Question 1

What is Llama 3.1 8B Stheno V3.4?

Accepted Answer

Llama 3.1 8B Stheno V3.4 is a model from Other, released on Aug 19, 2024. Turn Distribution # 1 Turn is considered as 1 combined Human/GPT pair in a ShareGPT format. 4 Turns means 1 System Row + 8 Human/GPT rows in total.

Question 2

How much does Llama 3.1 8B Stheno V3.4 cost?

Accepted Answer

On the Respan gateway, input starts at $0.20 per 1M tokens on Featherless, and output starts at $0.32 per 1M tokens on Featherless, after gateway discounts.

Question 3

Which providers serve Llama 3.1 8B Stheno V3.4 on Respan?

Accepted Answer

Llama 3.1 8B Stheno V3.4 is served by Featherless.

Question 4

What is Llama 3.1 8B Stheno V3.4's context window?

Accepted Answer

Llama 3.1 8B Stheno V3.4 accepts up to 33K tokens of context.

Question 5

How do I use Llama 3.1 8B Stheno V3.4 with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "llama-3.1-8b-stheno-v3.4". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Llama 3.1 8B Stheno V3.4?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Featherless at 5 tokens per second, and the lowest response latency was 1.4 seconds on Featherless. Speed varies with request size and provider.

Llama 3.1 8B Stheno V3.4

Providers

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps

Certified where it counts.