Skip to content
LLMTR Docs

Yandex

Yandex's own Alice AI and YandexGPT models are addressed in the LLMTR catalog with the yandex/ prefix, exactly as the catalog spells them. All five models work on the /v1/chat/completions endpoint.

Model Context Input / Output ($/1M)
yandex/alice-ai-llm 131,072 4.09836 / 9.836064
yandex/alice-ai-llm-flash 65,536 0.819672 / 1.639344
yandex/yandexgpt-5.1-pro 32,768 6.557376 / 6.557376
yandex/yandexgpt-5-pro 32,768 9.836064 / 9.836064
yandex/yandexgpt-5-lite 32,768 1.639344 / 1.639344

On Alice AI LLM Flash, repeated prompt prefixes can be served from a cache; those tokens bill at $0.204918 per 1M. The other four models have no cache discount.

Chat

Section titled “Chat”
Terminal window
curl "$LLMTR_BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "yandex/alice-ai-llm-flash",
    "messages": [
      { "role": "system", "content": "Answer briefly and clearly." },
      { "role": "user", "content": "Summarise this customer email in three bullet points." }
    ],
    "max_tokens": 1024
  }'

All five models support tool/function calling, streaming, and JSON output with response_format: { "type": "json_object" }.

Limits

Section titled “Limits”
  • The models accept text only. A request containing an image is refused with 400 unsupported_input and is not charged.
  • reasoning_effort is not supported on this provider; a request that sends it is refused with 400 invalid_request.
  • If a long answer comes back with finish_reason: "length", raise max_tokens and retry.