Llama 3 3 70b Instruct

Provider: watsonx · watsonx/meta-llama/llama-3-3-70b-instruct

Pricing per million tokens

Component USD per 1M tokens
Input $0.71
Output $0.71

Monthly cost estimates

Assuming 30% prompt-cache hit rate where available. Adjust for your actual usage.

Small
1M in / 200k out
$0.85
per month
Medium
10M in / 2000k out
$8.52
per month
Large
100M in / 20000k out
$85.20
per month

Context

Input window
128,000 tokens
Max output
128,000 tokens

Capabilities

  • ⬜ Vision (image input)
  • ✅ Function / tool calling
  • ⬜ Prompt caching
  • ⬜ Web search
  • ⬜ JSON / response schema

Compare Llama 3 3 70b Instruct with similar models

Flan T5 Xl 3b
watsonx
$0.60 in / $0.60 out
Granite 13b Chat V2
watsonx
$0.60 in / $0.60 out
Granite 13b Instruct V2
watsonx
$0.60 in / $0.60 out
Granite Ttm 1024 96 R2
watsonx
$0.38 in / $0.38 out
Granite Ttm 1536 96 R2
watsonx
$0.38 in / $0.38 out
Granite Ttm 512 96 R2
watsonx
$0.38 in / $0.38 out

Pricing data sourced from LiteLLM and refreshed regularly. Last updated May 20, 2026. Always verify with the provider's official pricing page before making business decisions.