ReMM SLERP 13B

Undi95
undi95/remm-slerp-l2-13bOpen Weights

Open-weight instruction model for adaptable chat and self-hosted production workloads

Benchmark Pricing$0.80 / 1M in$1.21 / 1M out$0.40 cache read
Context: 6,144 tokens•Max Output: 5,529 tokens•Knowledge: 2023-06-30•Released: 2023-07-22

TECHNICAL SPECIFICATIONS

Context Window6,1446.1K tokens
Max Output5,5295.5K tokens
LicenseOpen SourceSelf-hostable
Input Modalities
Text
Function / Tool CallingNot Supported
Structured OutputsPrompt Based

MODEL CONTEXT PROTOCOL (MCP) READINESS

⚠ ReMM SLERP 13B 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 6,144 tokens, this model can handle compact tool sets. Consider keeping MCP server tool manifests minimal to preserve headroom.

API CALL INVOCATION EXAMPLE

// Example: Calling ReMM SLERP 13B via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.UNDI95_API_KEY,
});

const response = await client.chat.completions.create({
  model: "undi95/remm-slerp-l2-13b",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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

PRICING BY PROVIDER

4 providers
NanoGPTundi95/remm-slerp-l2-13b
$0.80 / $1.21$0.40 cache
AI/ML APIundi95/remm-slerp-l2-13b
$0.69 / $1.03
Kilo Gatewayundi95/remm-slerp-l2-13b
$0.35 / $0.65
OpenRouterundi95/remm-slerp-l2-13b
$0.35 / $0.65

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

Prompt Caching Active

This model supports prompt caching at $0.40 / 1M tokens, saving up to 50% on repetitive MCP tool definitions and system instructions.

MODEL RESOURCES

View Undi95 HubHugging Face Weights