specter2_base
Embeddingtransformerspytorchbertfeature-extractionendataset:allenai/scirepevallicense:apache-2.0text-embeddings-inferenceendpoints_compatibledeploy:azureregion:us
컨텍스트
512 토큰
최대 출력
256 토큰
출시일
2023. 2. 16.
제공자
1
Overview
specter2_base is a large language model developed by Allen Institute for AI. It supports 512 tokens context and is available through 1 API provider(s).
Key Highlights
- Embedding
Brand
Allen Institute for AI
Organization
국가: USA
View all models, pricing and details from Allen Institute for AI.
Specifications
Basic Information
| 모델 | specter2_base |
| 브랜드 | Allen Institute for AI |
| Version | 2 |
| Model Type | transformers |
| 상태 | stable |
| 출시일 | 2023. 2. 16. |
| 인기 | 1203903 |
Architecture
| Parameter Size | Unknown / Not disclosed |
| Architecture Type | bert |
| Attention Mechanism | Unknown / Not disclosed |
| Tokenizer | Unknown / Not disclosed |
| Vocabulary Size | Unknown / Not disclosed |
Context & I/O
| 컨텍스트 | 512 tokens |
| 최대 출력 | 256 tokens |
| Modalities | Embedding |
| Languages | en |
Capabilities
| Vision | No |
| Audio | No |
| Reasoning | No |
| Function Call | No |
| MCP | No |
| JSON Mode | No |
| Embedding | Yes |
Training Data
| Training Dataset | Unknown / Not disclosed |
| Estimated Data Size | Unknown / Not disclosed |
| Knowledge Cutoff | Unknown / Not disclosed |
Inference & Deployment
| API Access | Yes |
| VRAM Estimate | Unknown / Not disclosed |
| Quantization Support | Unknown / Not disclosed |
| Hardware Requirements | Unknown / Not disclosed |
Safety & Compliance
| Safety Evaluations | Unknown / Not disclosed |
| Content Policy | Unknown / Not disclosed |
| Region Restrictions | Unknown / Not disclosed |
License & Pricing
| License | apache-2.0 |
| Commercial Use | Unknown / Not disclosed |
| Open Source | Yes |
Provider & Pricing
가격 변동
가격 변동 기록이 없습니다.
벤치마크
No benchmark data available.
Changelog
- Page created / data imported2026. 9. 23.
- Last updated2026. 9. 23.
FAQ
What is specter2_base?
specter2_base is a large language model developed by Allen Institute for AI.
Who developed specter2_base?
specter2_base was developed by Allen Institute for AI. You can learn more on the brand page or official website.
What is the context length of specter2_base?
specter2_base supports up to 512 tokens of context.
How much does specter2_base API cost?
API pricing for specter2_base starts at ₩0/1M per 1M input tokens and ₩0/1M per 1M output tokens. See the pricing table above for provider-specific rates.