losclouds

AI Models / Compare

Llama 3.3 70B Versatile on Groq

Production Groq text model for high-speed general chat and tool use.

Creator
Groq
Lifecycle
Active
Context
131.1K
Max output
32.8K
Released
Jan 6, 2025
Status
up
Input
$0.59 / 1M tokens
Output
$0.79 / 1M tokens
Cached read
/ 1M tokens
Cached write
/ 1M tokens
Batch discount
%
Source
Llama 3.3 70B Versatile on Groq pricing
Verified
Apr 2, 2026 (High)

Capabilities

Modalities
texttext
Capabilities
reasoningbatchSupportpromptCachingfunctionCallingstructuredOutputs
Strengths
Production-ready, Low-latency Groq hosting
Tradeoffs
Not a frontier reasoning model
Official Links

Benchmark Coverage

BenchmarkVersionScoreDateSourceNotes

Release History

ReleaseAliasLifecycleRelease DateDeprecationShutdownSummary
Llama 3.3 70B Versatile on Groqgroq-llama-3-3-70b-versatileActiveJan 6, 2025Current published model family snapshot.

Host Coverage

HostTypeContextPricing NoteDifferences
Groq APIfirst-party131.1KReference production Groq pricing.Production model tier
Migration Guidance

Default hosted Groq text tier when GPT-OSS depth is unnecessary.

Replacement models: groq-gpt-oss-120b

Change Events
DateTypeTitleDescriptionSource
Jan 6, 2025family_addedLlama 3.3 70B Versatile on Groq publishedInitial public model family launch.Llama 3.3 70B Versatile on Groq release notes

Other models from Groq

GPT-OSS 120B on Groq, GPT-OSS 20B on Groq, Groq Compound, Llama 3.1 8B Instant on Groq, Llama 4 Scout on Groq, Qwen3 32B on Groq