GreenPT / greenpt/devstral-2-123b-instruct-2512

Devstral 2 123B - access through LLMTR

Devstral 2 123B is a reasoning model tuned for software work, with a 1,000,000-token context window. Tool/function calling was verified over a full two-turn loop. Repeated prompt prefixes are served from a cache and those input tokens bill at a quarter of the normal input rate, which is where a workload that resends a large codebase as the same prefix sees the difference. It does not accept image input; a request containing an image is refused by LLMTR without being charged. The model reasons by default and those tokens bill as output.

Technical specifications

Canonical IDgreenpt/devstral-2-123b-instruct-2512
ProviderGreenPT
Context window1,000,000 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$1.342341
CHAT_COMPLETIONSCACHE_READPER_1M_TOKENS$0.335585
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$5.369364

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":"greenpt/devstral-2-123b-instruct-2512","messages":[{"role":"user","content":"Hello"}]}'

Related models