Llama 3 70B Instruct Reference API
Pricing & Specs

Meta · $0.88 input / $0.88 output per 1M tokens · 8.192K context window

No longer offered on OpenMark

$0.88
per 1M input tokens
$0.88
per 1M output tokens
8.192K
context window (tokens)

Llama 3 70B Instruct Reference API is no longer offered on OpenMark (deprecated or superseded upstream). Its specs are kept here for reference. If you're still running it in production, it's worth benchmarking current alternatives: newer models are often cheaper AND better on the same task.

Llama 3 70B Instruct Reference API API Pricing

TokensPrice
Input$0.88 / 1M tokens
Output$0.88 / 1M tokens

50% discount available for batch API requests. Batch API pricing is available via Together at 50%; cache pricing is not published.

What that means in practice

1x One typical task (1K input + 500 output tokens): $0.0013
1K 1,000 runs of that task: $1.32
💡 Real cost depends on how verbose the model is on YOUR prompts. Benchmark to measure actual tokens, not estimates.

Llama 3 70B Instruct Reference API Specs

SpecValue
Context window8.192K tokens
Input modalitiestext
Output modalitiestext
Latency (measured by OpenMark)~487ms median response
Reasoning modelNo
Tool / function callingNo
JSON modeYes
StreamingYes
Prompt cachingNo
Batch APIYes

Capabilities

chat streaming structured outputs

FAQ

How much does Llama 3 70B Instruct Reference API cost?

Llama 3 70B Instruct Reference API costs $0.88 per 1M input tokens and $0.88 per 1M output tokens.

What is Llama 3 70B Instruct Reference API's context window?

Llama 3 70B Instruct Reference API has a 8.192K-token context window.

Can I test Llama 3 70B Instruct Reference API on my own task?

Llama 3 70B Instruct Reference API is no longer offered on OpenMark, but you can benchmark its current alternatives from Meta and other providers on your own task, free tier available.

Still using Llama 3 70B Instruct Reference API?

It's been superseded. Benchmark its current alternatives on your actual
workload. You'll likely find something cheaper AND better. Free tier available.

Test Current Alternatives Free →

Get the monthly model change report

New models, API price changes, and retirements, straight from the registry that powers OpenMark. One email a month.