@acedatacloud/sdk 2026.1106.1 → 2026.1113.0
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/README.md +30 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -143,6 +143,29 @@ Streaming and `claude.chat.messages.countTokens(...)` also preserve thinking
|
|
|
143
143
|
configuration. Parameter pass-through does not guarantee model support; API errors
|
|
144
144
|
are returned through the SDK's normal error handling.
|
|
145
145
|
|
|
146
|
+
### Claude Fable 5.2
|
|
147
|
+
|
|
148
|
+
Use the exact model ID `claude-fable-5-2`. Native Messages preserves thinking and
|
|
149
|
+
tool content blocks. Omit `temperature`, `top_p` and `top_k`; adaptive thinking is
|
|
150
|
+
always enabled, and the output budget covers thinking plus the final answer.
|
|
151
|
+
Count Tokens and Responses are not published for this model. Consult the
|
|
152
|
+
[current model page](https://platform.acedata.cloud/models/claude-fable-5-2?m=chat)
|
|
153
|
+
for account availability and package-dependent prices; model discovery alone does
|
|
154
|
+
not guarantee a successful generation.
|
|
155
|
+
|
|
156
|
+
```typescript
|
|
157
|
+
const fable = new AceDataCloud({
|
|
158
|
+
apiToken: 'your-token',
|
|
159
|
+
baseURL: 'https://api.acedata.cloud',
|
|
160
|
+
});
|
|
161
|
+
const response = await fable.chat.messages.create({
|
|
162
|
+
model: 'claude-fable-5-2',
|
|
163
|
+
messages: [{ role: 'user', content: 'Explain this code.' }],
|
|
164
|
+
maxTokens: 4096,
|
|
165
|
+
output_config: { effort: 'high' },
|
|
166
|
+
});
|
|
167
|
+
```
|
|
168
|
+
|
|
146
169
|
## OpenAI Embeddings
|
|
147
170
|
|
|
148
171
|
```typescript
|
|
@@ -304,6 +327,13 @@ not trigger reference-video billing. Do not combine `videoList` with
|
|
|
304
327
|
|
|
305
328
|
## Suno music processing
|
|
306
329
|
|
|
330
|
+
`await client.suno.persona({ name, audioId })` creates a singer style with
|
|
331
|
+
`POST /suno/persona`; creation still follows the endpoint's pricing rules.
|
|
332
|
+
Listing with `GET /suno/persona` and deleting with `DELETE /suno/persona` are
|
|
333
|
+
free and require no extra billing-bypass header. Normal API authentication
|
|
334
|
+
still applies. The SDK currently provides only the creation helper; listing
|
|
335
|
+
and deletion require direct HTTP requests, not calls to `.persona(...)`.
|
|
336
|
+
|
|
307
337
|
For a private voice created by `client.suno.voices(...)`, upload the original
|
|
308
338
|
song with `await client.suno.upload({ audioUrl: sourceUrl, personaId })`.
|
|
309
339
|
This field is supported only for standard uploads (the default), not
|
package/package.json
CHANGED