impulse

Mythomax L2 13B

Open weights

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

API id mythomax-l2-13bReleased 2 Jul 2023 (Jul 2023)
Input / 1M
$0.09
at Novita AI
Output / 1M
$0.09
at Novita AI
Context window
4K
tokens
Max output
3K
tokens per reply
Hosts
3
3 listings
Released
Jul 2023
2 Jul 2023

Pricing

List prices at Novita AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.09$0.09

What it costs a month

At Novita AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$33.75
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$46.44
  • Coding agent1,000 requests a day, 40K in / 2K out$113
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$238
Use your own numbers

Where to run it

3 hosts serve Mythomax L2 13B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Novita AIInference
mythomax-l2-13b
$0.09 / $0.09
Fireworks AIInference
mythomax-l2-13b
$0.20 / $0.20
+122% vs headline
DeepInfraInference
MythoMax-L2-13b
$0.40 / $0.40
+344% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: other

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Novita AI.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Nemotron 3 Nano 30B A3B
    NVIDIA · on DeepInfra
    $0.05 / $0.20
    Has every key capability
    3% less
  • Granite 4.2 8B
    IBM · on W&B Inference
    $0.06 / $0.15
    Has every key capability
    8% less
  • Phi 4
    Microsoft · on DeepInfra
    $0.07 / $0.14
    Has every key capability
    3% less
  • Qwen Turbo
    Alibaba Qwen · on Alibaba DashScope
    $0.05 / $0.20
    Has every key capability
    3% less

Call it

Using Novita AI's API.

Python
from litellm import completion

response = completion(
    model="novita/mythomax-l2-13b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Mythomax L2 13B cost?

On Novita AI, Mythomax L2 13B costs $0.09 per million input tokens and $0.09 per million output tokens.

Which APIs offer Mythomax L2 13B?

Mythomax L2 13B runs on 3 APIs: Novita AI, Fireworks AI and DeepInfra.

What is Mythomax L2 13B's context window?

4K tokens, with up to 3K tokens in one reply.

Is Mythomax L2 13B being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Mythomax L2 13B?

Models that cost less and keep most of what it can do: Nemotron 3 Nano 30B A3B on DeepInfra (3% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Mythomax L2 13B released?

Independent released it on 2 Jul 2023.

What is Mythomax L2 13B's API model id?

Use mythomax-l2-13b with Novita AI. Other hosts use their own ids: MythoMax-L2-13b on DeepInfra.

Sources

Raw catalog entry for mythomax-l2-13b on Novita AI
{
  "litellm_provider": "novita",
  "mode": "chat",
  "input_cost_per_token": 9e-8,
  "output_cost_per_token": 9e-8,
  "max_input_tokens": 4096,
  "max_output_tokens": 3200,
  "supports_system_messages": true
}