Last refreshed 2026-06-29. Next refresh: weekly.
Why use Sonar on Vercel AI Gateway?
Vercel AI Gateway offers Sonar with competitive pricing. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.
Compare Sonar across 3 providers to find the best fit for your use caseInput / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export AI_GATEWAY_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],Model ID
perplexity/sonarRequest example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="perplexity/sonar",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "perplexity/sonar", not the LLMReference slug "sonar".
- creator/model-name e.g. kwaipilot/kat-coder-pro-v2
- The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.
Compare Sonar Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| OpenRouter | $1.00 | $1.00 |
| Perplexity Labs | $1.00 | $1.00 |
| Vercel AI Gateway | — | — |
Capabilities
Structured Outputs
About Sonar
Lightweight, cost-effective Perplexity search model with grounding and citations. Request fees: $5-$12/1K requests depending on search context depth (Low/Medium/High).
Get Started
Model Specs
Released2025-01-27
Context127k
ArchitectureDecoder Only