Sonar API
- Input
- $0.25per 1M tokens
- Output
- $2.5per 1M tokens
- Context
- 130K
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.
| Metric | Price |
|---|---|
| / 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.
| Workload | Tokens | Cost |
|---|---|---|
| 1,000 chat replies | 1,500 tokens in, 400 out, each | $1.38 |
| Summarise a 100-page document | 60K tokens in, 2K out | $0.020 |
| 10M tokens of coding-agent work | 10M tokens: 85% cached input, 12% fresh input, 3% output | $3.17 |
| 1M output tokens | Generated 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.
Temporarily unavailable
Temporarily unavailable
Temporarily unavailable
Use Sonar in your tools
Every coding agent below has a setup guide. Set the model to sonar.
More from Perplexity
Alternatives to Sonar
- Qwen3.5 27BQwen3.5 27B for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Alibaba
- Devstral 2Devstral 2 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Mistral
- Gemini 3.5 Flash LiteThe fastest, cheapest 3.5 model for high-throughput work.Google
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.