Cohere LLM (104B, 128K context) for enterprise: retrieval-augmented generation (RAG) with citations and multi-step tool use; open weights (CC-BY-NC 4.0).
Context window
128K
tokens
Parameters
104B
parameters
Release date
4 April 2024
Access:DownloadAPIHostedDeployment:💻 Local☁ Cloud
Overview
Applications
Access & deployment
DownloadAPIHosted
LocalCloud
Weights: Open weights
Key parameters
📏 Context: 128K
🧩 Parameters: 104B
✓ Tools · ✓ Fine-tuning
📥 Input: text
Technical specification
Context window
128K
tokens
Parameters
104B
parameters
License
CC-BY-NC 4.0 (wagi badawcze); komercyjnie przez API Cohere
Hardware requirements
An open-weights model (CC-BY-NC 4.0) for research on Hugging Face; its 104B parameters require multiple large-VRAM GPUs for local inference (quantized versions reduce requirements). Commercially available via the Cohere API and clouds (Azure, Amazon Bedrock, Oracle).
Features:✓ Tool use✓ Fine-tuning
Modalities
⬇ Input
text
⬆ Output
textcode
Capabilities and applications
Native model capabilities
Language modeling
Ability to predict subsequent tokens and generate coherent natural-language text based on the preceding context.
Category: language
Reasoning
The model's ability to reason logically and solve complex problems.
Category: reasoning
Multi-step reasoning
Carrying out multi-step chains of reasoning across long, complex tasks.
Category: reasoning
Retrieval-Augmented Generation (RAG)
The model's ability to generate answers grounded in retrieved documents/data, with source attribution (citations).
Category: language
Tool use
The model's ability to call external functions, APIs and tools during a conversation: calculator, search engine, code editor, database. The model decides when and how to use a tool and interprets its result.
Category: planning
Function Calling
Category: planning
Agentic capability
The model's ability to autonomously plan and execute multi-step tasks by sequentially using tools, maintaining context, and adapting to intermediate results.
Category: planning
Coding
Generating, analysing and modifying code in many programming languages. Covers writing functions, debugging, refactoring, code review, and creating tests. Measured by benchmarks such as HumanEval and SWE-bench.
Category: coding
Multilingual
Competence in many natural languages (from a few to over a hundred): understanding, generation, translation, and code-switching within a single conversation. Frontier models support a wide range of languages with comparable quality.
Category: language
Long context
Support for large context windows — tens to hundreds of thousands (or millions) of input tokens. Enables analysis of entire codebases, long documents, and many parallel conversations without losing earlier information. GPT-5.1 supports 400,000 tokens.
Category: language
Instruction following
Precisely following instructions contained in the prompt: response format, length, style, constraints (e.g. 'reply in six words'). GPT-5.1 significantly improved this capability compared to GPT-5.
Category: language
Structured output
Producing data in structured formats such as JSON.
Category: structured_generation
Technical architecture
Core Architecture
Training Techniques