Maxwel Agents

Managed Agents

Anthropic

Claude Opus 5.5

Multi-step agent workflows and deep multi-file analysis

OpenRouter
Anthropic
Google Vertex AI
SecurePlus
Anthropic

Claude Sonnet 5.5

Daily driver for code reviews and general tasks

OpenRouter
Anthropic
Google Vertex AI
SecurePlus
Anthropic

Claude Fable 5.1

Mythos-class flagship for the longest autonomous tasks and deepest analysis

OpenRouter
Anthropic
Private
Anthropic

Claude Haiku 5.5

Very cheap and very fast — for tool use, subagents and high-throughput pipelines

OpenRouter
Anthropic
Google Vertex AI
SecurePlus
OpenAI

GPT 6.1

Frontier model for agentic workflows with native tool orchestration and multimodal inputs

OpenRouter
Open
Google

Gemini 4 Carbon

Google's most capable model, via Vertex AI in the EU multi-region

Google Vertex AI
SecurePlus
Google

Gemini 3.8 Flash

Google's fast workhorse, via Vertex AI in the EU multi-region

Google Vertex AI
SecurePlus
DeepSeek

DeepSeek V4.1 Flash

DeepSeek's new standard model with image understanding — ahead of V4 Pro on most benchmarks per the vendor, at Flash speed with 1M context

DeepSeek
Lyceum
Verda
OpenRouter
Scaleway
SecurePlusEU
Open Source
DeepSeek

DeepSeek V4 Flash

Compact MoE variant for high-volume throughput with very long context at minimal cost

Lyceum
OpenRouter
SecureEU
Open Source
Alibaba

Qwen 3.8 27B

Open everyday model with image understanding and 262K context — hosted in the EU

Lyceum
Scaleway
SecureEU
Open Source
Alibaba

Qwen 3.8 Flash Next

The fastest model in the lineup: multimodal MoE with just 6B active parameters, built for agents, coding and long-running office workflows

Alibaba Cloud
Open
Open Source
Alibaba

Qwen 3.8 Max

Open frontier model with 2.4 trillion parameters for coding, research and long-horizon agents — the only model of its class available with EU data protection

Lyceum
Alibaba Cloud
SecureEU
Open Source
Moonshot

Kimi K3

Agentic orchestration with long context for multi-step workflows

Verda
Lyceum
Fireworks AI
Moonshot AI
SecurePlusEU
Open Source
Z.ai

GLM 5.3 Flash

Natively multimodal open-source model (MIT) with 1M context at the lowest price — understands images too

OpenRouter
Lyceum
SecureEU
Open Source
Z.ai

GLM 5.3

Top-tier model for agentic engineering and SWE-Bench tasks

OpenRouter
Lyceum
Z.ai
Scaleway
SecureEU
Open Source
Google

Nano Banana 2.1

Fast image generation and editing for iterative workflows — up to 14 reference images, half the price of Nano Banana 2

Google Vertex AI
SecurePlus
Google

Nano Banana Pro 2

Highest detail accuracy for complex scenes with many subjects

Google Vertex AI
Private
Google Vertex AI

Veo 3.1 Fast

Google's video model via Vertex AI on the gateway — cinematic motion with sound, up to 4K

Google Vertex AI
Private
ElevenLabs

ElevenLabs TTS v3

Studio quality for audiobooks and voiceovers in 70+ languages

ElevenLabs
Private
OpenAI

Whisper Large v3

Speech-to-text in 99 languages with high robustness

Groq
Scaleway
SecureEU
Open Source
ElevenLabs

ElevenLabs Scribe

Transcription with the best word accuracy — speaker diarization, 99 languages, per-word timestamps

ElevenLabs
Private
Brave Software

Brave Search

Seat and processing in the US (AWS)

Open
Perplexity AI

Perplexity Search

Seat and processing in the US, own index

Open
Mojeek Ltd

Mojeek Search

Seat and processing in the United Kingdom (adequacy decision), own index

Private