Nederlands
Perplexity Developers
Melden

Perplexity Developers✓

@perplexitydevs

Official @perplexity_ai developer account for real-time API updates.

39 Volgend8.1K Volgers176 Berichten
  1. Perplexity Developers✓@perplexitydevs
    You can now run pplx-decider-flash-v1.2 locally on your Mac, without an API key. Decider for Mac is an app that runs the 4B decision model on device. Ask a question about text or an image and get a probability back, all on your machine.
    Downloaden
    214846298.1K
  2. Perplexity Developers✓@perplexitydevs
    Berichten @perplexitydevs
    After a one-time 5.8 GB model download, the app serves the Decisions API at localhost:8080/v1/decisions. Use it to label files, route messages, check screenshots, or run a pre-commit check, all without data leaving your Mac.
    Downloaden
    11333.6K
  3. Perplexity Developers✓@perplexitydevs
    Berichten @perplexitydevs
    Requires a Mac with Apple silicon, macOS 13 or later, and 16 GB of memory.
    11232.5K
  4. Perplexity Developers✓@perplexitydevs
    The Batch API is now available on the Agent API. Upload a JSONL file of up to 50,000 requests, create a batch, and download the results when it finishes.
    253834.4K
  5. Perplexity Developers✓@perplexitydevs
    Berichten @perplexitydevs
    Every batch request runs the full Agent API loop, which means built-in tools like web_search and fetch_url work inside a batch. You can use any model from the Agent API models list.
    115849
  6. Perplexity Developers✓@perplexitydevs
    Berichten @perplexitydevs
    Try the new cookbook tutorial to enrich a CSV of companies overnight. One web-grounded Agent API request per row, written to JSONL, run as a batch, and joined back to your rows as enriched data.
    014421
  7. Perplexity Developers✓@perplexitydevs
    pplx-decider-v1.2 is the highest scoring decision model on ClaimBench. Try pplx-decider-v1.2 and pplx-decider-flash-v1.2 on OpenRouter or Perplexity API Console.
    Vals AI @ValsAI
    Today we’re releasing ClaimBench, our new benchmark targeted towards decision models. It tests whether a model can tell if a financial document supports, contradicts, or doesn’t address a claim. We evaluated 15 models on 1,960 claims paired with 10-K excerpts, with Decider V1.2 leading the pack of decision models.
    54513.7K
  8. Vals AI✓@ValsAI
    Today we’re releasing ClaimBench, our new benchmark targeted towards decision models. It tests whether a model can tell if a financial document supports, contradicts, or doesn’t address a claim. We evaluated 15 models on 1,960 claims paired with 10-K excerpts, with Decider V1.2 leading the pack of decision models.
    Downloaden
    191012627K
  9. Perplexity Developers✓@perplexitydevs
    pplx-decider-v1.2 (27B) and pplx-decider-flash-v1.2 (4B) are now available on OpenRouter.
    OpenRouter @OpenRouter
    Perplexity Decider v1.2 and Decider Flash v1.2 are now on OpenRouter @perplexity_ai's open-weights decision models take text or images and return typed answers with probabilities - Decider v1.2: a new 27B checkpoint, succeeding v1.1 - Decider Flash v1.2: 4B, faster and half the cost
    26692.8K
  10. OpenRouter✓@OpenRouter
    Perplexity Decider v1.2 and Decider Flash v1.2 are now on OpenRouter @perplexity_ai's open-weights decision models take text or images and return typed answers with probabilities - Decider v1.2: a new 27B checkpoint, succeeding v1.1 - Decider Flash v1.2: 4B, faster and half the cost
    11811947.5K
  11. Perplexity Developers✓@perplexitydevs
    Our next generation of open weights multimodal decision models comes in two sizes, pplx-decider-v1.2 and pplx-decider-flash-v1.2. Text and vision scores improve. Inference is up to 5x faster: all questions in a request run in one pass. Flash is the top 4B on the Decision Index.
    Downloaden
    2940345113K
  12. Perplexity Developers✓@perplexitydevs
    Berichten @perplexitydevs
    pplx-decider-v1.2 is the 27B default for nuanced decisions at $0.02 per million input tokens. pplx-decider-flash-v1.2 is for high-volume decisions with clear criteria like routing, labeling, and filtering, at half the price.
    12182.8K
  13. Perplexity Developers✓@perplexitydevs
    Berichten @perplexitydevs
    pplx-decider-v1.2 ranks #2 overall on the Hugging Face Decision Index. Open weights for both models are available to run on your own infrastructure.
    Downloaden
    01142.1K
  16. Perplexity Developers✓@perplexitydevs
    pplx-decider-v1.1-27b scores the highest on Decision Bench for accuracy, with the lowest cost. It reached 94.5% accuracy across 1071 cases at $0.017 per 1,000 decisions. Full evaluation: Get Started:
    Downloaden
    212526721.5K
  17. Perplexity Developers✓@perplexitydevs
    Berichten @perplexitydevs
    The Decisions API accepts text and image inputs. Our new cookbook builds a browser agent that sends a screenshot and questions to pplx-decider-v1.1-27b. Your code turns the returned probabilities into clicks, scrolls, and stops.
    2161.2K
  18. Perplexity Developers✓@perplexitydevs
    pplx-decider-v1.1-27b is now available on OpenRouter.
    OpenRouter @OpenRouter
    Perplexity Decider v1.1 is now on OpenRouter @perplexity_ai's open-weights multimodal decision model takes text, JSON, or images and returns typed answers with probabilities $0.02/M input. Output is free
    65749.9K
  19. OpenRouter✓@OpenRouter
    Perplexity Decider v1.1 is now on OpenRouter @perplexity_ai's open-weights multimodal decision model takes text, JSON, or images and returns typed answers with probabilities $0.02/M input. Output is free
    Perplexity Developers @perplexitydevs
    pplx-decider-v1.1-27b, our updated open weights multimodal decision model, is now available. It scores the highest on the new @huggingface Decision Index 0.3 benchmark. pplx-decider-v1.1-27b costs half as much as v1, at $0.02 per million input tokens.
    282524237.6K
  20. Perplexity Developers✓@perplexitydevs
    pplx-decider-v1.1-27b, our updated open weights multimodal decision model, is now available. It scores the highest on the new @huggingface Decision Index 0.3 benchmark. pplx-decider-v1.1-27b costs half as much as v1, at $0.02 per million input tokens.
    Downloaden
    4763567181K
  21. Perplexity Developers✓@perplexitydevs
    Berichten @perplexitydevs
    pplx-decider-v1.1-27b has a 250k context window and supports text and image input. View the weights on Hugging Face: Get started with the Perplexity Decisions API:
    20525K
  22. Perplexity Developers✓@perplexitydevs
    We're looking forward to working with the new @NVIDIA Vera CPU on SPACE.
    Downloaden
    Paul Fryzel @paulfryzel
    It was great to have the @NVIDIA team stop by and drop off their new Vera CPU. A lot of what we’re building depends on agents being able to run more capable code environments, safely and reliably. We’re excited to test this work on Vera.
    5813859.1K
  23. Paul Fryzel✓@paulfryzel
    It was great to have the @NVIDIA team stop by and drop off their new Vera CPU. A lot of what we’re building depends on agents being able to run more capable code environments, safely and reliably. We’re excited to test this work on Vera.
    Downloaden
    245321.3K
  24. Perplexity Developers✓@perplexitydevs
    Introducing the Perplexity Decisions API. It's powered by pplx-decider-v1-27b, our multimodal decision model trained to output a probability distribution over a fixed set of answers instead of text. It costs $0.04/million input tokens and scores 85.71% across benchmarks.
    Downloaden
    6194873254K
  25. Perplexity Developers✓@perplexitydevs
    Berichten @perplexitydevs
    pplx-decider-v1-27b is fine-tuned from Qwen3.8-27B with a 250k context window. View the weights on Hugging Face: Get started with the Perplexity Decisions API:
    41013515.5K
  26. Perplexity Developers✓@perplexitydevs
    Berichten @perplexitydevs
    You can use pplx-decider-v1-27b to triage customer support tickets, then route escalations to the Agent API. Our cookbook shows how to build the workflow, using the Decisions API for the initial decision and the Agent API for escalated requests.
    10366.6K