Question 1

What is L3.3 70B Magnum Diamond?

Accepted Answer

L3.3 70B Magnum Diamond is a model from Other, released on Jun 4, 2025. This model is finetuned from meta-llama/Llama-3.3-70B-Instruct as an rsLoRA adapter. It uses the same data mix as Doctor-Shotgun/L3.3-70B-Magnum-v5-SFT-Alpha, however with pre-tokenization and modifications to the custom loss masking. It's for all intents and purposes a version update to the former model. This model should perform competently with or without prepending character names, and with or without prefill.

Question 2

How much does L3.3 70B Magnum Diamond cost?

Accepted Answer

On the Respan gateway, input starts at $2.60 per 1M tokens on Featherless, and output starts at $3.00 per 1M tokens on Featherless, after gateway discounts.

Question 3

Which providers serve L3.3 70B Magnum Diamond on Respan?

Accepted Answer

L3.3 70B Magnum Diamond is served by Featherless.

Question 4

What is L3.3 70B Magnum Diamond's context window?

Accepted Answer

L3.3 70B Magnum Diamond accepts up to 33K tokens of context.

Question 5

How do I use L3.3 70B Magnum Diamond 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 "l3.3-70b-magnum-diamond". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is L3.3 70B Magnum Diamond?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Featherless at 3 tokens per second, and the lowest response latency was 6.8 seconds on Featherless. Speed varies with request size and provider.

L3.3 70B Magnum Diamond

Providers

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps

Certified where it counts.