llama-3.1-8b

8B
Context
128K
Input price
$0.02/1M tokens
Output price
$0.05/1M tokens

Capabilities

Reasoning & Interaction
Tool Calling
Infrastructure
Streaming

Details

Familyllama-3.1
License—
Status—
Typechat
Input modalitiestext
Output modalitiestext
Open weight—
Parameters8B
Architecture—
Context window128K tokens
Max input—
Max output—
Reasoning tokens—
Knowledge cutoff—
Release date—
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.02
Output
$0.05
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: llama-3.1

ModelContextMax outPricing
llama-3.1-8b128K—$0.02$0.05
llama-3.1-70b128K—$0.72$0.72

API

GET/v1/models/vercel/meta/llama-3.1-8b

llama-3.1-8b

Changes · 6 entries
meta/llama-3.1-8bupdateca7a400Nov 2, 2026, 03:02 AM
context_window131100→128000
pricinginput$0.1→$0.02output$0.1→$0.05
meta/llama-3.1-8bupdatea6d63d7Sep 15, 2026, 06:39 AM
context_window131100→128000
meta/llama-3.1-8bupdated657a45Jun 3, 2026, 03:19 AM
pricinginput$0.1→$0.02output$0.1→$0.05
meta/llama-3.1-8bupdateb301ebeMar 23, 2026, 11:47 PM
modalitiesinput["text"]output["text"]
meta/llama-3.1-8bupdate2b100acMar 23, 2026, 05:30 AM
model_typechat
parameters8
tools["function_calling"]
meta/llama-3.1-8bcreate7f5c66fMar 21, 2026, 05:16 AM