ai21について
AI21 Labs is an AI research and product company with an office in Tel Aviv, Israel. Their mission is to build advanced language models and writing-tools that enable humans and machines to collaborate in thinking and creating.
性能
ai21のモデルにおける最近のGateway性能。
—
最近のデータはありません
—
最近のデータはありません
—
最近のデータはありません
この研究機関のモデルがGatewayのトラフィックを処理すると、性能指標が表示されます。
最新モデル
提供状況、コンテキスト、価格、使用状況を含む最近のリリース。
Jamba 2 3B is a language model from ai21 for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Jamba Mini 2 is a language model from ai21 for chat, writing, analysis, and general-purpose automation. It is a smaller-footprint option suited to tighter latency or deployment budgets.
Jamba Reasoning 3B is a reasoning model from ai21 for multi-step analysis, math, and tool-driven tasks. It supports up to 256K of input context for long documents, codebases, and agent workflows.
Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. It supports up to 256K of input context for long documents, codebases, and agent workflows.
Jamba Mini 1.7 is a language model from ai21 for chat, writing, analysis, and general-purpose automation. It supports up to 256K of input context for long documents, codebases, and agent workflows.
Jamba Large 1.6 is a language model from ai21 for chat, writing, analysis, and general-purpose automation. It supports up to 256K of input context for long documents, codebases, and agent workflows.
Jamba Mini 1.6 is a language model from ai21 for chat, writing, analysis, and general-purpose automation. It supports up to 256K of input context for long documents, codebases, and agent workflows.
Jamba Large 1.5 is a language model from ai21 for chat, writing, analysis, and general-purpose automation. It supports up to 256K of input context for long documents, codebases, and agent workflows.
Jamba Mini 1.5 is a language model from ai21 for chat, writing, analysis, and general-purpose automation. It supports up to 256.1K of input context for long documents, codebases, and agent workflows.
ウェブ上の情報
公式プロフィール、研究、コミュニティの各チャンネル。
