Sonar API127K context
Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources.
Pricing & specs mirror our live pricing as of July 2026 (pay-as-you-go).
What is Sonar?
Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...
Sonar on the release timeline
Sonar pricing
Pay-as-you-go on DataLLM Lab — these are our live list prices (identical to the pricing page):
| Model | Input / 1M | Output / 1M | Cache read | Cache write | Context |
|---|---|---|---|---|---|
| Sonar | $1.00 | $1.00 | — | — | 127K |
On output price, Sonar is cheaper than 60% of the 309 models in the catalog.
What Sonar costs per month
| Workload | Tokens in / out (monthly) | Est. cost |
|---|---|---|
| Support chatbot | 40M / 12M | $52.00 |
| RAG / knowledge base | 200M / 20M | $220 |
| Coding agent | 80M / 25M | $105 |
| Batch extraction | 150M / 8M | $158 |
| Content generation | 20M / 40M | $60.00 |
Estimate your own monthly cost
Cost = input price × input volume + output price × output volume. The same five workloads run on every model page, so any two compare directly.
Sonar vs alternatives
| Model | Input / 1M | Output / 1M | Context | Our test |
|---|---|---|---|---|
| Sonar | $1.00 | $1.00 | 127K | — |
| Sonar Deep Research | $2.00 | $8.00 | 128K | — |
| Sonar Reasoning Pro | $2.00 | $8.00 | 128K | — |
| Sonar Pro | $3.00 | $15.00 | 200K | — |
| Weaver (alpha) | $0.75 | $1.00 | 8K | — |
| Hermes 3 405B Instruct | $1.00 | $1.00 | 131K | — |
When not to use Sonar
- It is served by a single provider, so there is less failover headroom during an outage.
Specs
| Model ID | perplexity/sonar |
| Modality | text+image->text (input: text, image) |
| Context window | 127,072 tokens |
| Tool / function calling | — |
| Structured output (JSON) | — |
| Released | 2025-01-27 |
| Open weights | — (hosted API only) |
How to call Sonar
from openai import OpenAI
client = OpenAI(base_url="https://api.datallmlab.com/v1", api_key="YOUR_DATALLM_LAB_KEY")
resp = client.chat.completions.create(
model="perplexity/sonar",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)curl https://api.datallmlab.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"perplexity/sonar","messages":[{"role":"user","content":"Hello"}]}'import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.datallmlab.com/v1", apiKey: process.env.DATALLM_KEY });
const r = await client.chat.completions.create({
model: "perplexity/sonar",
messages: [{ role: "user", content: "Hello" }],
});
console.log(r.choices[0].message.content);The same key routes Sonar and 300+ other models — switch models by changing one string. How OpenAI-compatible APIs work.
Prompting tips for Sonar
- Be explicit and show the shape of the answer. Spell out format, tone and constraints up front, and include one short example of the output you want — Sonar follows concrete instructions better than abstract ones.
- It reads images. Send image parts alongside your text and ask for specific outputs (named JSON fields, a table, "what changed") rather than "describe this".
Tips are derived from Sonar's actual capabilities — context window, tool & JSON support, modality and price tier — not generic advice.
Open-source tools for Sonar
Popular open-source frameworks and agents to build with Sonar over the API — star counts pulled from GitHub (July 2026).
Listed by GitHub stars; inclusion is by ecosystem relevance (agent frameworks, SDKs and gateways), not affiliation. Stars change — see each repo for current numbers.
Migrating to Sonar
Coming from OpenAI or another gateway? On an OpenAI-compatible setup the only changes are base_url → https://api.datallmlab.com/v1 and model → perplexity/sonar. Messages, streaming and the rest of your code stay the same. Routing & failover guide.
Rate limits & reliability
Rate limits here are the DataLLM Lab gateway's, not the upstream vendor's. On 429 (rate limited) or 503 (provider busy), retry with exponential backoff. See the error-code guide and failover setup.
Related reading
Call Sonar with one key
300+ models behind one OpenAI-compatible endpoint — better prices, better uptime, no subscriptions.
Get an API keyCompare pricingFrequently asked questions
What is Sonar?
Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It accepts text, image input with a 127K-token context window and was released on 2025-01-27. On DataLLM Lab it is callable through one OpenAI-compatible endpoint.
How much does Sonar cost?
On DataLLM Lab it is $1.00 per 1M input tokens and $1.00 per 1M output tokens — cheaper than about 60% of the 309-model catalog on output price. Pay-as-you-go, no subscription.
What is the context window of Sonar?
127K tokens.
Is Sonar open source?
No open weights are published — it is available through hosted API access only.
How do I call the Sonar API?
Point any OpenAI SDK at https://api.datallmlab.com/v1 and set model to "perplexity/sonar". One DataLLM Lab key routes this model and 300+ others; no code changes beyond the base URL and model string.
What are good alternatives to Sonar?
Close options by price and capability include Sonar Deep Research, Sonar Reasoning Pro, Sonar Pro — all callable with the same DataLLM Lab key.