Agnes 3.0 Flash is Agnes's language model. A fast-tier multimodal LLM from Sapiens AI's Agnes series, optimized for low-latency responses.
| Benchmarks | |
|---|---|
| Intelligence Index | #41 |
| GPQA | #20 |
| HLE | #45 |
| Time to First Token | #2 |
| SciCode | #42 |
| LCR | #30 |
| Output TPS | #233 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Agnes 3.0 Flash | — | — | — | — | Current |
| Agnes 2.5 Flash | — | 512K | $0.030 | $0.150 | Available |
| Agnes Image 2.0 Flash | — | — | — | — | Available |
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Agnes Video 2.0 | — | — | — | — | — |
| Agnes 2.5 Pro Beta | Pro | — | — | — | — |
| Agnes 2.5 Pro Alpha | Pro | — | — | — | — |
| Agnes 2.5 Pro | Pro | — | 1.0M | $0.450 | $0.900 |