Skip to content

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.

Wanderer

Free models only. Explore without spending a credit.

Gemma 4 26B
Google
North Mini Code
Cohere
Nemotron 3.5 Lightning
Nvidia
Nemotron 3 Ultra 550B
Nvidia
Hustler

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

GPT-5 Nano
OpenAI
Gemini 3.5 Flash Lite
Google
MiMo 2.5
Xiaomi
Qwen 3.8 Flash
Qwen
DeepSeek V4 Flash
DeepSeek
ProfessionalDefault

Balanced quality and speed for everyday work. Includes everything in Hustler.

Gemini 3.7 Flash
Google
GPT-5.6 Luna
OpenAI
GLM-5.3
Zhipu
GPT-5.6 Terra
OpenAI
Qwen 3.8 Max
Qwen
Operator

The best models available. For when quality is everything. Includes everything in Professional.

Claude Sonnet 5
Anthropic
GPT-5.6 Sol
OpenAI
Claude Opus 5
Anthropic

Every stack has different criteria. Before making any changes we cross-reference our own fleet routing telemetry (which models the auto-router actually picks, at what cost), OpenRouter’s category rankings (real-world usage for agent and coding work), each model’s live OpenRouter endpoint specs (pricing, throughput, availability, output-token limits), and independent evaluations from Artificial Analysis.

Stack Capability bar Cost bar
Wanderer Solid task completion Must be :free on OpenRouter
Hustler High success rate, strong value Lowest cost-per-run with acceptable quality
Professional High success rate, fast throughput Mid cost, latency matters here
Operator Best available, leads on reasoning Cost is secondary

Every candidate is also checked per provider endpoint for output-token limits that would overflow the CX23 VPS — the same model can be safe on one host and unusable on another. See VPS specs and model limits.

WandererFree
Floor
256K tokensFreeText

CX23-safe free coding model with tool support. Single Cohere endpoint, so availability is monitored.

1M tokensFreeTextAug 2026

Added Aug 2026 (Model Scout) as a faster free rung. Single Nvidia endpoint with variable free-tier uptime.

1M tokensFreeText

The strongest free model in the pool. Single endpoint with variable uptime, so it backs up rather than leads.

Mid
262K tokensFreeTextImageVideo

The resilient free floor and the image path for this stack — the only vision-capable free model in the pool.

HustlerLow cost
Floor
400K tokens$0.05 / $0.40 per MText

The reliable cheap floor. Consistent availability and broad task coverage.

1M tokens$0.15 / $1.25 per MTextImageAudioVideo

Ultra-low latency, built-in reasoning. Replaced the retired Gemini 2.5 Flash Lite (Model Scout, Aug 2026).

1M tokens$0.15 / $0.47 per MTextImageAug 2026

Cheap, capable, vision-capable. Single Alibaba endpoint with a safe 1M/131K context-output profile.

Ceiling
1M tokens$0.09 / $0.18 per MTextJul 2026

Near-frontier agent quality at reseller prices — one of the two most-used coding models on OpenRouter. Routing avoids its oversized-output endpoints (see VPS limits).

ProfessionalMid cost
1M tokens$0.38 / $1.88 per MTextImageAudioVideoAug 2026
AutomationBench-AA62.7
Source: artificialanalysis.ai ?,

Leads AutomationBench-AA and sits on the intelligence-vs-latency Pareto frontier. Promotional $0.75 / $3.75 per M through end of 2026.

Mid
1M tokens$0.20 / $1.20 per MTextImageJul 2026

OpenAI's cost-sensitive GPT-5.6 tier. Prices dropped sharply in Aug 2026. Safe 1M/128K context-output profile.

Zhipu
Mid
1M tokens$1.40 / $4.40 per MTextAug 2026
AA Intelligence Index60
Source: artificialanalysis.ai ?,

The open-weight flagship behind OpenRouter's "Ox Alpha" stealth launch. Ties Kimi K3 on Artificial Analysis's Intelligence Index.

Mid
1M tokens$2 / $12 per MTextImageJul 2026

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

Ceiling
1M tokens$2 / $6 per MTextImageAug 2026

The non-OpenAI ceiling, replacing Qwen 3.7 Max. Single Alibaba endpoint; independent benchmark data is still limited.

OperatorPremium
Mid
1M tokens$2 / $10 per MTextImageAug 2026

Replaces Sonnet 4.6 — cheaper and stronger. Frontier instruction-following and complex reasoning across coding and agents.

Mid
1M tokens$2 / $10 per MTextImageJul 2026

OpenAI's current flagship for complex professional work, coding, and agentic reasoning. Price dropped in Aug 2026.

Anthropic
Ceiling
1M tokens$5 / $25 per MTextImageAug 2026

The top capability rung and the image model for this stack. Every provider reports a safe 128K max output on its 1M context.

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.

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

Stack Typical 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.

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.

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.