Skip to content
OpenKey

MythoMax 13B

GrypheReleased Jul 2, 2023

One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge

Try in playground
Context window
4K tokens
Max output
4K tokens
Input
text
Output
text
Tokenizer
Llama2
Knowledge cutoff
Jun 30, 2023
Released
Jul 2, 2023

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.060$0.0018$0.062
Output$0.060$0.0018$0.062

Supported parameters

  • frequency_penalty
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • top_a
  • top_k
  • top_logprobs
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model gryphe/mythomax-l2-13b.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gryphe/mythomax-l2-13b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="gryphe/mythomax-l2-13b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "gryphe/mythomax-l2-13b",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does MythoMax 13B cost via API?
Through OpenKey, MythoMax 13B costs $0.062 per 1M input tokens and $0.062 per 1M output tokens. That is the provider price ($0.060 / $0.060) plus a flat 3% fee — nothing else.
What is MythoMax 13B's context window?
MythoMax 13B accepts up to 4K tokens of context and returns up to 4K tokens per request.
Is MythoMax 13B OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "gryphe/mythomax-l2-13b" using any OpenAI SDK — only the base URL and API key change.
What inputs does MythoMax 13B support?
MythoMax 13B accepts text input and produces text output. Its knowledge cutoff is Jun 30, 2023.