---
id: "gryphe/mythomax-l2-13b"
also: ["gryphe/mythomax-l2-13b", "Gryphe/MythoMax-L2-13b", "requesty/gryphe/mythomax-l2-13b"]
cheapest_list_usd_per_m: "0.06 in, 0.06 out, at nextbit/int4 on openrouter"
cheapest_effective_usd_per_m: "0.0594 in, 0.0573 out, at nextbit/int4 on openrouter"
context: 8192
max_output: 3686
input: ["text"]
output: ["text"]
released: "2023-07-02"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tools", "top_a", "top_k", "top_logprobs", "top_p"]
endpoints: 5
gateways: "openrouter (4), requesty (1)"
no_training: 5
trains: 0
retains_prompts: 0
---
# MythoMax 13B

The idea behind this merge is that each layer is composed of several tensors, which are in turn responsible for specific functions. Using MythoLogic-L2's robust understanding as its input and Huginn's extensive writing capability as its output seems to have resulted in a model that exceeds at both, confirming my theory. (More details to be released at a later time).