Back to changelog

Sherlock: Two New Stealth Alpha Models

Introducing Sherlock Dash Alpha and Sherlock Think Alpha (Grok 4.1) - free stealth models with 1.8M context, reasoning, vision, and advanced capabilities.

Sherlock: Two New Stealth Alpha Models

Update: Sherlock is Grok 4.1

Checkout Grok 4.1 here

We're excited to introduce two new stealth models from Sherlock - completely free with massive context windows and advanced capabilities!

🎯 New Models Available

Sherlock Dash Alpha - Fast Reasoning Model

1sherlock/sherlock-dash-alpha

Context Window: 1,800,000 tokens (1.8M)

Pricing: FREE ($0.00 per 1M tokens)

Stability: STABLE

Lightning-fast responses with reasoning, vision, and tool calling capabilities

Sherlock Think Alpha - Deep Reasoning Model

1sherlock/sherlock-think-alpha

Context Window: 1,800,000 tokens (1.8M)

Pricing: FREE ($0.00 per 1M tokens)

Stability: STABLE

Advanced reasoning model optimized for complex problem-solving tasks

✨ Features

Both models come with comprehensive capabilities:

✅ Streaming - Real-time response streaming

✅ Vision - Image understanding and analysis

✅ Tools - Function calling support

✅ Reasoning - Advanced chain-of-thought capabilities

✅ JSON Output - Structured output mode

🚀 Getting Started

Use these models just like any other model in our gateway:

1curl -X POST https://api.llmgateway.io/v1/chat/completions \
2  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "sherlock/sherlock-dash-alpha",
6    "messages": [{"role": "user", "content": "Explain quantum computing"}]
7  }'

🎁 Why These Models Stand Out

  • Completely Free: No costs for input or output tokens
  • Massive Context: 1.8M token context window for complex tasks
  • Full Feature Set: All capabilities included
  • Production Ready: Marked as STABLE for reliable use

Try in Playground 🚀

Get started now 🚀