Reka Flash 3

RekaaiReasoning

rekaai/reka-flash-3Open Weights

Efficient model for low-latency assistance, extraction, and routine automation

Benchmark Pricing$0.10 / 1M in$0.21 / 1M out

Context: 65,536 tokens•Max Output: 58,982 tokens•Knowledge: 2025-01-31•Released: 2025-03-10

TECHNICAL SPECIFICATIONS

Context Window65,53665.5K tokens

Max Output58,98259K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

Text

Function / Tool CallingNot Supported

Structured OutputsPrompt Based

MODEL CONTEXT PROTOCOL (MCP) READINESS

⚠ Reka Flash 3 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 65,536 tokens, this model can handle compact tool sets. Consider keeping MCP server tool manifests minimal to preserve headroom.

API CALL INVOCATION EXAMPLE

// Example: Calling Reka Flash 3 via OpenAI SDK
import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "rekaai/reka-flash-3",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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