LLMversus
Meta

Llama 3.3 70B

Complete specs, pricing, and benchmark data for Llama 3.3 70B by Meta. Last verified 2026-04-20.

JSON ModeFunctionsStreaming
Pricing

Input / 1M tokens

$0.120

Output / 1M tokens

$0.380

Context & Output

Context Window

128K

Max Output

4,096

TTFT

150ms

Speed

100 tok/s

Benchmarks

Arena ELO

1220

Coding ELO

1180

Reasoning ELO

1220

HumanEval

88

MMLU

86.2

MATH

96

GPQA

40

Try Llama 3.3 70B API

Start building with Llama 3.3 70B

Get API Access→

Price History (Input $/M tokens)

Strengths
  • +Excellent code generation
  • +Large context window
  • +Fast inference
Limitations
  • -No vision capabilities
  • -Weaker on reasoning tasks

Best For

CodingGeneral PurposeCost Effective

Compare Llama 3.3 70B with...

vs Claude Opus 4vs Gemini 2.5 Provs o3vs DeepSeek R1vs o1vs Qwen 3 235B MoEvs Gemini Experimental 1206vs GPT-4.5vs DeepSeek R1 (Groq)vs Llama 4 Maverickvs DeepSeek R1 (Together)vs Grok 3
Official Pricing Page →
Your ad here