losclouds

AI Models / Compare

Llama 3.1 8B

Cheapest Llama with 128K context; ideal for high-volume simple tasks.

Creator
Meta AI
Lifecycle
Active
Context
128.0K
Max output
8.2K
Released
Jul 23, 2024
Status
unknown
Input
$0.05 / 1M tokens
Output
$0.08 / 1M tokens
Cached read
/ 1M tokens
Cached write
/ 1M tokens
Batch discount
%
Source
Llama 3.1 8B pricing
Verified
Apr 5, 2026 (High)

Capabilities

Modalities
texttext
Capabilities
batchSupportpromptCachingfunctionCallingstructuredOutputs
Strengths
Very cheap, Fast throughput, Easy to self-host
Tradeoffs
Lower quality than 70B tiers
Official Links

Benchmark Coverage

BenchmarkVersionScoreDateSourceNotes

Release History

ReleaseAliasLifecycleRelease DateDeprecationShutdownSummary
Llama 3.1 8Bllama-3-1-8bActiveJul 23, 2024Current published model family snapshot.

Host Coverage

HostTypeContextPricing NoteDifferences
Groqcloud128.0K$0.05/$0.08 per MTok.Fastest inference
Migration Guidance

Use for cost-down scenarios from Llama 3.x 70B.

Replacement models: llama-3-3-70b

Change Events
DateTypeTitleDescriptionSource
Jul 23, 2024family_addedLlama 3.1 8B publishedInitial public model family launch.Llama 3.1 8B release notes

Other models from Meta AI

Llama 3.1 405B, Llama 3.1 70B, Llama 3.2 11B Vision, Llama 3.2 90B Vision, Llama 3.3 70B, Llama 4 Maverick, Llama 4 Scout