docs/models.md

Models

The co-op serves models from multiple providers. This is the single list — both the chat and the API draw from it, so it's the one place to look (and the one place to update).

Naming

Models are named provider/model-name, so you can choose not just which model but where it runs. The provider part tells you the value it stands for:

Provider	Value	What it means
Tinfoil	private	Models run inside hardware enclaves (TEEs), and requests/responses are encrypted end-to-end (EHBP), so neither we nor the provider can read your prompts or responses. Verifiable via remote attestation.
GreenPT	green	Models served on 100% renewable energy in the EU. Cleaner energy, but standard (non-enclave) hosting — privacy here is a policy commitment, not architectural.
PublicAI	public	(coming soon — publicly developed models.)

Current models

Pricing is per 1 million tokens, input / output (what the co-op pays the provider — your own cost is your monthly allowance, not per-token billing).

Model	Provider	Value	Pricing (in / out)	Notes
deepseek-v4-1-flash	Tinfoil	private	$0.65 / $1.45	Default; best for agentic tasks (1M context, tool calling).
gpt-oss-120b	Tinfoil	private	$0.15 / $0.60	Lightweight fallback.
glm-5-3-flash	Tinfoil	private	$0.40 / $1.25	Fast, efficient MoE model.
greenpt/green-r	GreenPT	green	$0.35 / $0.95	Reasoning, renewable energy.
greenpt/green-l	GreenPT	green	$0.25 / $0.80	Lightweight, renewable energy.

Some models also have a discounted cached-input rate (when a prompt is reused and doesn't need to be re-read) — see the code/litellm config for the exact numbers. Pricing here mirrors the model_info in the LiteLLM config (code/litellm/config.yaml), which is the authoritative source — the two are kept in sync.

Note: the three Tinfoil models currently use their bare names (no tinfoil/ prefix). They'll be renamed to tinfoil/deepseek-v4-1-flash and so on in an upcoming change — we'll email members before that happens. GreenPT models already use the greenpt/ prefix.

Limitations on privacy

Only Tinfoil offers architectural privacy. The other providers are chosen for their value (renewable energy, public models) but do not run in enclaves — prompts and responses pass through them in the ordinary way. Your chat history is also stored on our server so you can revisit it, and that stored history is not encrypted in a way that prevents us from technically reading it — we commit not to. The full distinction — what's architecturally private versus what's a policy commitment — is in the Privacy Policy.