---
title: "Best Llama Models for OpenClaw (2026): Cloud vs Self-Hosted"
description: "Meta's Llama lineup splits in two: cheap long-context cloud models (Scout, Maverick) and self-hosted open weights (Llama 3.3 70B). Different tool for different jobs."
date: 2026-04-17
updatedDate: 2026-09-08
location: San Francisco, CA – Apr 17th, 2026
image: /images/best-llama-models-for-openclaw-hero.jpg
keywords: "openclaw llama, best llama model for openclaw, llama 4 maverick openclaw, llama 4 scout openclaw, llama 3.3 70b openclaw, ollama openclaw, llama self-hosted openclaw"
faq:
  - question: "What is the best Llama model for OpenClaw?"
    answer: "Depends on whether you're running cloud or local. On cloud, Llama 4 Scout at $0.08/M input is the default for long-context work — 328K window at prices below DeepSeek. On self-hosted, Llama 3.3 70B through Ollama is the standard for privacy-sensitive or air-gapped deployments. Llama 4 Maverick at $0.15/M and 1M context is worth it when you need the absolute longest context cheaply."
  - question: "How much does it cost to use Llama with OpenClaw?"
    answer: "Cloud Llama models range from $0.08/M input (Scout) to $0.51/M input (Llama 3 70B). Output costs range from $0.30/M (Scout) to $0.74/M (Llama 3 70B). Self-hosted is free in per-token terms but requires 40GB+ VRAM for Llama 3.3 70B at reasonable quantization — so it makes economic sense at high volume or for privacy reasons, not casual use."
  - question: "How do I run Llama locally with OpenClaw?"
    answer: "Install Ollama (brew install ollama), pull the model (ollama pull llama3.3:70b-instruct-q4_K_M), and start the server (ollama serve). Then add Ollama as a provider in ~/.openclaw/openclaw.json with baseUrl 'http://localhost:11434/v1'. Run 'openclaw gateway config.apply' and switch with /model."
---

Llama doesn't fit neatly into the standard model-roundup format. Meta's open-weight strategy means Llama shows up in two very different places: as cheap long-context cloud endpoints, and as the de-facto standard for self-hosted OpenClaw setups.

Short version: **Llama 4 Scout for cloud long-context work, Llama 4 Maverick when you need 1M tokens, Llama 3.3 70B for self-hosted.** Llama 3 70B Instruct is still in API catalogs but there's no reason to pick it over Scout.

## The quick answer

| Model | Input/Output Cost | Context | Best For |
|---|---|---|---|
| **Llama 4 Scout** | $0.08 / $0.30 | 328K | Default cloud Llama |
| **Llama 4 Maverick** | $0.15 / $0.60 | 1M | Long-context cloud work |
| **Llama 3.3 70B (Ollama)** | $0 (self-hosted) | 128K | Privacy, air-gapped, high volume |
| Llama 3 70B Instruct | $0.51 / $0.74 | 8K | Legacy — use Scout |

Start with **Llama 4 Scout** for cloud workloads. If you're running local, pull **Llama 3.3 70B** through Ollama.

## Llama 4 Scout — the cloud default

$0.08/M input, $0.30/M output, 328K context, 16K output cap. Scout is Meta's answer to the cost-optimized tier — priced below DeepSeek and GLM Flash, with a much larger context window.

The 328K context is the real differentiator. Most budget models cap around 128K–200K. Scout can hold roughly 5x more code in working memory, which matters for codebase-wide refactors and large-document analysis.

Tool calling works but isn't at Sonnet-level reliability. Function arguments are usually well-formed, but Scout occasionally misses optional parameters or invents schema fields. For OpenClaw's interactive coding loops, you'll want to keep a higher-quality fallback configured (Sonnet 4.6 is the usual pairing).

The 16K output cap is the weakness. Scout can't regenerate large files in one pass — you'll need to chunk your asks. For most refactor workflows this is fine; for full-file rewrites, reach for a model with a higher output limit.

## Llama 4 Maverick — the 1M-context model

$0.15/M input, $0.60/M output, 1M context, 16K output cap. Maverick is Scout with more context, at roughly 2x the price.

The jump from 328K to 1M is only worth it if you actually need it. Most OpenClaw tasks fit comfortably in Scout's 328K window. The scenarios where Maverick earns its premium:

- **Monorepo-wide reasoning.** You want the model to see the entire service, not a subset.
- **Long conversation history.** Agent sessions that span hours and need full context of previous tool calls.
- **Large document analysis.** Feeding a full codebase, ADRs, and design docs together.

If you're doing anything shorter, Scout's 328K is plenty and you're paying for context you'll never use.

## Llama 3.3 70B (self-hosted via Ollama)

Free in per-token terms but gated by hardware. You need 40GB+ VRAM for Q4_K_M quantization, which in practice means a server with an H100, A100, or a machine with two consumer GPUs in parallel. Apple Silicon with 64GB+ unified memory works but is slower.

Llama 3.3 70B is what you deploy when cloud isn't an option:

- **Privacy-sensitive workloads.** Medical records, legal discovery, proprietary codebases that can't leave the building.
- **Air-gapped environments.** Compliance requirements that prohibit any outbound connection.
- **High-volume batch processing.** At enough throughput, the amortized cost of self-hosting beats per-token cloud pricing.

The 128K context is narrower than Scout's 328K, but for self-hosted use it's rarely the bottleneck. The bottleneck is inference speed — expect 20-40 tokens/second on a single H100, which is slower than cloud.

Reliability for self-hosted is what you make it. Ollama crashes occasionally on long runs. For production, wrap it in a supervisor or run it through haimaker's gateway with a cloud fallback configured. See our [local LLM setup guide](/blog/self-hosted-ai-agents-local-llms) for hardware specifics.

## Llama 3 70B Instruct — skip it

Still in the OpenRouter catalog at $0.51/M input, $0.74/M output, 8K context. There's no scenario where this is the right choice over Scout. Scout is 6x cheaper on input with 40x the context. If you have Llama 3 70B in an existing config, swap it out.

## Setup in OpenClaw

Llama isn't a built-in provider. Three routes depending on where you're running it.

#### Cloud through haimaker.ai

All Llama 4 cloud models are available through [haimaker.ai](https://app.haimaker.ai):

```json
{
  "models": {
    "providers": {
      "haimaker": {
        "baseUrl": "https://api.haimaker.ai/v1",
        "apiKey": "your-haimaker-api-key",
        "api": "openai-completions"
      }
    }
  }
}
```

Then add the models to your allowlist:

```json
{
  "agents": {
    "defaults": {
      "models": {
        "meta-llama/llama-4-scout": {},
        "meta-llama/llama-4-maverick": {}
      }
    }
  }
}
```

For the cloud route you can skip the copy-paste: `npx -y @haimaker/connect --openclaw` writes that haimaker provider and the Llama 4 allowlist in one command, and `--model meta-llama/llama-4-scout` defaults you to the cheap long-context pick — see the [connect docs](/connect). (The self-hosted Ollama setup below still needs the manual block.)

#### Self-hosted through Ollama

Install Ollama and pull Llama 3.3:

```bash
brew install ollama
ollama pull llama3.3:70b-instruct-q4_K_M
ollama serve
```

Then add Ollama as a provider in `~/.openclaw/openclaw.json`:

```json
{
  "models": {
    "providers": {
      "ollama": {
        "baseUrl": "http://localhost:11434/v1",
        "apiKey": "ollama",
        "api": "openai-completions"
      }
    }
  }
}
```

Add the model to the allowlist under `meta-llama/llama3.3:70b` (or whatever tag you pulled) and apply config. Full walkthrough in our [self-hosted local LLMs guide](/blog/self-hosted-ai-agents-local-llms).

## What I'd do

Run **Llama 4 Scout** as your default cloud Llama. The 328K context and $0.08/M pricing make it genuinely useful for cost-constrained workloads.

Reach for **Maverick** only when you know you need the full 1M context. Don't pay for it speculatively.

Use **Llama 3.3 70B self-hosted** when you have a real reason — privacy, compliance, or volume. Self-hosting is a commitment: hardware, reliability, updates. Don't do it casually.

Llama's strength isn't that any single model beats the Western flagships. It's that the open-weight option exists at all. If your threat model or compliance story requires running inference inside your own infrastructure, Llama is the answer. If you're just cost-optimizing and don't need self-hosting, GLM-4.7 or DeepSeek V3.2 are better picks per dollar.

<a href="https://app.haimaker.ai/sign-up?utm_source=family_roundup&utm_medium=cta&utm_campaign=openclaw_llama" class="cta-button">TRY LLAMA ON HAIMAKER</a>

---

*For self-hosted setup, see our [local LLMs guide](/blog/self-hosted-ai-agents-local-llms). For a full comparison of open-weight options, see the [local models roundup](/blog/best-local-models-for-openclaw).*