KI‑Modell‑Intelligenz

Anbieter · 2026-10-08

agnes

3 kanonische Modelle3 Einträge insgesamt (inkl. Derivate)
ModellEingabe / 1MAusgabe / 1MKontextHosterTags
Agnes 2.5 Pro Alpha$0.450$0.9001M1tools · json · reasoning · vision · open-weights
Agnes 2.0 FlashUnbekanntUnbekannt512K1tools · json · reasoning · vision
Agnes 2.5 FlashUnbekanntUnbekannt512K1tools · json · reasoning · vision

Frequently asked questions

How many AI models does agnes offer?

We track 3 canonical agnes models. The list is recomputed daily.

Which agnes model is the cheapest?

Agnes 2.5 Pro Alpha is currently the lowest-priced agnes model, at $0.450 per 1M input tokens and $0.900 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which agnes model has the largest context window?

Agnes 2.5 Pro Alpha leads at 1M tokens. This is the total of prompt + completion.

Which agnes models support tool calling?

Multiple agnes models support tool calling, with Agnes 2.5 Pro Alpha being a popular pick. The capability column in the table above marks every model with agnes tool-calling support.

Which agnes models accept image input?

Agnes 2.5 Pro Alpha accepts image input. Other vision-capable agnes models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.

What are the best alternatives to agnes?

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 agnes 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.

Zuletzt aktualisiert:

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.