Solar Pro 4
Upstage · released Aug 10, 2026
- Type
- Closed
- Input
- $0.090
- Output
- $0.36
- Cached
- $0.018
List price · per 1M tokens · Upstage at 524K context · source ↗
Our take
Written Sep 10, 2026Solar Pro 4 is a hosted-only text model from Upstage built for long-document work, handling up to 524,288 tokens in a single request. Its agent-task scores are weak across every measured sub-skill, so treat it as a context-length specialist rather than an autonomous agent.
Pick this when you need half-a-million-token context at a low per-token rate, or when you want throughput choice from the same host. Skip it if you are building autonomous agents, recovering from failed commands, or need measured proof of steerability or tool-use quality.
The case for it
- Half-a-million-token request limit at a low per-token rate.
- Three throughput tiers from Upstage — 35, 33, or 10 tokens per second — with no price difference.
The case against it
- Poor recovery from failed commands in agent sessions, the weakest of its five measured sub-scores.
- Every agent sub-score is negative, with no positive skill to offset the recovery deficit.
- Near-zero measured steerability and tool-use quality, with no benchmark evidence of strength in either.
How good is it?
A closed text model for everyday writing and chat, though multi-step tasks and tool calls are not its strength.
- carrying out multi-step tasks for youArena Agent · 53rd of 55
- calling tools to carry out requestsArena Agent · Tool use · 51st of 55
- changing course when you give new instructionsArena Agent · Steerability · 50th of 55
- getting back on track after a step failsArena Agent · Recovery · 49th of 55
EverydayGeneral questions and everyday reasoning
Not yet scored on Arena Text (overall).
CodingWriting and fixing code on its own
Not yet scored on Arena Coding.
AgenticPlanning, calling tools, staying on task
Arena Agent53rd of 55 · −0.162
Arena Agent is the only board that has scored it for this.
WritingDrafting and rewriting prose
Not yet scored on Arena Creative Writing.
Placings on Arena's agent boards, from live sessions people ran themselves. A model can lead on one of these and sit mid-field on the others.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model5 scoresEvery figure we hold, from 5 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked 4 hours ago — each listing carries its own date.
Upstage, through OpenRouter
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts Upstage on 524K of context.
- per 1M tokens
- $0.090 in / $0.36 out
- Context served
- 524K
- Throughput
- ~67 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.090 / $0.36checked 4 hours ago | 524K | not measured | Unknown | Unknown | Unknown |
| UpstageThrough OpenRouter | $0.090 / $0.36checked 4 hours ago | 524K131K max reply | 67 tok/s | No | Yesunknown period | Confirmed |
OpenRouterAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| UpstageThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
Models people weigh against Solar Pro 4
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text in, text out
- Catalogue slug
- upstage-solar-pro-4