GeekRadar / The comparison desk

COMPARE.

AI models

Unspecified

azure_ai/Phi-3-medium-128k-instruct

AI model

API mode: Chat^*
Maximum output: 4,096 tokens^*

No matched benchmark results are available for this entry yet.

Run it locally

Inference · memory estimate

azure_ai/Phi-3-medium-128k-instruct

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Maximum input: 128,000 tokens^*
Maximum output: 4,096 tokens^*
API mode: Chat^*
Image input: No^*
Tool choice: Yes^*

System configuration

Detailed specifications

Specifications · 10 fields

deprecation date

2025-08-30^*

Scope and conditions

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/Phi-3-medium-128k-instruct^*
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

1.7e-7^*

Scope and conditions

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/Phi-3-medium-128k-instruct^*
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

azure_ai^*

Scope and conditions

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/Phi-3-medium-128k-instruct^*
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: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/Phi-3-medium-128k-instruct^*
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

4,096^*

Scope and conditions

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/Phi-3-medium-128k-instruct^*
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

4,096^*

Scope and conditions

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/Phi-3-medium-128k-instruct^*
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: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/Phi-3-medium-128k-instruct^*
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

6.8e-7^*

Scope and conditions

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/Phi-3-medium-128k-instruct^*
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 tool choice

Yes^*

Scope and conditions

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/Phi-3-medium-128k-instruct^*
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

No^*

Scope and conditions

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/Phi-3-medium-128k-instruct^*
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.^*

* Provisional data