Last refreshed 2026-11-13. Next refresh: weekly.
Why use pplx-decider-v1.3 on Vercel AI Gateway?
Vercel AI Gateway offers pplx-decider-v1.3 with pay-as-you-go pricing at $0.02/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.
Compare pplx-decider-v1.3 across 2 providers to find the best fit for your use caseSetup recipe
Python + curlpip install openaiexport AI_GATEWAY_API_KEY=...import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],perplexity/pplx-decider-v1.3Request example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="perplexity/pplx-decider-v1.3",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "perplexity/pplx-decider-v1.3", not the LLMReference slug "pplx-decider-v1.3".
- creator/model-name e.g. kwaipilot/kat-coder-pro-v2
- The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.
Compare pplx-decider-v1.3 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Perplexity Labs | $0.02 | Free |
| Vercel AI Gateway | $0.02 | Free |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.02 |
| Output tokens | Free |
Capabilities
About pplx-decider-v1.3
pplx-decider-v1.3 is Perplexity's 27B multimodal decision model, released November 12, 2026 as the successor to pplx-decider-v1.2 on the Qwen3.8-27B backbone, with open weights under Apache 2.0. Instead of generating text it returns probabilities: it reads a state of text, JSON or images and answers named yes/no (noul), choice and score questions in one pass, each question isolated from the others. v1.3 adds locate questions, which extract verbatim text spans from the state with character offsets and confidence scores.