Sonar Deep Research
Closed weights. No supported local deployment or GPU requirement is published.
GeekRadar / The comparison desk
COMPARE.
AI modelsSonar Deep Research
AI model Released
- API mode
- Chat*
- Context window
- 128,000 tokens
- Maximum output
- 32,768 tokens
- Open weights
- No
No matched benchmark results are available for this entry yet.
Run it locally
API cost
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
Sonar Deep Research
Capabilities
- Context window
- 128,000 tokens
- Maximum input
- 128,000 tokens*
- Maximum output
- 32,768 tokens
- Reasoning
- Yes
- Tool calling
- No
- Open weights
- No
- Knowledge cutoff
- 2025-01
- API mode
- Chat*
- Web search
- Yes*
Input modalities
- text
Output modalities
- text
System configuration
Detailed specifications
Specifications · 11 fields
- citation cost per token
- 2.0e-6*
Scope and conditions
- native_context
- provider
- perplexity*
- mode
- chat*
- full_native_model_id
- perplexity/sonar-deep-research*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- input cost per token
- 2.0e-6*
Scope and conditions
- native_context
- provider
- perplexity*
- mode
- chat*
- full_native_model_id
- perplexity/sonar-deep-research*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- litellm provider
- perplexity*
Scope and conditions
- native_context
- provider
- perplexity*
- mode
- chat*
- full_native_model_id
- perplexity/sonar-deep-research*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- max input tokens
- 128,000*
Scope and conditions
- native_context
- provider
- perplexity*
- mode
- chat*
- full_native_model_id
- perplexity/sonar-deep-research*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- max tokens
- 128,000*
Scope and conditions
- native_context
- provider
- perplexity*
- mode
- chat*
- full_native_model_id
- perplexity/sonar-deep-research*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- mode
- chat*
Scope and conditions
- native_context
- provider
- perplexity*
- mode
- chat*
- full_native_model_id
- perplexity/sonar-deep-research*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per reasoning token
- 3.0e-6*
Scope and conditions
- native_context
- provider
- perplexity*
- mode
- chat*
- full_native_model_id
- perplexity/sonar-deep-research*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per token
- 8.0e-6*
Scope and conditions
- native_context
- provider
- perplexity*
- mode
- chat*
- full_native_model_id
- perplexity/sonar-deep-research*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- search context cost per query
- search_context_size_high
- 0.005*
- search_context_size_low
- 0.005*
- search_context_size_medium
- 0.005*
Scope and conditions
- native_context
- provider
- perplexity*
- mode
- chat*
- full_native_model_id
- perplexity/sonar-deep-research*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports reasoning
- Yes*
Scope and conditions
- native_context
- provider
- perplexity*
- mode
- chat*
- full_native_model_id
- perplexity/sonar-deep-research*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports web search
- Yes*
Scope and conditions
- native_context
- provider
- perplexity*
- mode
- chat*
- full_native_model_id
- perplexity/sonar-deep-research*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
0 selected Compare 0
* Provisional data