Question 1

What is L3 8B Stheno V3.2?

Accepted Answer

L3 8B Stheno V3.2 is a model from Other, released on Jun 5, 2024. I have done a test run with multiple variations of the models, merged back to its base at various weights, different training runs too, and this Sixth iteration is the one I like most.

Question 2

How much does L3 8B Stheno V3.2 cost?

Accepted Answer

On the Respan gateway, input starts at $0.05 per 1M tokens on Novita, and output starts at $0.05 per 1M tokens on Novita, after gateway discounts. Averaged across 2 providers, it costs $0.21 per 1M input tokens and $0.21 per 1M output tokens.

Question 3

Which providers serve L3 8B Stheno V3.2 on Respan?

Accepted Answer

2 providers serve L3 8B Stheno V3.2: Novita and Featherless.

Question 4

What is L3 8B Stheno V3.2's context window?

Accepted Answer

L3 8B Stheno V3.2 accepts up to 8K tokens of context on its largest provider route.

Question 5

How do I use L3 8B Stheno V3.2 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 "l3-8b-stheno-v3.2". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is L3 8B Stheno V3.2?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Novita at 34 tokens per second, and the lowest response latency was 0.8 seconds on Novita. Speed varies with request size and provider.

Provider	Context	Input	Output	Capabilities
NovitaSave 10%`novita/Sao10K/L3-8B-Stheno-v3.2`	8K	$0.05/M	$0.05/M	—
Featherless`featherless_ai/Sao10K/L3-8B-Stheno-v3.2`	8K	$0.37/M	$0.38/M

L3 8B Stheno V3.2

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps

L3 8B Stheno V3.2 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.