GeekRadar / The comparison desk

COMPARE.

AI models

Unspecified

ovhcloud/Meta-Llama-3_1-70B-Instruct

AI model

API mode: Chat^*
Maximum output: 131,000 tokens^*

No matched benchmark results are available for this entry yet.

Run it locally

Inference · memory estimate

ovhcloud/Meta-Llama-3_1-70B-Instruct

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Maximum input: 131,000 tokens^*
Maximum output: 131,000 tokens^*
Tool calling: No^*
Structured output: No^*
API mode: Chat^*
Tool choice: No^*

System configuration

Detailed specifications

Specifications · 10 fields

input cost per token

6.7e-7^*

Scope and conditions

native_context

provider: ovhcloud^*
mode: chat^*
full_native_model_id: ovhcloud/Meta-Llama-3_1-70B-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

ovhcloud^*

Scope and conditions

native_context

provider: ovhcloud^*
mode: chat^*
full_native_model_id: ovhcloud/Meta-Llama-3_1-70B-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

131,000^*

Scope and conditions

native_context

provider: ovhcloud^*
mode: chat^*
full_native_model_id: ovhcloud/Meta-Llama-3_1-70B-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

131,000^*

Scope and conditions

native_context

provider: ovhcloud^*
mode: chat^*
full_native_model_id: ovhcloud/Meta-Llama-3_1-70B-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

131,000^*

Scope and conditions

native_context

provider: ovhcloud^*
mode: chat^*
full_native_model_id: ovhcloud/Meta-Llama-3_1-70B-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: ovhcloud^*
mode: chat^*
full_native_model_id: ovhcloud/Meta-Llama-3_1-70B-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

6.7e-7^*

Scope and conditions

native_context

provider: ovhcloud^*
mode: chat^*
full_native_model_id: ovhcloud/Meta-Llama-3_1-70B-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 function calling

No^*

Scope and conditions

native_context

provider: ovhcloud^*
mode: chat^*
full_native_model_id: ovhcloud/Meta-Llama-3_1-70B-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 response schema

No^*

Scope and conditions

native_context

provider: ovhcloud^*
mode: chat^*
full_native_model_id: ovhcloud/Meta-Llama-3_1-70B-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

No^*

Scope and conditions

native_context

provider: ovhcloud^*
mode: chat^*
full_native_model_id: ovhcloud/Meta-Llama-3_1-70B-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