WeavePrism
All modelsStart free
11 tasks ranked · free

Best LLMs for classification & routing

Labeling, intent detection, moderation, routing. Every model in the catalog, ranked three ways and priced at a realistic 25M input / 1.5M output tokens a month for this task.

Balanced pick
GPT-5 nano

What the engine picks on the default cost/quality/speed mix before you touch a slider.

Highest quality
Claude Opus 4.5

Top task score (90/100) at $163/mo for this volume.

Budget pick
GPT-5 nano

The cheapest model that stays close to the leader on quality — 82/100 at $1.85/mo.

By quality

Highest task score first.

1Claude Opus 4.5Anthropic90/100$163/mo2Gemini 3 ProGoogle89/100$68.0/mo3GPT-5.1OpenAI88/100$46.3/mo4Claude Sonnet 4.5Anthropic88/100$97.5/mo5Gemini 2.5 FlashGoogle87/100$11.3/mo6Claude Haiku 4.5Anthropic86/100$32.5/mo

Best value

Most quality per dollar of monthly spend.

1GPT-5 nanoOpenAI$1.85/moquality 822Mistral Small 3.2Mistral$2.95/moquality 823Gemini 2.5 Flash-LiteGoogle$3.10/moquality 824Grok 4.1 FastxAI$5.75/moquality 845Qwen3 235BAlibaba (Qwen)$6.82/moquality 846DeepSeek V3.2DeepSeek$7.63/moquality 84

Cheapest

Lowest monthly cost at this volume.

1GPT-5 nanoOpenAI$1.85/moquality 822Mistral Small 3.2Mistral$2.95/moquality 823Gemini 2.5 Flash-LiteGoogle$3.10/moquality 824Grok 4.1 FastxAI$5.75/moquality 845Qwen3 235BAlibaba (Qwen)$6.82/moquality 846DeepSeek V3.2DeepSeek$7.63/moquality 84

Fit to your volume

The ranking above prices a typical month. Enter your own classification & routing volume and, if you like, a monthly ceiling — the picks re-rank as you type. No signup.

Models for Classification & routing, ranked by quality per dollar at your volume
ModelQualityPer month Value
GPT-5 nano OpenAI82$1.8544.32
Mistral Small 3.2 Mistral82$2.9527.80
Gemini 2.5 Flash-Lite Google82$3.1026.45
Grok 4.1 Fast xAI84$5.7514.61
Qwen3 235B Alibaba (Qwen)84$6.8212.32
DeepSeek V3.2 DeepSeek84$7.6311.01
Llama 4 Maverick Meta83$8.0310.34
GPT-5 mini OpenAI85$9.259.19

Value = quality points per dollar of monthly spend at your volume. Quality scores are benchmark-informed estimates, not evals — validate on your own workload before migrating.

Price your own classification & routing volume

These rankings use a typical monthly volume. Plug in your real token counts and the free estimator re-ranks every model on cost and quality.

Open the estimator

Embed the live pick

A self-updating SVG badge of the balanced pick for classification & routing. Drop it in a README or blog — it re-renders the day the catalog changes.

WeavePrism balanced pick for classification & routingMore badges
![Best for classify](https://weaveprism.com/api/embed/best/classification.svg)

Best models for other tasks

Coding & code reviewAgents & tool useReasoning & analysisWriting & contentChat & supportData extractionSummarizationTranslationVision & multimodalGeneral / other

Prices are list $/1M tokens, hand-maintained from public provider pricing. Quality scores are benchmark-informed 0-100 estimates, not evals — validate on your own workload before moving production traffic. Not affiliated with any model provider. Compare Claude Opus 4.5 vs GPT-5 nano