Meta Llama 3 70B Instruct

MetaReleasedApr 18, 2024KnowledgeDec 2023
Context
131K
Max output
131K
Serving providers
3
Cheapest input
$0.12 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand

Input pricing runs from $0.12 to $1.10 per 1M tokens across 3 providers, so the dearest route costs 817% more than the cheapest for the same model.

Serving providerInput /1MOutput /1MEndpoints
HyperbolicCheapest$0.12$0.301
ComponentUnitStandardBatchCached
Text input/1M tok$0.1200
Text output/1M tok$0.3000
Anyscale$1.00$1.001
Azure$1.10$0.371

Price history

input + output $/1M since we started tracking
Input Output
Input down 88% since first tracked
$0.000$0.500$1.00May 23Jun 14Jul 21Jun 22$0.300$0.120

Cost calculator

estimate your monthly spend on this model
$48
estimated / month

Model IDs

copy the exact identifier for your platform
hyperbolic/meta-llama/Meta-Llama-3-70B-Instructanyscale/meta-llama/Meta-Llama-3-70B-Instructazure_ai/Meta-Llama-3-70B-Instruct

Frequently asked questions

Meta Llama 3 70B Instruct pricing, context and availability

How much does Meta Llama 3 70B Instruct cost?

Meta Llama 3 70B Instruct costs $0.12 per 1M input tokens and $0.30 per 1M output tokens at its cheapest provider via Hyperbolic. Across 3 serving providers, input prices range from $0.12 to $1.10 per 1M tokens.

What is the context window of Meta Llama 3 70B Instruct?

Meta Llama 3 70B Instruct accepts up to 131K tokens of context and can return up to 131K output tokens.

Which providers serve Meta Llama 3 70B Instruct?

Meta Llama 3 70B Instruct is available from 3 serving providers, each with its own pricing and model ID. Hyperbolic is currently the cheapest.

What can Meta Llama 3 70B Instruct do?

Meta Llama 3 70B Instruct supports tool use.

Other Meta models

compare pricing across the Meta lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI