price Solar Pro 4 falls in the llm11-fast band, but no pack routes to it because Upstage is not one of the labs the packs draw from. You can still pin it: pass upstage/solar-pro4 as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Solar Pro 4 a System One model?
- No. Solar Pro 4 answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Solar Pro 4 cost?
- $0.090 per million input tokens and $0.360 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00054, so a thousand of them is about $0.540. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Solar Pro 4 context window?
- 524,288 tokens, with up to 131,072 tokens in a single reply.
- Does Solar Pro 4 support tool calling and structured output?
- The catalogue lists tool calling, structured output and reasoning controls.
- Can I use Solar Pro 4 through llm11?
- Yes. Set model to upstage/solar-pro4 on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Solar Pro 4?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Solar Pro 4 falls in the llm11-fast band, but no pack routes to it because Upstage is not one of the labs the packs draw from. You can still pin it: pass upstage/solar-pro4 as model and routing steps aside while verification still runs.
- What is a cheaper alternative to Solar Pro 4?
- Nearest in price and below it: Meta Llama 3.3 70B Instruct at $0.100 in and $0.320 out, Qwen Qwen3 235B A22B Instruct 2507 at $0.087 in and $0.350 out and Google Gemma 4 31B at $0.090 in and $0.340 out. The catalogue has no benchmark score for Solar Pro 4, so this is a price ordering. It does not claim these answer as well.