Llama 3 8B Instruct Lite API
Pricing & Specs
Meta · $0.14 input / $0.14 output per 1M tokens · 8.192K context window
No longer offered on OpenMark
Llama 3 8B Instruct Lite API is no longer offered on OpenMark (deprecated or superseded upstream).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 8B Instruct Lite API API Pricing
| Tokens | Price |
|---|---|
| Input | $0.14 / 1M tokens |
| Output | $0.14 / 1M tokens |
Batch API pricing is available via Together at 50%; cache pricing is not published.
What that means in practice
Llama 3 8B Instruct Lite API Specs
| Spec | Value |
|---|---|
| Context window | 8.192K tokens |
| Input modalities | text |
| Output modalities | text |
| Latency (measured by OpenMark) | ~496ms median response |
| Reasoning model | No |
| Tool / function calling | No |
| JSON mode | Yes |
| Streaming | Yes |
| Prompt caching | No |
| Batch API | Yes |
Capabilities
Notes
Deprecated/removed from Together AI.
FAQ
How much does Llama 3 8B Instruct Lite API cost?
Llama 3 8B Instruct Lite API costs $0.14 per 1M input tokens and $0.14 per 1M output tokens.
What is Llama 3 8B Instruct Lite API's context window?
Llama 3 8B Instruct Lite API has a 8.192K-token context window.
Can I test Llama 3 8B Instruct Lite API on my own task?
Llama 3 8B Instruct Lite 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 8B Instruct Lite API?
It's been superseded. Benchmark its current alternatives on your actual
workload. You'll likely find something cheaper AND better. Free tier available.