Upstage Models

1 modelGeneral models from $0.3/M inputUp to 524K context

Usage

Last 7 days · 2026-09-25 to 2026-10-15

Tokens

164M

Requests

435

Models in use

1 of 1

Tokens per day, stacked by model

067.4M135M09-252026-09-25 — 28,292,495 tokens solar-pro4: 28,292,4952026-09-26 — 134,799,535 tokens solar-pro4: 134,799,5352026-09-27 — 0 tokens2026-10-10 — 74,285 tokens solar-pro4: 74,2852026-10-12 — 290 tokens solar-pro4: 2902026-10-14 — 579,750 tokens solar-pro4: 579,7502026-10-15 — 685 tokens solar-pro4: 685

Which models that traffic went to

  1. Solar Pro4100.0%164M

Share of 164M tokens.

The two views disagree on purpose: a model can take a large share of the calls and a small share of the tokens — many short requests — or the reverse. Which one matters depends on whether your cost is driven by call volume or by prompt length. Measured on AIHubMix over the last 7 days, counting the 1 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 1 Upstage Models

Open in model list
Upstage models on AIHubMix with input and output modalities, context length, maximum output, price per million tokens including cache read and cache write rates, and measured throughput and latency.
Modalities
solar-pro4Takes text, returns text.524K131K$0.3$1.2/M$0.06/M5 tok/s0.56 s

Prices are USD per million tokens; cache read and cache write are the rates for prompt-cache hits and for writing a prompt into the cache. Throughput and latency are measured on AIHubMix — the same figures the model detail page shows — not vendor claims. A dash means the catalog does not publish that field for that model, which is not the same as the model not supporting it.

Upstage on AIHubMix

Which Upstage model should I start with?

solar-pro4 at $0.3/M input — the cheapest entry here that declares a token price, and it carries a 524K context.

How is cached input billed?

The Cache read column is the rate for input tokens served from the prompt cache — for example solar-pro4 bills cache hits at 20% of the input rate. Cache write is the surcharge for putting a prompt into the cache in the first place, and only a few upstreams bill it separately. A dash in either column means the catalog carries no cache rate for that model, so plan on paying the full input rate.

Do I need a separate Upstage account?

No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.

Other Model Authors

See all model authors →
Qwen
154 modelsOpenAI
143 modelsGoogle
89 modelsZ.AI
71 modelsLlama
53 models

Start calling Upstage in one line

One key, one endpoint, 924 models across 43 model authors.

Get API keyRead the docs

© 2023 - 2026 AIHubMix, LLC

Product

Developer

Company

Terms & Policies