foldrun 14.0.1 → 14.0.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/docs/providers.md +4 -3
- package/package.json +1 -1
package/docs/providers.md
CHANGED
|
@@ -55,9 +55,10 @@ billed in credits at **foldrun's price list**
|
|
|
55
55
|
API; each provider is sent what its own API documents, the rest left
|
|
56
56
|
out. Anthropic gets the request as written. DeepSeek takes every level
|
|
57
57
|
(`medium` and `xhigh` run as `high`). Kimi takes `low`, `high` and
|
|
58
|
-
`max`: `medium` and `xhigh` run as `high`, and it always thinks. OpenAI
|
|
59
|
-
(over its Responses API)
|
|
60
|
-
`xhigh` and `max` run as `high`.
|
|
58
|
+
`max`: `medium` and `xhigh` run as `high`, and it always thinks. OpenAI's
|
|
59
|
+
GPT-6 models (over its Responses API) take all five; Gemini takes `low`,
|
|
60
|
+
`medium`, `high`, so `xhigh` and `max` run as `high`. Where a level is
|
|
61
|
+
changed the step's log says so. No provider is sent `temperature` or
|
|
61
62
|
`top_p` — the reasoning models fix them.
|
|
62
63
|
- **Where each provider processes the prompt** is its own: DeepSeek in
|
|
63
64
|
the People's Republic of China (its privacy policy), Moonshot in
|