@juspay/neurolink 12.44.3 → 12.44.5
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/CHANGELOG.md +2 -2
- package/README.md +2 -2
- package/dist/browser/neurolink.min.js +3 -3
- package/dist/constants/tokens.d.ts +6 -6
- package/dist/constants/tokens.js +6 -6
- package/dist/factories/providerDescriptors.js +3 -3
- package/dist/models/manifests/google-ai.js +3 -3
- package/dist/models/modelRegistry.js +2 -2
- package/dist/providers/perplexityDecider.js +7 -1
- package/docs-site/static/search-index.json +6 -6
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
|
1
|
-
## [12.44.
|
|
1
|
+
## [12.44.5](https://github.com/juspay/neurolink/compare/v12.44.4...v12.44.5) (2026-10-02)
|
|
2
2
|
|
|
3
3
|
### Bug Fixes
|
|
4
4
|
|
|
5
|
-
- **(
|
|
5
|
+
- **(decide):** classify the image-wording over-length 400 as max_tokens_exceeded and record the measured limits ([4605bba](https://github.com/juspay/neurolink/commit/4605bba765fc39d8a1c0942c72e487193e59f930))
|
|
6
6
|
|
|
7
7
|
## [11.2.3](https://github.com/juspay/neurolink/compare/v11.2.2...v11.2.3) (2026-08-19)
|
|
8
8
|
|
package/README.md
CHANGED
|
@@ -390,8 +390,8 @@ Measured against TypeSafe's live API — don't extrapolate past these:
|
|
|
390
390
|
|
|
391
391
|
The figures above are TypeSafe's. Perplexity's Decisions API, measured on a real account in October 2026:
|
|
392
392
|
|
|
393
|
-
- Up to 128 questions and 8 images per request. The server reads under 262,144 input tokens (the state and the
|
|
394
|
-
- Latency grows faster than linearly with input: 3.9 s at 65,000 tokens, 10 s at 146,000, 22.9 s at 251,000 (about 17,000, 15,000 and 11,000 tokens per second). An image costs about one input token per 32 × 32 tile plus about 95
|
|
393
|
+
- Up to 128 questions and 8 images per request. The server reads under 262,144 input tokens (the state, the questions and the images all count; an image counts one token per 32 × 32 tile, measured) and refuses more with an explicit 400; it never cuts a state off silently.
|
|
394
|
+
- Latency grows faster than linearly with input: 3.9 s at 65,000 tokens, 10 s at 146,000, 22.9 s at 251,000 (about 17,000, 15,000 and 11,000 tokens per second). An image costs about one input token per 32 × 32 tile, plus about 95 to 103 tokens that look like fixed request overhead.
|
|
395
395
|
- 10 requests per second on the account tested; a 429 carries `Retry-After`, which NeuroLink honours.
|
|
396
396
|
- NeuroLink's own state window is 100,000 estimated tokens, a deliberate local limit and not the server's. The price, $0.04 per million input tokens (image tokens included, output free), is Perplexity's documented figure.
|
|
397
397
|
|