|
An endpoint that reports the API credit balance, and a 401 that says which balance is empty
|
|
3
|
43
|
October 26, 2026
|
|
Decisions API: shared state counted per question in usage.input_tokens
|
|
10
|
147
|
October 26, 2026
|
|
Mac app 26.24.0 (28) – all MCP tools broken and irrecoverable in Spaces
|
|
12
|
730
|
October 26, 2026
|
|
You can now run pplx-decider-flash-v1.2 locally on your Mac, without an API key
|
|
0
|
87
|
October 23, 2026
|
|
Adding claude reasoning/thinking controls to the agent/responses api
|
|
1
|
40
|
October 22, 2026
|
|
Pplx-decider-v1.2 is the highest scoring decision model on ClaimBench
|
|
0
|
94
|
October 20, 2026
|
|
Billing-read OAuth for API cost dashboards
|
|
2
|
71
|
October 20, 2026
|
|
Agent API: prompt caching for openai/gpt-6.1-sol (cache writes billed, breakpoints dropped)
|
|
0
|
19
|
October 20, 2026
|
|
plans to add the `google/gemini-4-argon` model to the Agent API
|
|
1
|
37
|
October 19, 2026
|
|
Agent API using credit balance, which we never used
|
|
1
|
22
|
October 19, 2026
|
|
Hack The Nest at EMU (Nov 14-15): who should I talk to about API credits for student hackers?
|
|
3
|
44
|
October 14, 2026
|
|
Decisions API returns near-uniform probabilities for every question, including the quickstart example
|
|
2
|
50
|
October 13, 2026
|
|
Reg: Dashboard and Billing
|
|
0
|
26
|
October 12, 2026
|
|
Agent API using credit
|
|
1
|
56
|
October 12, 2026
|
|
Pplx-decider-v1.1-27b scores the highest on Decision Bench for accuracy, with the lowest cost
|
|
0
|
95
|
October 9, 2026
|
|
The Agent API does not output image URLs
|
|
8
|
99
|
October 7, 2026
|
|
We're releasing pplx-embed-v2-late, two late-interaction embedding models that retrieve text, images, and pages with a shared embedding space for cross-model querying
|
|
0
|
299
|
October 7, 2026
|
|
Starting new user costs
|
|
4
|
211
|
October 7, 2026
|
|
Pplx-decider-v1.1-27b, our updated open weights multimodal decision model, is now available
|
|
0
|
953
|
October 6, 2026
|
|
We built a new way to train contextual embedding models, which encode each chunk of a document with the whole document in view
|
|
0
|
56
|
September 30, 2026
|
|
Unreachable RPM values on Agent API Rate Limits docs table
|
|
4
|
101
|
September 29, 2026
|
|
You can now build custom reusable agents in the Perplexity Agent API with Profiles, Skills, and managed connectors
|
|
0
|
76
|
September 28, 2026
|
|
Perplexity search results format: Need option to Hide Computer After Searches
|
|
0
|
29
|
September 28, 2026
|
|
Preserve AI-suggested follow-up prompts after the user begins typing
|
|
0
|
13
|
September 28, 2026
|
|
Add a batch query endpoint to Sonar
|
|
0
|
22
|
September 27, 2026
|
|
Keep support for Sonar-pro on the Agents API
|
|
1
|
97
|
September 25, 2026
|
|
Contextualized Embeddings endpoint (/v1/contextualizedembeddings) rate-limits per chunk instead of per request
|
|
1
|
52
|
September 24, 2026
|
|
Introducing Fast Search in the Perplexity Search API
|
|
0
|
116
|
September 24, 2026
|
|
Standard embeddings — x-ratelimit-limit meters input texts, not requests; documented 512-text batch unreachable at Tier 1
|
|
5
|
101
|
September 23, 2026
|
|
API function for Max users: token balance, history of usage, refill settings
|
|
4
|
128
|
September 20, 2026
|