LLMTR / llmtr/ornith-1-35b

Ornith 1.0 35B - access through LLMTR

LLMTR Ornith 1.0 35B is a Turkey-hosted first-party coding model. It is trained to carry out multi-step tasks inside real repositories rather than to emit single-shot code: browsing a codebase, editing files, running tests, and chaining tools. It is invoked through the OpenAI-compatible Chat Completions interface, offers a 32K context window, and supports tool calling and prompt-cache reads. The model always reasons step by step before answering and returns those steps separately in `message.reasoning_content`; this cannot be turned off, so budget at least 1500 `max_tokens` or the budget is consumed during reasoning and the content comes back empty. Generation takes considerably longer than on lightweight chat models, so `stream: true` is recommended. Requests are processed on our servers in Turkey and are not forwarded to a third-party provider.

Technical specifications

Canonical IDllmtr/ornith-1-35b
ProviderLLMTR
Context window32,768 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$2.00
CHAT_COMPLETIONSCACHE_READPER_1M_TOKENS$0.500000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$5.00

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":"llmtr/ornith-1-35b","messages":[{"role":"user","content":"Hello"}]}'

Related models