Skip to content

Model Stacks

A model stack is a preset of three AI models: a primary model and two fallbacks. If the primary is unavailable or rate-limited, your bot automatically tries the next one — no downtime, no config changes needed.

Stacks at a glance

Wanderer

Free models only. Explore without spending a credit.

1
Qwen3.6 Plus
Primary · Qwen
2
Gemma 3 27B
Fallback 1 · Google
3
Step 3.5 Flash
Fallback 2 · StepFun
Hustler

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

1
Gemini Flash Lite
Primary · Google
2
GLM-4.5 Air
Fallback 1 · Z-AI
3
GPT-5 Nano
Fallback 2 · OpenAI
Professional Default

Balanced quality and speed for everyday work.

1
Gemini 2.5 Flash
Primary · Google
2
Claude Haiku 4.5
Fallback 1 · Anthropic
3
GPT-5 Nano
Fallback 2 · OpenAI
Operator

The best models available. For when quality is everything.

1
Claude Sonnet 4.6
Primary · Anthropic
2
Gemini 3 Pro Preview
Fallback 1 · Google
3
GPT-4o
Fallback 2 · 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
Qwen / Alibaba
Primary
1M tokens Free TextImageVideo Apr 2026
SWE-bench Verified 78.8
Source: openrouter.ai ↗

Competitive with paid frontier models on coding. 1M context, tool calling, 600 req/min with no daily cap.

Google
Fallback 1
131K tokens Free TextImage Mar 2025

Google's open multimodal model. Strong general capability, 140+ languages, function calling.

StepFun
Fallback 2
32K tokens Free Text
PinchBench success rate 85.3
Source: pinchbench.com ↗

Proven free fallback. Consistent task completion across benchmark runs.

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.

Fallback 1
131K tokens $0.13 / $0.85 per M Text Jul 2025
PinchBench success rate 85.7
Source: pinchbench.com ↗
PinchBench value score 772
Source: pinchbench.com ↗

PinchBench rank 4 overall. 85.7% task success at $0.15/run — value score nearly double Gemini 2.5 Flash.

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

Reliable OpenAI fallback. Consistent availability and broad task coverage.

Professional Mid cost
Primary
1M tokens $0.30 / $2.50 per M TextImageAudioVideo Jun 2025

Advanced reasoning with built-in thinking. Top weekly model on OpenRouter. Strong across coding, maths, and science.

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
128K tokens $0.15 / $0.60 per M TextImage

Lightweight OpenAI fallback. Reliable last resort.

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.

Fallback 1
1M tokens $1.25 / $10 per M TextImageAudioVideo

Google's flagship. Strong multimodal reasoning. Preview model — watch for stable release.

OpenAI
Fallback 2
128K tokens $2.50 / $10 per M TextImageAudio

Battle-tested flagship. Broad capability across all task types.

How fallback works

Your bot tries models in order. If the primary is unavailable or rate-limited, it moves to fallback 1, then fallback 2. This happens silently — you won’t notice unless you’re watching closely.

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.