Get started

Solar Mini 4

Timed at 90.9 tok/s, on 6 Design Arena boards, and not scored by Artificial Analysis.

retrieved sha256 · 0bb53a77713f

Models/Upstage/Solar Mini 4USD per 1M tokens · as OpenRouter routes it
upstage/solar-mini4Upstage · base listing · Other tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.05per 1M tokens
Output$0.20per 1M tokens
Cached input$0.005per 1M tokens
Context524k524,288 tokens
What the list says · the fields OpenRouter publishes for this id9 fields
AuthorUpstage
Listed
Canonical idupstage/solar-mini4-20260922
Context524,288 tokens
Max output131,072 tokens
Modalitiestext → text
TokenizerOther
Reasoningoptional, off by default · effort max, xhigh, high, medium, low, minimal, none, medium by default
Moderationnot moderated by OpenRouter

Measured speed

34,023 requests · 2 endpoints · 30-minute window
Throughput90.9 tok/sMedian output rate, weighted across the 2 endpoints serving it by the requests each answered.the speed board
First token1.72sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread61 to 93The slowest and the fastest route serving this model, in tokens per second. Speed is a property of the route, not of the weights.the board, fastest first

OpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.

Every endpoint

2 priced · 2 timed · cheapest first
  1. Upstageupstage/zdr · listed · 50% off$0.05$0.20$0.005not declared131k61 tok/s252.35s2,189 req100%
  2. Upstageupstage · listed · 50% off$0.05$0.20$0.005not declared131k93 tok/s331.68s31,834 req100%

Each track runs from a route's p90, the rate nine in ten of its requests met or beat, up to its median. Weighted by requests, the figure above reports where the traffic went rather than what one route does: 1 of the 2 timed routes are slower than it, and the middle route runs at 77 tok/s. The widest median-to-p90 gap is Upstage's, 2.82x.

Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . 2 of the 2 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Upstage (upstage) at 97.81% on 9 Nov 2026 and Upstage (upstage/zdr) at 98.56% on 9 Nov 2026. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.

Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .

What each seller accepts

13 parameters · 2 sellers
  1. frequency_penaltyevery seller
  2. include_reasoningevery seller
  3. max_tokensevery seller
  4. parallel_tool_callsevery seller
  5. presence_penaltyevery seller
  6. reasoningevery seller
  7. reasoning_effortevery seller
  8. response_formatevery seller
  9. structured_outputsevery seller
  10. temperatureevery seller
  11. tool_choiceevery seller
  12. toolsevery seller
  13. top_pevery seller

All 13 are accepted by every one of the 2 sellers that publish a list. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.

Price position

342 priced models

Blended $0.088 per million tokens, 3 in to 1 out: cheaper than 318 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.

Measured quality

145 models with an index · 132 on a design arena board

Each mark is one board this model stands on, placed at the share of that board it scores above, and led to its number in the list under the rule. The columns and the ledger below carry the figures.

Intelligence Indexnot scoredArtificial Analysis has not scored this model on its Intelligence Index.the intelligence leaderboard
Coding Indexnot scoredArtificial Analysis has not scored this model on its Coding Index.the coding leaderboard
Agentic Indexnot scoredArtificial Analysis has not scored this model on its Agentic Index.the agentic leaderboard
  1. 3D scenes · Models1081 Elowin rate 24.6% · source rank 98the board, 113 ranked
  2. Code · Models1123 Elowin rate 29.8% · source rank 103the board, 120 ranked
  3. Data visualisation · Models1124 Elowin rate 31.9% · source rank 95the board, 110 ranked
  4. Game development · Models1095 Elowin rate 27.7% · source rank 99the board, 120 ranked
  5. UI components · Models1078 Elowin rate 26.0% · source rank 108the board, 116 ranked
  6. Websites · Models1140 Elowin rate 32.1% · source rank 100the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals

Epoch AI has not placed Solar Mini 4 on its Capabilities Index, or places it under a name the pairing does not reach. Epoch places a model once four of its benchmarks carry a result.

Benchmark results

none of 6 boards

None of the 6 openly licensed boards Vitna mirrors has published a result for Solar Mini 4 under a name that matches its listing, and names are matched to the catalog exactly and never guessed. Every board, with its licence and what its publisher measures, is on /benchmarks.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Vitna ran none of these evaluations and adjusted none of these figures.