Files
docs/models.md
T

64 lines
3.8 KiB
Markdown

# 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).
## Providers
Models are named `provider/model-name`, so you can choose not just *which* model
but *where* it runs. Providers differ along two independent axes: **privacy**
(how protected your prompts and responses are) and **green energy** (how the
compute is powered). These are gradations, not binary switches — and no
provider today is best on both.
| Provider | Value | Privacy | Green energy | What that means |
|---|---|---|---|---|
| **Tinfoil** | *private* | **Strongest — architectural** | Not a green claim | Runs in hardware enclaves (TEEs) with end-to-end encryption (EHBP), verifiable via remote attestation. Neither we nor Tinfoil can read your prompts or responses at inference time. Energy mix is not disclosed. |
| **GreenPT** | *green* | **Policy-based** | **Strongest — 100% renewable** | Standard (non-enclave) hosting in the EU; privacy rests on GreenPT's commitments and EU data rules, not on cryptography. Compute runs on 100% renewable energy. |
| **PublicAI** | *public* | (to be confirmed) | (to be confirmed) | Coming soon — publicly developed models. Details pending. |
**Reading the gradations:**
- **Privacy:** *architectural* (Tinfoil) beats *policy-based* (GreenPT). An
enclave protects you even if the provider is compromised; a policy protects
you only as far as the provider keeps its word. Both are better than a
provider with neither.
- **Green energy:** *100% renewable* (GreenPT) beats *undisclosed* (Tinfoil).
GreenPT reports its energy mix; Tinfoil does not, so we can't claim greenness
for it — it may or may not be renewable.
Trade-offs are real: the most private option (Tinfoil) isn't the greenest, and
the greenest option (GreenPT) isn't the most private. The point of the co-op is
that **you choose** which axis matters more for a given task.
## 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 | Privacy | Green energy | Pricing (in / out) | Notes |
|---|---|---|---|---|---|
| `tinfoil/deepseek-v4-1-flash` | Tinfoil | architectural | undisclosed | $0.65 / $1.45 | Default; best for agentic tasks (1M context, tool calling). |
| `tinfoil/gpt-oss-120b` | Tinfoil | architectural | undisclosed | $0.15 / $0.60 | Lightweight fallback. |
| `tinfoil/glm-5-3-flash` | Tinfoil | architectural | undisclosed | $0.40 / $1.25 | Fast, efficient MoE model. |
| `greenpt/green-r` | GreenPT | policy | 100% renewable | $0.35 / $0.95 | Reasoning, renewable energy. |
| `greenpt/green-l` | GreenPT | policy | 100% renewable | $0.25 / $0.80 | Lightweight, renewable energy. |
| `greenpt/glm-5.3-flash` | GreenPT | policy | 100% renewable | $0.11 / $0.44 | Fast GLM model, 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.
## 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](privacy-policy.md).