Agnes 2.5 Pro Beta
AI model by Sapiens AI. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Agnes 2.5 Pro Beta is a budget-tier option from Sapiens AI at $0.30/M output tokens. Despite the low price, it scores competitively on Coding Index (62.3) and Intelligence Index (49.1) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Agnes 2.5 Pro Beta reports 168 tok/s output speed and 2000ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, Agnes 2.5 Pro Beta costs $0.13 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-09-06.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Agnes 2.5 Pro BetaCurrent | $0.10 | $0.30 | 168 tok/s |
| Gemma 4 12B (Non-reasoning) | $0.10 | $0.30 | 108 tok/s |
| Step 3.5 Flash 2603 | $0.10 | $0.30 | 205 tok/s |
| Mistral Small 3.1 | $0.10 | $0.30 | 138 tok/s |
| Mistral Small 3.2 | $0.10 | $0.30 | 140 tok/s |
| Nemotron 3 Nano Omni 30B A3B Reasoning | $0.07 | $0.30 | 328 tok/s |