Sapiens AI

Agnes 2.5 Pro Alpha

AI model by Sapiens AI. Real-time pricing and benchmark data.

Pricing (per 1M tokens)

Input$0.45
Output$0.90
Blended (3:1)$0.56

Source: Artificial Analysis

Performance

Output Speed134 tok/s
Time to First Token1929ms

Median values from Artificial Analysis

Editorial Analysis

Profile. Agnes 2.5 Pro Alpha is a budget-tier option from Sapiens AI at $0.90/M output tokens. Despite the low price, it scores competitively on GPQA Diamond (87.6%) and Coding Index (58.8) — making it a candidate for high-volume production workloads where unit cost dominates.

Latency. On latency, Agnes 2.5 Pro Alpha reports 134 tok/s output speed and 1929ms 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 Alpha costs $0.54 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 2026-07-24.

Compare with similar models

ModelInputOutputSpeed
Agnes 2.5 Pro AlphaCurrent
$0.45$0.90134 tok/s
GLM-4.6V (Reasoning)
$0.30$0.900 tok/s
GLM-4.6V (Non-reasoning)
$0.30$0.900 tok/s
DeepSeek V3 (Dec '24)
$0.36$0.890 tok/s
Trinity Large Thinking
$0.23$0.88142 tok/s
DeepSeek V4 Pro (Reasoning, High Effort)
$0.43$0.8770 tok/s

Example Costs

Single Request
$0.0009
1.0K in / 500 out
1K Requests/day
$0.9000
1.0M in / 500.0K out
10K Requests/day
$9.00
10.0M in / 5.0M out