MythoMax 13B
Gryphe · released Aug 10, 2023 · Gryphe/MythoMax-L2-13b
- Type
- Open weightsCustom licence
- Params
- 13B
- Context
- 8K
about 6K words of context · download allowed, licence restricts use
Our take
Written Sep 2, 2026MythoMax 13B is a 13-billion-parameter text model released in 2023 with a restricted custom licence. It is a budget option for basic text generation, with very low token rates available from some hosts and one host offering markedly higher throughput than the rest.
Pick this for basic short-context text tasks where cost matters most — some hosts charge a fraction of what others do for the same model. Use the highest-throughput host if you are processing high volumes. Skip it if you need verified quality scores, a permissive licence, or context beyond 8,192 tokens.
The case for it
- Very low token pricing from multiple providers — the cheapest rate in its own offer set is several times below its most expensive.
- One host delivers more than double the throughput of its other measured offers.
The case against it
- No benchmark scores in our data — chat, reasoning, coding and knowledge are all unverified.
- Custom restricted licence; terms for commercial use, redistribution and modification are unspecified.
- 8,192-token request limit with sharp price variation across hosts.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 11.5 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 19.5 GB spare means a 10% error in the size would not change the answer.
Apple M1 (8-core GPU) · 16 GB
Borderline fit on an estimated size. It leaves 0.7 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 2 hours ago — each listing carries its own date.
The only listing at 8K of context — the other 4 in the table below are not like-for-like. One cheaper row there is outside that comparison: a different context length.
- per 1M tokens
- $0.080 in / $0.11 out
- Context served
- 8K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Novita AIDirect | $0.090 / $0.090checked 2 hours ago | 4K | not measured | Unknown | Unknown | Unknown |
| OpenRouterOpenRouter's own listing | $0.080 / $0.11checked 2 hours ago | 8K | not measured | Unknown | Unknown | Unknown |
| Parasailfp16Through OpenRouter | $0.080 / $0.11checked 2 hours ago | 4K4K max reply | 90 tok/s | No | No | Confirmed |
| DeepInfrafp16Direct and through OpenRouter | $0.40 / $0.40checked 2 hours ago | 4K4K max reply through OpenRouter | 46 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Mancer 2fp8Through OpenRouter | $0.35 / $0.60checked 2 hours ago | 8K7K max reply | 62 tok/s | No | No | Confirmed |
Novita AI
DeepInfraAcross the 5 listings we hold: 3 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 2 do not say. 3 appear in the zero-retention registry we check (1 of them only through OpenRouter); the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| Novita AIDirect | |||
| OpenRouterOpenRouter's own listing | ✗ | ✓ | ✓ |
| Parasailfp16Through OpenRouter | ✗ | ✗ | ✓ |
| DeepInfrafp16Direct and through OpenRouter | ✗ | ✗ | ✗ |
| Mancer 2fp8Through OpenRouter | ✗ | ✓ | ✓ |
Tool calling: 0 of 5 listings say yes, 4 say no, 1 publishes no parameter list. JSON output: 2 of 5 listings say yes, 2 say no, 1 publishes no parameter list. Strict schema: 3 of 5 listings say yes, 1 says no, 1 publishes no parameter list.
When we formed this view
Recent changes
What moved
input −13% ($0.40 → $0.35 per 1M tokens)What moved
input −11% ($0.45 → $0.40 per 1M tokens), output −8% ($0.65 → $0.60 per 1M tokens)What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- 1 of 5 listings publishes no parameter list, so what its API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 5 listings do not say whether they train on prompts, and 1 answers only through OpenRouter, not for its own listing.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- Gryphe/MythoMax-L2-13b
- Architecture
- Dense
- Takes in, gives back
- Text in, text out
- Catalogue slug
- gryphe-mythomax-13b