Skip to content
LLMs
MythoMax 13B logo

MythoMax 13B

by MythoMax 13B

MythoMax 13B is a large language model from MythoMax 13B. It costs $0.060 per million input tokens and $0.060 per million output tokens. Its context window is 8K tokens.

Structured outputOpen weights
Input / 1M tokens
$0.060
Output / 1M tokens
$0.060
Cached input / 1M
-

Not supported

Context window
8K

tokens

Who serves it cheapest

4 hosts serve MythoMax 13B. Same weights, same API - the price difference is pure margin and routing.

Providers serving MythoMax 13B, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
NextBitCheapestint4$0.060$0.0604K-99.9%
Parasailfp16$0.080$0.1104K-99.6%
DeepInfrafp16$0.400$0.4004K-100.0%
Mancer 2fp8$0.350$0.6008K-99.9%

The spread between NextBit and Mancer 2 is 6.9× for identical weights. Quantization and context limits differ, so check both columns before switching.

About MythoMax 13B

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

Specifications

MythoMax 13B specifications
Model IDgryphe/mythomax-l2-13b
ProviderMythoMax 13B
Context window8K tokens
Max output4K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff2023-06-30
Open weightsYes - Gryphe/MythoMax-L2-13b
ReleasedJuly 2, 2023

Cheaper alternatives

Models that cost less than MythoMax 13B while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does MythoMax 13B cost?

$0.060 per million input tokens and $0.060 per million output tokens.

What is the context window of MythoMax 13B?

8K tokens, with up to 4K tokens of output per request.

Which provider serves MythoMax 13B cheapest?

NextBit at $0.060 per million input tokens - 6.9× cheaper than Mancer 2, the most expensive of the 4 hosts serving it.