← Stack

Model catalogue

A living catalogue, refreshed as models ship and specifications move. The durable analysis lives in the decision guides: choosing a model and deploying models.

Catalogue

Tier
Openness
Deployment
Sovereignty
Specialization
14 models
Claude OpusAnthropicFrontierClosedProprietary200K

The heavy-reasoning tier: best goal coherence over long agentic runs and the hardest code. Price reserves it for the steps that genuinely need it, not the default node.

ReasoningAgenticCoding
Reviewed 2026-06-25
Claude SonnetAnthropicWorkhorseClosedProprietary200K

The production workhorse: reliable structured output and strong long-horizon coherence at a fraction of frontier cost. Our default for most agent nodes.

AgenticCodingLong context
Reviewed 2026-06-25
Claude HaikuAnthropicSmallClosedProprietary200K

The fast, cheap router: sub-second latency at a fraction of the workhorse price. Ideal for classification, triage and the cheap leg of a routing strategy.

GeneralAgentic
Reviewed 2026-06-25
Claude MythosAnthropicFrontierClosedProprietaryn/a

A gated frontier model with exceptional cybersecurity capability, released to vetted defenders only (Project Glasswing). Page-worthy: the case study for when a model earns its own page.

Security
Reviewed 2026-06-25
GPT-5OpenAIFrontierClosedProprietary400K

The main frontier alternative to Claude: very reliable structured output and tool calling, broad general capability. Azure gives EU-region hosting.

GeneralAgenticCoding
Reviewed 2026-06-25
GeminiGoogleFrontierClosedProprietary1M

Native multimodal and the longest context window in the closed tier. Vertex AI gives EU regions for residency-sensitive workloads.

MultimodalLong context
Reviewed 2026-06-25
LlamaMetaWorkhorseOpen-weightLlama Community128K

The open-weight default with the largest ecosystem and tooling. The license is not OSI open-source: it carries an active-users cap and EU conditions, read it before you build.

GeneralLong context
Reviewed 2026-06-25
QwenAlibabaFrontierOpen-weightApache-2.0256K

The strongest permissive open-weight line: Apache-2.0, excellent coding, very broad language coverage, and sizes spanning frontier down to small. The clean commercial choice.

CodingAgenticMultilingual
Reviewed 2026-06-25
DeepSeekDeepSeekFrontierOpen-weightMIT128K

Open-weight reasoning and agentic-coding leader under an MIT license, the cleanest terms for unrestricted commercial use. Strong on SWE-bench-style tasks.

ReasoningCodingAgentic
Reviewed 2026-06-25
MistralMistral AIWorkhorseOpen-weightApache-2.0 / Proprietary256K

The EU-native option: open models under Apache-2.0 plus hosted flagships, EU hosting with no third-country transfer. The default when sovereignty drives the choice.

GeneralMultilingual
Reviewed 2026-06-25
GLMZhipu AIWorkhorseOpen-weightMIT200K

A clean MIT license and a low active-parameter footprint make it one of the cheapest fully open self-hosted options at sustained scale.

CodingAgentic
Reviewed 2026-06-25
KimiMoonshot AIFrontierOpen-weightModified MIT256K

A strong agentic and long-context open-weight contender that has topped neutral capability indices. Heavy to self-host, often consumed managed.

AgenticLong context
Reviewed 2026-06-25
GemmaGoogleEdgeOpen-weightGemma license128K

Google's small open-weight family, notably RAM-efficient. The go-to for on-device and multimodal mobile, where a few gigabytes is the whole budget.

MultimodalGeneral
Reviewed 2026-06-25
PhiMicrosoftSmallOpen-weightMIT128K

Small models that punch above their size on reasoning, MIT-licensed. Quantized to a few gigabytes, they run a capable assistant on a laptop or phone, fully offline.

ReasoningGeneral
Reviewed 2026-06-25