Out of the box LLM models
llm.generate_text
node will default to our LLM proxy, which bills usage directly from the Credits included in your subscription to the MainlyAI Platform. This also means that you don’t have to manually set up API keys or other credentials. To use your own models, simply connect them to the llm
reciever.
Model | Context | Input Cost / 1M | Output Cost / 1M |
---|---|---|---|
o1 | 128k | ¤ 1410.26 | ¤ 5641.03 |
o1-mini | 128k | ¤ 282.05 | ¤ 1128.21 |
gpt-4o | 128k | ¤ 235.04 | ¤ 940.17 |
gpt-4o-mini | 128k | ¤ 14.10 | ¤ 56.41 |
Model | Context | Input Cost / 1M | Output Cost / 1M |
---|---|---|---|
ministral-3b-latest | 128k | ¤ 3.76 | ¤ 3.76 |
ministral-8b-latest | 128k | ¤ 9.40 | ¤ 9.40 |
codestral-latest | 32k | ¤ 18.80 | ¤ 56.41 |
mistral-small-latest | 32k | ¤ 18.80 | ¤ 56.41 |
mistral-large-latest | 128k | ¤ 188.03 | ¤ 564.10 |
Model | Context | Input Cost / 1M | Output Cost / 1M |
---|---|---|---|
llama-3.3-70b-versatile | 128k | ¤ 55.47 | ¤ 74.27 |
llama-3.1-8b-instant | 128k | ¤ 4.70 | ¤ 7.52 |
llama3-70b-8192 | 8k | ¤ 55.47 | ¤ 74.27 |
llama3-8b-8192 | 8k | ¤ 4.70 | ¤ 7.52 |
mixtral-8x7b-32768 | 32k | ¤ 22.56 | ¤ 22.56 |
gemma2-9b-it | 8k | ¤ 18.80 | ¤ 18.80 |
Model | Context | Input Cost / 1M | Output Cost / 1M |
---|---|---|---|
grok-beta | 131k | ¤ 470.09 | ¤ 1410.26 |
grok-2-latest | 131k | ¤ 188.03 | ¤ 940.17 |