Baseten releases joey-1, a 2B-parameter open-weights decision model, at $0.01 per million tokens
Baseten released joey-1 on October 29, 2026. It is a 2B-parameter decision model from its in-house research lab Base Labs, priced at $0.01 per million tokens. It is available through Baseten Model APIs and as open weights on Hugging Face.
Baseten on October 29, 2026 released joey-1, a 2B-parameter decision model developed by its in-house research lab Base Labs. The model is priced at $0.01 per million tokens. It is available through Baseten Model APIs and as open weights on Hugging Face.
Key details
- Model: joey-1
- Developer: Base Labs, Baseten's in-house research lab
- Parameters: 2B
- Price: $0.01 per million tokens
- Access: Baseten Model APIs and open weights on Hugging Face
- Release date: October 29, 2026
Family context
With joey-1, the Base Labs decision model family now spans three sizes. The new model joins mammoth-1 (27B) and elephant-1 (9B), which were part of the family release on October 21.
What this means
joey-1 is the smallest of the three Base Labs decision models, at 2B parameters, compared with 9B for elephant-1 and 27B for mammoth-1. Publishing it as open weights on Hugging Face alongside hosted access through Baseten Model APIs gives developers two ways to use it: self-hosting the weights or calling the managed API at $0.01 per million tokens.
Related Articles
Apex Intelligence releases Apex-35B-V1.0, a Qwen3.6-35B-A3B derivative, with open weights on Hugging Face
Apex Intelligence, a Chinese startup founded in June 2026, released its first model, Apex-35B-V1.0, on October 28 with weights on Hugging Face. It is built on Alibaba's Qwen3.6-35B-A3B and, the company says, was developed with help from its automated research system, Apex Research. All benchmark results come from the company's own evaluation.
Liquid AI releases LFM3-VL-2B, a 1.92B on-device vision-language model with video input and thinking
Liquid AI has released LFM3-VL-2B, a 1.92B-parameter vision-language model that accepts text, images and video. It is the first LFM vision model with video input, adds step-by-step thinking, and ships with a 128K-token context window under the LFM Open License v1.0.
Liquid AI releases LFM3-Omni-2B, a 2.17B omni-modal model with speech output
Liquid AI has released LFM3-Omni-2B, its first omni-modal model in the LFM3 family, with 2.17B total parameters and a 32K-token context. It accepts text, images, video and audio, and outputs text, 24 kHz speech, or both interleaved.
NVIDIA Nemotron 3.5 Transcribe: open 30B model handles 40 languages, diarization and translation
NVIDIA released Nemotron 3.5 Transcribe, an open-weight, promptable speech model that transcribes 40 languages, translates 31 to or from English and labels speakers in 13. It is available on Hugging Face and ModelScope alongside Granary v2 data and NeMo Speech fine-tuning recipes.
Comments
Loading...