Marin 8B Instruct
Pricing & Specs
Marin · $0.18 input / $0.18 output per 1M tokens · 4.096K context window
No longer offered on OpenMark
Marin 8B Instruct is no longer offered on OpenMark (deprecated or superseded upstream).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.
Marin 8B Instruct API Pricing
| Tokens | Price |
|---|---|
| Input | $0.18 / 1M tokens |
| Output | $0.18 / 1M tokens |
Batch API pricing is available via Together at 50%; cache pricing is not published.
What that means in practice
Marin 8B Instruct Specs
| Spec | Value |
|---|---|
| Context window | 4.096K tokens |
| Input modalities | text |
| Output modalities | text |
| Latency (measured by OpenMark) | ~210ms median response |
| Reasoning model | No |
| Tool / function calling | No |
| JSON mode | Yes |
| Streaming | Yes |
| Prompt caching | No |
| Batch API | Yes |
Capabilities
FAQ
How much does Marin 8B Instruct cost?
Marin 8B Instruct costs $0.18 per 1M input tokens and $0.18 per 1M output tokens.
What is Marin 8B Instruct's context window?
Marin 8B Instruct has a 4.096K-token context window.
Can I test Marin 8B Instruct on my own task?
Marin 8B Instruct is no longer offered on OpenMark, but you can benchmark its current alternatives from Marin and other providers on your own task — free tier available.
Still using Marin 8B Instruct?
It's been superseded. Benchmark its current alternatives on your actual
workload — you'll likely find something cheaper AND better. Free tier available.