Models & providers

The in-app chat runs on whichever model you pick. Dalea supports six providers: one that's hosted by us out of the box, and five that you bring your own API key for.

The Dalea default — no setup

The Dalea provider runs on operator-managed EU infrastructure and is enabled for every workspace from day one. You don't need to register an account anywhere, you don't store a key. Use it for general-purpose chat, prototyping, and any workspace that doesn't want to manage external billing.

gpt-oss 120b

Open-weight 120B reasoning model. Default for new workspaces. 128K ctx

Gemma 4 26B A4B (MoE)

Open-weight mixture-of-experts. 256K ctx

Bring-your-own-key providers

For the other five providers, each user adds their own API key from Settings → AI Providers. Keys are personal — they live in your user vault, not the workspace's, so you control them and you can revoke at any time. Keys are encrypted at rest and never logged. The request goes straight from our servers to the provider.

Anthropic

Reasoning via Claude's thinking budget. All Claude 4.x models accept images.

Claude Opus 4.7

Frontier model. 1M ctx

Claude Sonnet 4.6

Balanced speed and quality. 1M ctx

Claude Haiku 4.5

Fastest Claude with thinking. 200K ctx

OpenAI

GPT-5.x family. Every entry reasons and accepts images.

GPT-5.5 Pro

Highest-tier GPT-5.x. `low` effort is not accepted — minimum is `medium`. 1M ctx

GPT-5.5

Default flagship. 1M ctx

GPT-5.4

Previous-generation flagship; still supported for parity. 1M ctx

GPT-5.4 Mini

Cheaper / faster. Caps at `high` — no `xhigh`. 1M ctx

Google

Gemini 2.5+ and the open-weight Gemma 4 family, all multimodal. Gemini models expose effort tiers; Gemma 4 reasons natively without one.

Gemini 3.1 Pro (preview)

Frontier Gemini, preview channel. 1M ctx

Gemini 3.1 Pro (preview, tool-tuned)

Same model tuned to prefer user-supplied tools — recommended for tool-heavy chats. 1M ctx

Gemini 3 Flash (preview)

Cheaper preview. 1M ctx

Gemini 2.5 Pro

Stable flagship. 1M ctx

Gemini 2.5 Flash

Faster, cheaper sibling. 1M ctx

Gemini 2.5 Flash-Lite

Smallest Gemini 2.5 tier. 1M ctx

Gemma 4 31B / 26B A4B

Open-weight, Apache 2.0. Natively multimodal. 256K ctx

Mistral

Mistral splits into adjustable-reasoning, native-reasoning, and non-reasoning families. All entries are vision-capable. The unified Mistral 3.x / 4 generation (Medium 3.5, Small 4, Large 3) ships at 256K context; Magistral medium/small stay on the 128K reasoning-tuned base.

Magistral Medium / Small

Native reasoners — always think; no effort knob. 128K ctx

Mistral Medium 3.5

Reasoning toggle. 256K ctx

Mistral Small 4

Same toggle, smaller and cheaper. 256K ctx

Mistral Large 3

Non-reasoning multimodal MoE. 256K ctx

DeepSeek

V4 family.

DeepSeek V4 Pro

Text only — DeepSeek's production API does not yet accept images. 1M ctx

DeepSeek V4 Flash

Cheaper V4 variant with the same reasoning tiers. 1M ctx

Reasoning effort

For models that expose a controllable reasoning knob, the picker shows the effort tiers the provider actually accepts — they vary:

Provider	Effort tiers
Anthropic (Sonnet 4.6 / Haiku 4.5)	low / medium / high
Anthropic (Opus 4.7, adaptive)	low / medium / high / xhigh
OpenAI (GPT-5.5, GPT-5.4)	low / medium / high / xhigh
OpenAI (GPT-5.5 Pro)	medium / high / xhigh
OpenAI (GPT-5.4 Mini)	low / medium / high
Google (Gemini 2.5 + 3 Pro)	low / medium / high
Google (Gemini 3 Flash)	minimal / low / medium / high
Mistral (Medium 3.5 / Small 4)	none / high
DeepSeek (V4 Pro / Flash)	high / max
Dalea (gpt-oss 120b)	low / medium / high

Higher effort buys deeper analysis at higher latency and cost. Defaults are tuned per model — leave it on medium unless you have a reason to override.

Vision

If your selected model lacks vision support (DeepSeek V4, gpt-oss 120b), the composer disables the paperclip icon and image drops are ignored. The server also rejects image attachments for non-vision models with MODEL_NO_VISION, defence in depth.

The total per-request attachment size is capped by CHAT_IMAGE_TOTAL_BUDGET_BYTES (server config). Compress screenshots before attaching if you hit the limit.

Picking and switching

Each user has a default model (Settings → AI Providers); the chat header lets you switch per turn. Switching mid-conversation is supported — the next assistant turn uses the new model, prior turns stay in their original provider's transcript.

What's next