ChatGPT vs Perplexity
Both are ai tools. Here is what separates them.
| ChatGPT | Perplexity | |
|---|---|---|
| Category | AI | AI |
| Pricing model | freemium | freemium |
| Price from | Freemium | Freemium |
| Upvotes | 8 | 6 |
| What it does | OpenAI's assistant, with browsing, images and code execution built in. | An answer engine that cites its sources instead of listing ten blue links. |
What ChatGPT is
ChatGPT is OpenAI's assistant, reached through a web app, a desktop app and mobile apps. The free tier is listed at $0 per month, and everything above it is sold either as a subscription or, for developers, as an API key that bills per token at published API rates instead. Three models are listed: GPT-5.6 Sol, GPT-5.6 Terra and GPT-5.6 Luna. Each carries a context window of about 1.05 million tokens and a maximum output of 128K tokens, so what separates them is the cost of running them rather than how much they can read at a time. The Plus allowances make that concrete. Counted per five hour window, Sol runs to roughly 10 to 100 messages, Terra to 20 to 170, and Luna to 215 to 1,720. Choosing a model is partly a decision about how many turns a working session needs. ChatGPT Go is listed at $8 per month and Plus at $20 per month, with Pro starting from $100. ChatGPT Business is $25 per user per month billed monthly, or $20 per user per month on annual billing, and a Business Premium seat carries five times the usage allowance of a Business Standard seat. Enterprise and Edu are quoted through sales, drop fixed rate limits altogether and scale usage with credits instead. Codex is reachable from the web, a command line interface, an IDE extension and iOS. ChatGPT is also a host for third-party apps. An app is built on a Model Context Protocol server combined with skills and optional UI, and selected MCP tools can return UI resources back into the conversation. Anything bound for the public directory passes through a public review process first, and the developer guidelines are specific about what gets in. An app must supply a privacy policy before it can be installed. Its name cannot be a single dictionary word unless there is a genuine brand connection behind it. It may not collect payment card data, health information, government IDs or authentication credentials through its input schema. It must suit a general audience that includes users aged 13 to 17, and may not target children under 13. Apps that transact are limited to physical goods, with digital products, subscriptions, tokens and credits all prohibited. On the compliance side, OpenAI holds SOC 2 Type 2 along with ISO 27001:2022, ISO 27017:2015, ISO 27018:2019, ISO 27701:2019 and ISO/IEC 42001:2023 attestations, and runs a responsible disclosure programme through Bugcrowd.
What Perplexity is
Perplexity sells four developer APIs for web search and web grounded answers: a Router API, an Agent API, a Search API and an Embeddings API. Requests authenticate with a bearer token supplied in the Authorization header, and billing is pay as you go, with no subscription required. The Agent API returns answers grounded in the web with citations attached, and it can also route a request to third party models from OpenAI, Anthropic, Google and xAI. The Search API is the lower level option, returning ranked raw web results rather than a written answer. Each result carries a title, a URL and a content snippet, with publication and last updated dates available as optional fields. A call accepts between one and twenty results and returns ten by default, can be restricted to at most twenty domains and twenty languages, and can be filtered by publication date, by last updated date, or by a recency window of an hour, day, week, month or year. The Router API puts open weight models hosted by Perplexity behind a single OpenAI compatible endpoint. Pricing differs by product. The Search API is 5.00 USD per 1,000 requests. Sonar is billed at 1 USD per million input tokens and 1 USD per million output tokens plus a per request fee, and Sonar Pro at 3 USD per million input tokens and 15 USD per million output tokens plus a per request fee. Agent API tool calls are billed per invocation: 0.0025 USD for a web search, 0.0005 USD for fetching a URL, and 0.005 USD each for people search and finance search. Third party models routed through the Agent API are billed per million tokens. Embeddings are cheaper again. The pplx-embed-v1-0.6b model returns 1024 dimensions, accepts up to 32K tokens and costs 0.004 USD per million tokens, while pplx-embed-v1-4b returns 2560 dimensions at 0.03 USD per million tokens. Rate limits are tied to spend. Access is banded into six usage tiers, running from Tier 0 at zero cumulative credit purchased up to Tier 5 at 5,000 USD or more, and Agent API limits rise across that range from 50 requests per minute to 8,000. The Search API is the exception, capped at 50 query units per second regardless of tier. Beyond the raw endpoints, Perplexity publishes a Python SDK and a TypeScript SDK, plus a command line tool that returns structured JSON search results and extracts passages from up to 50 URLs in a single call. On data handling, it operates a zero data retention policy for the Chat Completions API and keeps no prompt or response content, states that customer API data is not used to train its models, and holds a SOC 2 Type II report published through its trust portal.
We are not affiliated with either product. Upvote counts come from the published formula and neither position was paid for.