Agnes 2.5 Pro Beta
Agnes 2.5 Pro Beta by Sapiens AI is a paid reasoning model with text and image input, tool calling, Thinking mode, and agentic terminal task support.
Model Overview
Capabilities, design details, and architectural traits
Agnes 2.5 Pro Beta - Paid reasoning model with text and image input
Agnes 2.5 Pro Beta is a paid reasoning model from Sapiens AI, positioned above flash-class models in reasoning depth. It targets production workloads such as complex code tasks, science and math reasoning, long-context understanding, knowledge-intensive Q&A, and agentic terminal or workflow tasks. It uses the same request parameters, response formats, supported text protocols, and context limits as the other Agnes 2.5 Pro models.
Key characteristics
| Trait | Detail |
|---|---|
| Model type | Paid reasoning model with text and image input, text output |
| Multi-protocol API | Serves three endpoints: Chat Completions, Responses, and Messages |
| Thinking mode | Optional thinking field enables Thinking mode in Anthropic-compatible requests |
| Agentic terminal tasks | Designed for agentic coding workflows and terminal or workflow tasks |
| Tool calling | OpenAI-compatible function calling and external tool orchestration |
| Image understanding | Accepts image URL inputs for visual analysis and multimodal reasoning |
| Long-context analysis | Handles long documents, structured context, and multi-turn reasoning |
Integration pattern
The model is called through the Agnes AI API using the live model ID agnes-2.5-pro-beta. It supports streaming responses and standard sampling parameters such as temperature, top_p, and max_tokens, plus the chat_template_kwargs extension field for OpenAI-compatible requests.
Benchmark Performance
Independent evaluations · Artificial Analysis
Accuracy & Capability Details
Compare Models Side-by-Side
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | |||
|---|---|---|---|
| General Info | |||
| Provider | Sapiens AI | Anthropic | Anthropic |
| Release Date | August 26, 2026 | September 22, 2026 | September 28, 2026 |
| Knowledge Cutoff | - | - | Jun 2026 |
| Context & Limits | |||
| Context Window | 262K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | $0.10 Best Input Pricing | $4 | $2 |
| Output Pricing | $0.30 Best Output Pricing | $20 | $10 |
| Modalities | |||
| Inputs | text | textimagefile | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 35.2 | 57.6 Best Intelligence Index | 56.0 |
| Coding Index | 62.3 | - | - |
| Agentic Index | 43.8 | - | - |
Humanity's Last Exam
Extremely difficult logical reasoning and knowledge.
Long Context Reasoning
Logical reasoning over long context windows.
SciCode Benchmark
Scientific coding and mathematical modeling.
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
Explore more from Sapiens AI
Other models by Sapiens AI
Top AI Models
Leading alternatives by intelligence score
Claude Opus 5.5
Muse Spark 1.3
GPT-6 Astra
