Perplexity: Sonar
Sonar is a language model from Perplexity released on Jan 1, 2024. It reads text and writes text, with a 128K token context window and up to 4K tokens per reply.
Show moreShow less
It costs $1 per million input tokens and $1 per million output tokens.
It supports tool calling and structured JSON output.
11 providers serve it, including Vercel AI Gateway, DevPass (LLM Gateway) and LLM Gateway. The lowest input price is $0.25 per million tokens at Vercel AI Gateway.
- Modalities
- In / out price
- $1 / $1 per 1M
- Context
- 128K
- Max output
- 4K
- Released
- Jan 1, 2024
- Knowledge cutoff
- Sep 2025
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Sonar pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $1 / 1M tokens | |
|---|---|---|
| Output | $1 / 1M tokens |
Sonar providers
11 providers serve it, including Vercel AI Gateway, DevPass (LLM Gateway) and LLM Gateway. The lowest input price is $0.25 per million tokens at Vercel AI Gateway. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Perplexity First party | $1 | $1 | – | 128K | 4K |
| Vercel AI Gateway | $0.25 | $2.50 | – | 127K | 8K |
| DevPass (LLM Gateway) | $0.25 | $2.50 | – | 130K | 4K |
| LLM Gateway | $0.25 | $2.50 | – | 130K | 4K |
| Perplexity Agent | $0.25 | $2.50 | $0.0625 | 128K | 8K |
| Eden AI | $1 | $1 | – | 127K | 4K |
| Helicone | $1 | $1 | – | 127K | 4K |
| Kilo Gateway | $1 | $1 | – | 127K | 114K |
| Opper | $1 | $1 | – | 128K | 4K |
| SAP AI Core | $1 | $1 | – | 128K | 4K |
| AI/ML API | $1.30 | $1.30 | – | 128K | 100K |
What Sonar costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Sonar through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Temperature
temperature
Alternatives to Sonar
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 22.9
Reads text. Tool calling, structured output, reasoning. Served by 18 providers.
by nvidiaJun 4, 20261M context$0.50/M input tokens$2.50/M output tokens18 providers
- Index 36
Reads text. Tool calling, structured output, reasoning. Served by 56 providers.
by deepseekApr 24, 20261M context$0.66/M input tokens$1.98/M output tokens56 providers
- Index 22.2
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 24 providers.
by googleJul 9, 20261.05M context$0.30/M input tokens$2.50/M output tokens24 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 32 providers.
by googleMar 20, 2025$0.30/M input tokens$2.50/M output tokens32 providers
- 262K context
Reads text and images. Tool calling, structured output. Served by 15 providers.
by mistralaiNov 1, 2024$0.50/M input tokens$1.50/M output tokens15 providers
- Index 25.2
Reads text, images and video. Tool calling, structured output, reasoning. Served by 24 providers.
by qwenJun 2, 20261M context$0.40/M input tokens$1.60/M output tokens24 providers
More from Perplexity
Embed v1 0.6b
Embeddings32K contextTurns text into vectors for search and retrieval.
by perplexityFeb 26, 2026
Embed v1 4b
Embeddings32K contextTurns text into vectors for search and retrieval.
by perplexityFeb 26, 2026
- 200K context
Reads text and images. Structured output, reasoning.
by perplexityOct 30, 2025$3/M input tokens$15/M output tokens
- 128K context
Reads text. Reasoning. Served by 6 providers.
by perplexityJan 27, 2025$2/M input tokens$8/M output tokens6 providers
- 200K context
Reads text and images. Structured output. Served by 8 providers.
by perplexityJan 1, 2024$3/M input tokens$15/M output tokens8 providers
- 128K context
Reads text and images. Structured output, reasoning. Served by 6 providers.
by perplexityJan 1, 2024$2/M input tokens$8/M output tokens6 providers
Sonar questions
How much does the Sonar API cost?
$1 per million input tokens and $1 per million output tokens. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Sonar?
128,000 tokens of input, and it can write up to 4,096 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Sonar?
11 providers serve it, including Vercel AI Gateway, DevPass (LLM Gateway) and LLM Gateway. The lowest input price is $0.25 per million tokens at Vercel AI Gateway. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Sonar support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Sonar open source?
No. Perplexity serves it through an API only, so you cannot download the weights or host it yourself.
When was Sonar released?
Jan 1, 2024, with training data up to Sep 2025.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on Sonar?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting