sonar
Sonar is Perplexity’s lightweight, affordable and fast search-grounded model, with citations and customizable sources, for adding simple question-answering features.
料金： 入力：100 万トークンあたり 240 クレジット（約 $1.20）、出力：100 万トークンあたり 240 クレジット（約 $1.20）。
料金更新日
今日はどんなお手伝いができますか？
このデモページにはクライアントの完全な記憶機能はありません。すべての機能をご利用いただくには、クライアントまたは CLI から接続してください。
Perplexity のほかの AI モデル
Sonar API on ModelFold
Sonar is Perplexity’s lightweight, affordable and fast search-grounded model, with citations and customizable sources, for adding simple question-answering features. Try Sonar in the ModelFold Playground, then call it from your own code through an OpenAI-compatible chat completions API.
What Is the Sonar API
Sonar at a glance
Sonar is a chat model from Perplexity. It accepts text and images as input and returns text, with a context window of up to 127K tokens.
Use it without hosting anything
On ModelFold you call Sonar with a single API key — no model weights to download and no inference servers to run. The same key also works for the other chat, image, video and audio models on ModelFold.
Core Capabilities of Sonar
Up to 127K tokens of context
Keep long conversations, large documents and sizeable code in a single request, so the model can reason over the full material instead of fragments.
Understands images
Besides text, Sonar accepts images as input, so a single request can combine instructions with visual or other media.
How to Use Sonar on ModelFold
- 1
Step 1: Try it in the Playground
Open the Playground at the top of this page, type a prompt and see how Sonar responds before writing any code.
- 2
Step 2: Create an API key
Sign in to ModelFold and create an API key in the console. Keep it secret and send it as a Bearer token.
- 3
Step 3: Send a request
Call POST https://modelfold.ai/v1/chat/completions with "model": "sonar" and your messages. Existing OpenAI-compatible SDKs work by changing the base URL and key.
- ✓
Step 4: Ship and monitor
Integrate the response into your product and check token usage and spend for every call in the console logs.
What You Can Build with Sonar
High-volume pipelines
Run classification, extraction, rewriting and batch jobs at scale where cost per request matters.
Low-latency experiences
Power chat interfaces, autocomplete and interactive tools where users expect fast responses.
Long-document workflows
Feed in long reports, contracts, manuals or codebases and ask for summaries, comparisons and answers grounded in the material.
Frequently Asked Questions
What is Sonar?⌄
Sonar is Perplexity’s lightweight, affordable and fast search-grounded model, with citations and customizable sources, for adding simple question-answering features.
Which inputs does Sonar support?⌄
Sonar accepts text and images and returns text. Through ModelFold you can send text and images (OpenAI-style image_url content); in the Playground you can also attach documents, which are converted to text.
How long is the context window of Sonar?⌄
Up to 127K tokens, shared between your input and the model’s output.
Does Sonar support function calling?⌄
Function calling is not listed for Sonar; requests that include tools will be rejected. Use plain prompts or JSON output instead.
How is Sonar billed on ModelFold?⌄
Pay as you go by tokens: input and output tokens are charged at the per-million-token prices shown on this page. There is no monthly fee, and failed requests are not charged.
How do I call Sonar through the API?⌄
Send a POST request to https://modelfold.ai/v1/chat/completions with "model": "sonar", using your ModelFold API key as the Bearer token.
| 入力 | 240 クレジット 1M tokens≈ $1.20 |
| 出力 | 240 クレジット 1M tokens≈ $1.20 |
トークン単位で課金し、入力と出力は別料金です。思考トークンは出力に含まれます。Playground でも同じ計算を使います。
API ドキュメントを見る →AI Agents · Claude Code / Cursor / Trae →curl https://modelfold.ai/v1/chat/completions \
-H "Authorization: Bearer $MODELFOLD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"sonar","messages":[{"role":"user","content":"Hello"}]}'