Skip to content
PerplexityChatsonarTemporarily unavailable

Sonar API

Input
$0.25per 1M tokens
Output
$2.5per 1M tokens
Context
130K
No gateway feesPay-as-you-go only

Sonar for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Explore Sonar for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses through the unified API. Supported interfaces and current availability are shown below.

  • OpenAI-style Chat Completions
  • Anthropic-style Messages
  • OpenAI-style Responses

Model details

Context window
130K tokens
Max output
—
Input
Text
Output
Text
Capabilities
Streaming
Interfaces
OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses

Sonar API pricing

Prices use the units shown below. No gateway fees. Usage, size and model options may affect the total.

Sonar pricing.
MetricPrice
/ 1M input tokens$0.25
/ 1M output tokens$2.5
/ 1M cache write tokens (5 min)$0.25
/ web search$0.0025

What Sonar costs for real work

Typical workloads at list price, worked out from the rates above. Nothing is added on top.

WorkloadTokensCost
1,000 chat replies1,500 tokens in, 400 out, each$1.38
Summarise a 100-page document60K tokens in, 2K out$0.020
10M tokens of coding-agent work10M tokens: 85% cached input, 12% fresh input, 3% output$3.17
1M output tokensGenerated text only$2.50

Sonar is pay-as-you-go only

Sonar is not included in Token Plans. Call it from a pay-as-you-go balance at the list price above, with no gateway fee.

Why teams pick it

  • Sonar for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

API availability

This model is temporarily unavailable. You can compare its features and pricing, but requests are not currently accepted.

/v1/chat/completionsOpenAI-style Chat Completions · openai SDK or plain HTTP

Temporarily unavailable

/v1/messagesAnthropic-style Messages · @anthropic-ai/sdk SDK or plain HTTP

Temporarily unavailable

/v1/responsesOpenAI-style Responses · openai SDK or plain HTTP

Temporarily unavailable

Use Sonar in your tools

Every coding agent below has a setup guide. Set the model to sonar.

Run Sonar in Claude Code

More from Perplexity

Alternatives to Sonar

Questions about this model

How much does the Sonar API cost?
Sonar costs $0.25 per 1M input tokens and $2.5 per 1M output tokens on Inferray. That is the list price, with no gateway fee on top.
Is there a free tier for Sonar?
No. You add credit and pay Sonar's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.
Am I charged for failed requests?
No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.
Is Sonar included in Token Plans?
No. Sonar is pay-as-you-go only; Token Plans cover the other text models in the catalog.
Can I use Sonar in Claude Code?
Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to sonar. The same key works in Codex, opencode, Cline, and other agents.
Does Sonar support tool calling and vision?
Sonar supports streaming on Inferray. It does not take image input. It does not support tool calling.
Is it the real Sonar?
Yes. A request for sonar is answered by Sonar from Perplexity, billed at its published list price. Inferray never substitutes a different or smaller model.

Prices from the catalog as of November 12, 2026.