Skip to content

OpenRouter Model Stacks for AI Assistants

A model stack is a curated set of AI models that your OpenClaw assistant routes across intelligently. Instead of locking you to one model, the stack hands every message to OpenRouter’s auto-router, which picks the best model from the set for that specific request, a hard coding question might go to the strongest model, a quick reply to a faster, cheaper one. Each stack also has a built-in cost-vs-quality lean, so the routing matches the stack’s intent.

Stacks at a glance

Wanderer

Free models only. Explore without spending a credit.

Gemma 4 26B
Google
North Mini Code
Cohere
Nemotron 3 Ultra 550B
Nvidia
Hustler

Efficient paid models. Quality stays high, spend stays low.

Gemini Flash Lite
Google
GPT-5 Nano
OpenAI
Hy3
Tencent
Professional Default

Balanced quality and speed for everyday work.

Claude Haiku 4.5
Anthropic
GPT-5.6 Luna
OpenAI
GPT-5.6 Terra
OpenAI
Qwen 3.7 Max
Qwen
Operator

The best models available. For when quality is everything.

Claude Sonnet 4.6
Anthropic
Claude Opus 4.8
Anthropic
Grok Build 0.1
xAI
GPT-5.6 Sol
OpenAI

How we choose models

Every stack has different criteria. We cross-reference PinchBench (real-world task success rates and cost-per-run value scores) with OpenRouter (live pricing, throughput, availability) before making any changes.

StackCapability barCost bar
WandererSolid task completionMust be :free on OpenRouter
HustlerHigh success rate, strong value scoreLowest cost-per-run with acceptable quality
ProfessionalHigh success rate, fast throughputMid cost, latency matters here
OperatorBest available, leads on reasoningCost is secondary

Model details and benchmarks

Wanderer Free
Primary
256K tokens Free Text

CX23-safe free coding model with tool support. New to the stack, so availability and real-world quality are being monitored.

Fallback 1
1M tokens Free Text
PinchBench avg score 89.9
Source: pinchbench.com ?,

Best-scoring free model on PinchBench. Single endpoint with variable uptime, so it backs up rather than leads.

Google
Fallback 2
262K tokens Free TextImageVideo
PinchBench value score 173.1
Source: pinchbench.com ?,

Swapped in from the 31B variant (Model Scout, Jul 2026) — 2 providers instead of 1, best value score on PinchBench. Also handles image messages for this stack.

Hustler Low cost
Primary
1M tokens $0.10 / $0.40 per M TextImageAudioVideo
PinchBench value score 367
Source: pinchbench.com ?,

Optimised for ultra-low latency and cost efficiency. Built-in reasoning via API.

Hy3
Tencent
Fallback 1
262K tokens $0.14 / $0.58 per M Text Jul 2026

New paid saver candidate with three providers, configurable reasoning, tool use, and a safe 262K/131K context-output profile.

OpenAI
Fallback 2
128K tokens $0.15 / $0.60 per M TextImage

Reliable OpenAI fallback. Consistent availability and broad task coverage.

Professional Mid cost
OpenAI
Primary
1M tokens $1 / $6 per M TextImage Jul 2026
PinchBench success rate 88.7
Source: pinchbench.com ?,

OpenAI's cost-sensitive GPT-5.6 tier. Five live endpoints and a safe 1M/128K context-output profile.

Anthropic
Fallback 1
200K tokens $1 / $5 per M TextImage
SWE-bench Verified 73
Source: openrouter.ai ?,

Near-frontier intelligence at low latency. Matches Sonnet 4 on reasoning, coding, and computer use.

OpenAI
Fallback 2
1M tokens $2.50 / $15 per M TextImage Jul 2026
PinchBench success rate 89.7
Source: pinchbench.com ?,

OpenAI's balanced GPT-5.6 tier for everyday coding, reasoning, and agentic work.

Fallback 3
1M tokens $1.25 / $3.75 per M Text May 2026
PinchBench avg score 92.5
Source: pinchbench.com ?,

Excellent OpenClaw benchmark performance and value. Single-provider availability is covered by the stack's outer fallback.

Operator Premium
Anthropic
Primary
1M tokens $3 / $15 per M TextImage Feb 2026
SWE-bench Verified 72.7
Source: openrouter.ai ?,

Frontier performance across coding, agents, and professional work. Leads on instruction-following and complex reasoning.

Anthropic
Fallback 1
1M tokens $5 / $25 per M TextImage
PinchBench avg score 90.5
Source: pinchbench.com ?,

PinchBench top-tier model with seven endpoints. Every live provider reports a safe 128K max output on its 1M context.

OpenAI
Fallback 2
1M tokens $5 / $30 per M TextImage Jul 2026

OpenAI's current flagship for complex professional work, coding, and agentic reasoning.

Fallback 3
256K tokens $1 / $2 per M TextImage
PinchBench success rate 88.9
Source: pinchbench.com ?,

Added Jul 2026 (Model Scout) — xAI's first entry in our stacks. Coding/agent-focused, 4 xAI-operated endpoints.

How auto-routing works

For each message, OpenRouter’s auto-router looks at the models in your stack and picks the best fit for that request, weighing capability against cost using the stack’s lean (Operator leans hard toward quality; Wanderer and Hustler lean toward savings; Professional sits in the middle). Harder tasks pull a stronger model; simple ones get a faster, cheaper one. You don’t configure anything, it happens per message, automatically, within the set you’ve chosen. If the router itself ever has a hiccup, a reliable safety model in the stack catches it, so there’s no downtime.

Credit usage

Costs vary by model and message length. Rough per-message estimates:

StackTypical cost per message
Wanderer$0
Hustler$0.001–$0.005
Professional$0.003–$0.015
Operator$0.015–$0.08

Check your Dashboard usage tab to monitor actual spend.

Switching stacks

Open your Dashboard, go to Settings, and select a new stack. The change applies immediately, no redeploy needed. You can also ask your bot to use any individual model for a specific conversation without changing your stack.

Model compatibility

Stack models are tested for compatibility with the CX23 VPS before any changes are made. If you use the custom model picker, be aware that some newer 1M context models have a token specification issue that causes immediate overflow errors. See VPS specs and model limits for the full details.