losclouds
Model · Meta AI

Llama 3.1 70B

Workhorse open-weight 70B — good quality/cost ratio, widely hosted.

Pricing

Model Overview

Tracked token-pricing fields for this model family. Empty pricing fields stay hidden until the source publishes them.

Model pricing
Price fieldValue
Input$0.59 / 1M tokens
Output$0.79 / 1M tokens
SourceLlama 3.1 70B pricing
VerifiedApr 5, 2026 (High)

Surface

Capabilities

Input and output modalities, enabled feature flags, strengths, and tradeoffs.

Model capabilities
AttributeValues
Modalities
text
to
text
Capabilities
batchSupportpromptCachingfunctionCallingstructuredOutputs
StrengthsWidely hosted, Strong open 70B
TradeoffsText-only, 8K output

References

Official Links

Canonical launch, documentation, pricing, and release-note URLs.

Coverage

Benchmark Coverage

Reported benchmark families, versions, scores, sources, and notes.

Benchmark coverage
BenchmarkVersionScoreDateSourceNotes
MMLU202486 %Jul 1, 2024MetaVendor-reported

Lifecycle

Release History

Lifecycle transitions and release timeline for this model family.

Release history
ReleaseAliasLifecycleRelease DateDeprecationShutdownSummary
Llama 3.1 70Bllama-3-1-70bActiveJul 23, 2024Current published model family snapshot.

Surfaces

Host Coverage

Provider-specific hosting, context, pricing notes, feature differences, and provider-status context.

Host coverage
HostTypeContextPricing NoteDifferences
Groqcloud128.0K$0.59/$0.79 per MTok.Fast inference
DeepInfracloud128.0K$0.23/$0.23 per MTok.

Migration

Migration Guidance

Documented migration summary, successor families, and known breaking changes.

Migration guidance
TopicDetails
SummaryConsider Llama 3.3 70B for better quality at similar cost.
Replacement modelsllama-3-3-70b

Timeline

Change Events

Cataloged model-family updates and source references.

Change events
DateTypeTitleDescriptionSource
Jul 23, 2024family_addedLlama 3.1 70B publishedInitial public model family launch.Llama 3.1 70B release notes

From Meta AI

Other models from Meta AI