# Model Library

> Canonical: https://www.overmindlab.ai/models

Every model here trains on your agent's own data, benchmarks against your production model, and serves through one OpenAI-compatible API. The weights are yours.

## Qwen 3

- [Qwen 3 4B](https://www.overmindlab.ai/models/qwen-3-4b): 4B, 128K context, —; train from $0.70, serve from $4.00 per 1M output tokens
- [Qwen 3 1.7B](https://www.overmindlab.ai/models/qwen-3-1-7b): 1.7B, 128K context, —; train from $0.55, serve from $4.00 per 1M output tokens
- [Qwen 3 0.6B](https://www.overmindlab.ai/models/qwen-3-0-6b): 0.6B, 128K context, —; train from $0.50, serve from $2.50 per 1M output tokens
- [Qwen 3 8B](https://www.overmindlab.ai/models/qwen-3-8b): 8B, 128K context, —; train from $1.00, serve from $6.00 per 1M output tokens
- [Qwen 3 Coder 30B MoE](https://www.overmindlab.ai/models/qwen-3-coder-30b-a3b-instruct): 30B MoE (3B active), 256K context, —; train from $2.00, serve from $8.00 per 1M output tokens
- [Qwen 3 14B](https://www.overmindlab.ai/models/qwen-3-14b): 14B, 128K context, —; train from $1.25, serve from $10.00 per 1M output tokens
- [Qwen 3 32B](https://www.overmindlab.ai/models/qwen-3-32b): 32B, 128K context, —; train from $2.25, serve from $20.00 per 1M output tokens

## Qwen 3.5

- [Qwen 3.5 4B](https://www.overmindlab.ai/models/qwen-3-5-4b): 4B, 256K context, —; train from $0.70, serve from $4.00 per 1M output tokens
- [Qwen 3.5 2B](https://www.overmindlab.ai/models/qwen-3-5-2b): 2B, 256K context, —; train from $0.55, serve from $4.00 per 1M output tokens
- [Qwen 3.5 0.8B](https://www.overmindlab.ai/models/qwen-3-5-0-8b): 0.8B, 256K context, —; train from $0.50, serve from $2.50 per 1M output tokens
- [Qwen 3.5 9B](https://www.overmindlab.ai/models/qwen-3-5-9b): 9B, 256K context, —; train from $1.00, serve from $6.00 per 1M output tokens
- [Qwen 3.5 27B](https://www.overmindlab.ai/models/qwen-3-5-27b): 27B, 256K context, —; train from $2.00, serve from $15.00 per 1M output tokens
- [Qwen 3.5 35B MoE](https://www.overmindlab.ai/models/qwen-3-5-35b-a3b): 35B MoE (3B active), 256K context, —; train from $2.50, serve from $8.00 per 1M output tokens

## Llama 3

- [Llama 3.2 3B Instruct](https://www.overmindlab.ai/models/llama-3-2-3b-instruct): 3B, 128K context, —; train from $0.55, serve from $4.00 per 1M output tokens
- [Llama 3.2 1B Instruct](https://www.overmindlab.ai/models/llama-3-2-1b-instruct): 1B, 128K context, —; train from $0.50, serve from $2.50 per 1M output tokens
- [Llama 3.1 8B Instruct](https://www.overmindlab.ai/models/meta-llama-3-1-8b-instruct-reference): 8B, 128K context, —; train from $1.00, serve from $6.00 per 1M output tokens
- [Llama 3.1 8B Instruct](https://www.overmindlab.ai/models/llama-3-1-8b-instruct): 8B, 128K context, —; train from $1.00, serve from $6.00 per 1M output tokens
- [Llama 3.3 70B Instruct](https://www.overmindlab.ai/models/llama-3-3-70b-instruct): 70B, 128K context, —; train from $4.50, serve from $35.00 per 1M output tokens

## Antares

- [Antares 1B (Security)](https://www.overmindlab.ai/models/antares-1b): 1.8B, 128K context, —; train from $0.55, serve from $4.00 per 1M output tokens
- [Antares 350M (Security)](https://www.overmindlab.ai/models/antares-350m): 350M, 32K context, —; train from $0.50, serve from $2.50 per 1M output tokens

## LFM2.5

- [LFM2.5 1.2B Instruct](https://www.overmindlab.ai/models/lfm-2-5-1-2b-instruct): 1.2B, 32K context, —; train from $0.50, serve from $2.50 per 1M output tokens
- [LFM2.5 350M](https://www.overmindlab.ai/models/lfm-2-5-350m): 350M, 32K context, —; train from $0.50, serve from $2.50 per 1M output tokens
- [LFM2.5 230M](https://www.overmindlab.ai/models/lfm-2-5-230m): 230M, 32K context, —; train from $0.50, serve from $2.50 per 1M output tokens

## Qwen 2.5

- [Qwen 2.5 0.5B Instruct](https://www.overmindlab.ai/models/qwen-2-5-0-5b-instruct): 0.5B, 32K context, —; train from $0.50, serve from $2.50 per 1M output tokens
- [Qwen 2.5 7B Instruct](https://www.overmindlab.ai/models/qwen-2-5-7b-instruct): 7B, 128K context, —; train from $1.00, serve from $6.00 per 1M output tokens
- [Qwen 2.5 14B Instruct](https://www.overmindlab.ai/models/qwen-2-5-14b-instruct): 14B, 128K context, —; train from $1.25, serve from $10.00 per 1M output tokens
- [Qwen 2.5 72B Instruct](https://www.overmindlab.ai/models/qwen-2-5-72b-instruct): 72B, 128K context, —; train from $5.00, serve from $40.00 per 1M output tokens
- [Qwen 2.5 32B Instruct](https://www.overmindlab.ai/models/qwen-2-5-32b-instruct): 32B, 128K context, —; train from $2.25, serve from $20.00 per 1M output tokens
- [Qwen 2.5 Coder 32B Instruct](https://www.overmindlab.ai/models/qwen-2-5-coder-32b-instruct): 32B, 128K context, —; train from $2.25, serve from $20.00 per 1M output tokens

## Gemma 4

- [Gemma 4 E4B](https://www.overmindlab.ai/models/gemma-4-e4b-it): E4B (~8B), 128K context, —; train from $0.75, serve from $4.00 per 1M output tokens
- [Gemma 4 E2B](https://www.overmindlab.ai/models/gemma-4-e2b-it): E2B (~5.1B), 128K context, —; train from $0.55, serve from $4.00 per 1M output tokens
- [Gemma 4 12B](https://www.overmindlab.ai/models/gemma-4-12b-it): 12B, 256K context, —; train from $1.00, serve from $6.00 per 1M output tokens
- [Gemma 4 31B](https://www.overmindlab.ai/models/gemma-4-31b-it): 31B, 256K context, —; train from $2.50, serve from $10.00 per 1M output tokens
- [Gemma 4 26B-A4B](https://www.overmindlab.ai/models/gemma-4-26b-a4b-it): 26B (4B active), 256K context, —; train from $2.00, serve from $8.00 per 1M output tokens

## Qwen 3.8

- [Qwen 3.8 27B](https://www.overmindlab.ai/models/qwen-3-8-27b): 27B, 256K context, —; train from $2.00, serve from $15.00 per 1M output tokens

## Qwen 3.6

- [Qwen 3.6 27B](https://www.overmindlab.ai/models/qwen-3-6-27b): 27B, 256K context, —; train from $2.00, serve from $15.00 per 1M output tokens

## GPT-OSS

- [GPT-OSS 20B](https://www.overmindlab.ai/models/gpt-oss-20b): 20B MoE, 128K context, —; train from $1.75, serve from $12.00 per 1M output tokens

## Nemotron 3.5

- [Nemotron 3.5 Lightning 30B-A3B](https://www.overmindlab.ai/models/nvidia-nemotron-3-5-lightning-30b-a3b): 30B-A3B, 256K context, —; train from $2.00, serve from $6.00 per 1M output tokens

## Muse Glimmer

- [Muse Glimmer 30B](https://www.overmindlab.ai/models/muse-glimmer-30b): 30B, 128K context, —; train from $2.50, serve from $10.00 per 1M output tokens

Inference API: https://docs.overmindlab.ai/models/inference.md