What is Anubis 70B V1.2?

Anubis 70B V1.2 is a model from Other, released on Jan 21, 2026. > A step up from the previous Anubis models. Better prose, better logic (for a 70b).

How much does Anubis 70B V1.2 cost?

On the Respan gateway, input starts at $0.72 per 1M tokens on Featherless, and output starts at $0.72 per 1M tokens on Featherless, after gateway discounts.

Which providers serve Anubis 70B V1.2 on Respan?

Anubis 70B V1.2 is served by Featherless.

What is Anubis 70B V1.2's context window?

Anubis 70B V1.2 accepts up to 33K tokens of context.

How do I use Anubis 70B V1.2 with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "anubis-70b-v1.2". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

How fast is Anubis 70B V1.2?

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 8.6 seconds on Featherless. Speed varies with request size and provider.