Models/llama-3-70b

llama-3-70bActive · Inference

Replicate · Released · Llama Community License

Replicate chat model.

Context

8K

Max output

8K

Input

$0.65

Output

$2.75

Cached in

-

Latency

-

Capabilities

Core

Streaming

Function calling

JSON mode

Structured outputs

Multimodal

Vision

Image input

Audio

Image generation

Video

Advanced

Reasoning

Tool calling

MCP

Prompt caching

Batch API

Embeddings

Details

ProviderReplicate

Released

LicenseLlama Community License

InputText

OutputText

Throughput-

Availability-

Related models

gpt-5Replicate0$1.25 gpt-5-miniReplicate0$0.25 gpt-5-nanoReplicate0$0.05