docs: Metis decisions now count toward the allowance
Metering on /v1/systemone is live: each call is billed at $0.12 per 1M input tokens, computed from the exact token count GreenPT returns and attributed to the calling member key. Replace the "not yet metered" warnings in models.md and api-access.md with the accurate position. (metering verified 2026-11-03; code/litellm patch_passthrough_token_cost.py)
This commit is contained in:
1 parent
7c9c8ef578
commit
cdb62fc247
2 files changed
+9
-9
No files matched your search
+4
-3
@@ -84,9 +84,10 @@ Two practical notes:
|
|||||||
and receive probabilities; there is nothing for an OpenAI SDK's
|
and receive probabilities; there is nothing for an OpenAI SDK's
|
||||||
`chat.completions` to parse. Post the body directly (`curl`, `requests`,
|
`chat.completions` to parse. Post the body directly (`curl`, `requests`,
|
||||||
`httpx`, or an SDK's generic POST).
|
`httpx`, or an SDK's generic POST).
|
||||||
- **Its usage is not yet metered** (see the note in the model list): calls
|
- **Its usage is metered like any other call.** Each decision is billed at
|
||||||
currently register no spend against your key. Use it as though it counted
|
**$0.12 per 1M input tokens**, figured from the exact token count GreenPT
|
||||||
toward your allowance, because that is what it is meant to do.
|
returns (Metis generates no prose, so there is no output cost). Decisions draw
|
||||||
|
on the same monthly allowance as chat.
|
||||||
|
|
||||||
## Coding agents and other OpenAI-compatible clients
|
## Coding agents and other OpenAI-compatible clients
|
||||||
|
|
||||||
|
|||||||
@@ -227,12 +227,11 @@ curl https://gateway.inference.coop/v1/systemone \
|
|||||||
```
|
```
|
||||||
|
|
||||||
Metis is hosted by **GreenPT** — the same policy-based privacy, EU hosting, and
|
Metis is hosted by **GreenPT** — the same policy-based privacy, EU hosting, and
|
||||||
100% renewable energy as the 🌱 chat models. **Metering on this route is not yet active.** Verified 2026-11-03: a call to
|
100% renewable energy as the 🌱 chat models. **Decisions count toward your
|
||||||
`/v1/systemone` returns a correct answer but registers no spend against the
|
monthly allowance**, like every other call: each request is metered at
|
||||||
key that made it, so decisions currently do not count toward your monthly
|
**$0.12 per 1M input tokens**, computed from the exact token count GreenPT
|
||||||
allowance. That is a gap on our side, not a policy — the intent is that
|
reports back, and appears in your usage record alongside your chat calls.
|
||||||
decisions draw on the same allowance as everything else. Until it is fixed,
|
(Metis generates no prose, so there is no output charge.)
|
||||||
please use the route in the spirit of the allowance it is meant to share.
|
|
||||||
|
|
||||||
## Limitations on privacy
|
## Limitations on privacy
|
||||||
|
|
||||||
|
|||||||
Reference in new issue
Block a user