Aya Expanse 8B

Cohere

cohere/c4ai-aya-expanse-8bOpen Weights

Compact open multilingual model optimized for generation across 23 languages

Benchmark Pricing$0.00 / 1M in$0.00 / 1M out

Context: 8,000 tokens•Max Output: 4,000 tokens•Released: 2024-10-24

TECHNICAL SPECIFICATIONS

Context Window8,0008K tokens

Max Output4,0004K tokens

LicenseCC-BY-NC-4.0Self-hostable

Input Modalities

Text

Function / Tool CallingNot Supported

Structured OutputsPrompt Based

MODEL CONTEXT PROTOCOL (MCP) READINESS

⚠ Aya Expanse 8B does not natively advertise tool-calling capabilities. When connecting to MCP servers, function calling must be handled via structured prompt injection.

MCP Context Window Recommendations

With a context capacity of 8,000 tokens, this model can handle compact tool sets. Consider keeping MCP server tool manifests minimal to preserve headroom.

API CALL INVOCATION EXAMPLE

// Example: Calling Aya Expanse 8B via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.COHERE_API_KEY,
});

const response = await client.chat.completions.create({
  model: "cohere/c4ai-aya-expanse-8b",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);