Voltropy / voltropy/vast-10m-flash-free

Vast-10M Flash - access through LLMTR

Vast-10M Flash is Voltropy's model built on DeepSeek V4.0 Flash with Voltropy's own attention method, VSA (Voltropy Scalable Attention), which extends the context window to 10,119,296 tokens. It is designed for texts that should be read whole rather than in chunks, such as contracts, case files, an entire codebase or log archives. It accepts text only. Tool calling (tool_choice auto, required, a named function and none), JSON mode and structured output with JSON Schema are supported; there is no reasoning mode. A request body can be at most 24 MB. With long prompts and at busy times the first token can take minutes to arrive; use stream: true and set your client's timeout accordingly. It is free until 26 October 2026, 23:59 (TRT), with 10 million tokens per person per day (input and output together).

Technical specifications

Canonical IDvoltropy/vast-10m-flash-free
ProviderVoltropy
Context window10,119,296 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_TOKENSNot available
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENSNot available

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":"voltropy/vast-10m-flash-free","messages":[{"role":"user","content":"Hello"}]}'

Related models