Perplexity Sonar Deep Research
perplexity/sonar-deep-researchPar Perplexity · famille: sonar-deep-research · sorti 2025-02-01 · fin de connaissance: 2025-01
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Capacités
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding16
- Tool calling0/40
- Structured output0/20
- Reasoning10/10
- Context window (100K → 1M)2/20
- Provider availability4/10
Agents34
- Tool calling0/35
- Structured output0/25
- Reasoning15/15
- Output token limit15/15
- Provider availability4/10
JSON / structured output0
- Structured output / JSON mode0/50
- Tool calling0/20
- Temperature control0/10
- Price-friendly for high-volume0/20
Cost efficiency37
- Headline price (log-scaled)37/95
- Has prompt-cache pricing0/5
Long context45
- Context window (100K → 2M)35/90
- Has published price for full window10/10
Production-readiness78
- Number of independent providers20/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers8/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $14.00 $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $28.00 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $8.00 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $24.00 $0.02 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $28.80 $0.03 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Détail des tarifs
Tarif recommandé de perplexity · sonar-deep-research
Disponible chez 4 fournisseurs
| Fournisseur | ID modèle fournisseur | Entrée / 1M | Sortie / 1M | Contexte | Publié le |
|---|---|---|---|---|---|
| Perplexity perplexity | sonar-deep-research | $2.00 | $8.00 | 128K | 2025-02-01 |
| Kilo Gateway kilo | perplexity/sonar-deep-research | $2.00 | $8.00 | 128K | 2025-01-27 |
| SAP AI Core sap-ai-core | sonar-deep-research | $2.00 | $8.00 | 128K | 2025-02-01 |
| Helicone helicone | sonar-deep-research | $2.00 | $8.00 | 127K | 2025-01-27 |
Incohérences de données entre fournisseurs
- context_window varies: 127000, 128000
Les fournisseurs rapportent des valeurs différentes pour ce modèle. Les infos clés ci-dessus utilisent un fournisseur représentatif ; voir le tableau pour le détail par fournisseur.
Frequently asked questions
How much does Perplexity Sonar Deep Research cost?
Perplexity Sonar Deep Research costs $2.00 per 1M input tokens and $8.00 per 1M output tokens, sourced from perplexity. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Perplexity Sonar Deep Research?
Perplexity Sonar Deep Research has a context window of 128K tokens, with a max output of 33K tokens per reply. This is the total combined size of prompt + completion.
Does Perplexity Sonar Deep Research support tool calling?
No. Perplexity Sonar Deep Research does not support tool calling (function calling). If your workflow requires it, look at the /capabilities/tool-calling list for alternatives.
Does Perplexity Sonar Deep Research support structured output / JSON mode?
Support for structured output / JSON-schema-constrained decoding is not reported for Perplexity Sonar Deep Research in our data source. Verify with Perplexity's official documentation before relying on it in production.
Can Perplexity Sonar Deep Research accept image input?
No. Perplexity Sonar Deep Research only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is Perplexity Sonar Deep Research open-weight?
No. Perplexity Sonar Deep Research is a proprietary model — only Perplexity (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.
What are the best alternatives to Perplexity Sonar Deep Research?
If Perplexity Sonar Deep Research doesn't fit, consider Sonar, Sonar Pro, Sonar Reasoning Pro. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More Perplexity models
- Sonar$1.00 in / $1.00 out
- Sonar Pro$3.00 in / $15.00 out
- Sonar Reasoning Pro$2.00 in / $8.00 out
Dernière mise à jour :
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.