PublicAI / publicai/apertus-v1.5-8b-thinking

Apertus v1.5 8B Thinking - access through LLMTR

Apertus v1.5 8B Thinking is a reasoning model that works through problems step by step before answering. The reasoning trace is returned in a separate field rather than mixed into the answer. It is more accurate than the standard 8B version on mathematics, logic puzzles, multi-step analysis, and tasks that need careful reading. Reasoning is on by default and can be turned off by appending `:fast` to the model id (`publicai/apertus-v1.5-8b-thinking:fast`) or by sending `reasoning: false` in the request body; with it off, responses get noticeably shorter and consume fewer output tokens. It handles text and image input, offers a 262,144-token context window, and can produce JSON-formatted output. This variant does not support function calling; use Apertus v1.5 8B for tool-calling flows. Images must be supplied as base64 data URLs.

Technical specifications

Canonical IDpublicai/apertus-v1.5-8b-thinking
ProviderPublicAI
Context window262,144 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext, image

Pricing

A 6% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$0.100000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$0.200000

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":"publicai/apertus-v1.5-8b-thinking","messages":[{"role":"user","content":"Hello"}]}'

Related models