No matched benchmark results are available for this entry yet.
Run it locally
Inference · memory estimate
gemini/gemini-3.1-flash-live-preview
Not enough verified architecture information for a reliable VRAM estimate.
Capabilities
Maximum input
131,072 tokens*
Maximum output
65,536 tokens*
Reasoning
Yes*
Tool calling
Yes*
Structured output
No*
API mode
Realtime API*
Image input
Yes*
Audio input
Yes*
Audio output
Yes*
Web search
Yes*
Input modalities
text*
image*
audio*
video*
Output modalities
text*
audio*
System configuration
Detailed specifications
Specifications · 27 fields
deprecation date
2026-11-17*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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.*
gemini audio only live
Yes*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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 audio token
3.0e-6*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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 image token
1.0e-6*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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 second
8.33333333333e-5*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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
7.5e-7*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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 video per second
3.3333333333333335e-5*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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 video token
1.0e-6*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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
gemini*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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
131,072*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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 output tokens
65,536*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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
65,536*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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
realtime*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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 audio token
1.2e-5*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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
4.5e-6*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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.*
rpm
10*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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.*
supported endpoints
/v1/realtime*
Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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.*
supported modalities
text*
image*
audio*
video*
Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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.*
supported output modalities
text*
audio*
Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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 audio input
Yes*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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 audio output
Yes*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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 function calling
Yes*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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 response schema
No*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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 vision
Yes*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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.*
tpm
250,000*Scope and conditions
native_context
provider
gemini*
mode
realtime*
full_native_model_id
gemini/gemini-3.1-flash-live-preview*
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.*