Available models for Serverless Inference #
Access the most popular models instantly, with no cold starts. Pay only for what you use (by tokens, minutes, steps) ensuring cost efficiency and seamless performance.
Text Models #
Name | String in API | Size | Context Length | Quantization | License | |
---|---|---|---|---|---|---|
Llama 3.1 70B Instruct | llama-3.1-70b-instruct | 70.60B | 8k | bf16 | Llama 3.1 Community License Agreement | |
Qwen 2.5 Coder 32B Instruct | qwen2.5-coder-32b-instruct | 32.80B | 8k | bf16 | Apache License 2.0 | |
Pixtral 12b 2409 | pixtral-12b-2409 | 12.40B | 8k | bf16 | Apache License 2.0 | |
Mistral Nemo Instruct 2407 | mistral-nemo-instruct-2407 | 12.20B | 8k | bf16 | Apache License 2.0 | |
Llama 3.1 8B Instruct | llama-3.1-8b-instruct | 8.03B | 8k | bf16 | Llama 3.1 Community License Agreement |
Important: Context Length is intentionally set low during the Early Access phase and will be updated once General Availability is released
Ektos AI offers the most popular and trending open source models. We add new models on our platform immediately after they are released.
If you would like to use a model that is not currently supported, please let us know on Discord!
Next steps #
- Use text models.
- Use audio models.
- Use embedding models.
- Get in touch and interact with our community on our Discord.