Agnes AI / agnes/agnes-2.5-flash

Agnes 2.5 Flash - access through LLMTR

Agnes 2.5 Flash is Agnes AI's general-purpose model for chat, coding and agent workflows. It has a 524,288-token context window and a single response can be at most 65,536 tokens. It accepts image and video input alongside text, supports tool/function calling (including forced and named tool choice) and schema-enforced JSON output, and streams. Repeated prompt prefixes are served from a prompt cache. The model reasons by default; add the `:fast` suffix when you want a direct answer, or `:think` to force reasoning back on. Reasoning tokens are billed as output. Images and video must be sent as base64 data URLs — this upstream cannot fetch remote URLs, so a public https:// image link is rejected. The model is currently offered free, under a request quota counted over a rolling 24-hour window plus a short-window rate limit; a refused request tells you when to retry.

Technical specifications

Canonical IDagnes/agnes-2.5-flash
ProviderAgnes AI
Context window524,288 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext, image, video

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_COMPLETIONSCACHE_READPER_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":"agnes/agnes-2.5-flash","messages":[{"role":"user","content":"Hello"}]}'

Related models