Upstage / upstage/solar-pro2

Solar Pro 2 - access through LLMTR

Solar Pro 2 is Upstage's enterprise model for complex reasoning and generation. It has a 65,536-token context window, and generated tokens come out of that same window. Reasoning is off by default. You select a level with `reasoning_effort` across minimal, low, medium, and high; the model starts thinking at `medium`. There is no `none` level on this model — sending it returns an error listing the levels that do exist. One important difference: where Solar Pro 4 and Pro 3 return the reasoning trace in the response's `reasoning` field, Solar Pro 2 does not return it at all. The reasoning tokens are still produced, counted in `usage.completion_tokens_details.reasoning_tokens`, and billed as output — so you see the cost without seeing the content. Every `tool_choice` value works for native tool/function calling, and it produces JSON object output as well as schema-conforming structured output. Repeated prompt prefixes engage the prompt-cache discount. It accepts text only; image and audio input are not supported. Official language coverage is English, Korean, and Japanese.

Technical specifications

Canonical IDupstage/solar-pro2
ProviderUpstage
Context window65,536 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$0.150000
CHAT_COMPLETIONSCACHE_READPER_1M_TOKENS$0.015000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$0.600000

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"upstage/solar-pro2","messages":[{"role":"user","content":"Hello"}]}'

Related models