Интерфейс моделей ИИ

Провайдер · 2026-11-15

augure

4 канонических моделей6 записей всего (включая производные)
МодельВход / 1MВыход / 1MКонтекстПровайдерыТеги
Tofino 3$0.430$1.42262K1tools · json · vision
Ossington 5$1.07$2.14262K1tools · json · reasoning · vision
Rosedale One$1.78$4.271.05M1tools · json · reasoning · vision
Ossington 4.1$1.78$4.27262K1tools · json · reasoning · vision
Qwen3.8 Flash Nextпроизводная$1.42$2.85262K1tools · json · reasoning · open-weights
GLM-5.3производная$2.14$4.99262K1tools · json · reasoning · open-weights

Frequently asked questions

How many AI models does augure offer?

We track 4 canonical augure models plus 2 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily.

Which augure model is the cheapest?

Tofino 3 is currently the lowest-priced augure model, at $0.430 per 1M input tokens and $1.42 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which augure model has the largest context window?

Rosedale One leads at 1.05M tokens. This is the total of prompt + completion.

Which augure models support tool calling?

Multiple augure models support tool calling, with Tofino 3 being a popular pick. The capability column in the table above marks every model with augure tool-calling support.

Which augure models accept image input?

Tofino 3 accepts image input. Other vision-capable augure models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.

What are the best alternatives to augure?

Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.

How fresh is this augure pricing data?

Daily. Our pipeline syncs every morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.

Последнее обновление:

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.