Models

All models available on AAChat

Default

gpt-4o

gpt-4o is the flagship model of this family, supports a 128k context window and is optimized for dialog.

deepseek/deepseek-r1-0528-qwen3-8b

The first reasoning model from DeepSeek. Outperforms OpenAI GPT-4-o1 on multiple benchmarks.

Meta-Llama-3.3-70B-Instruct

Generation over generation, Meta Llama 3 demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.

Qwen 3 235B A22B

Qwen3 (232Bx22B 'T') is a hybrid instruct + reasoning text model based on a sparse mixture-of-experts architecture. It balances efficiency, performance and quality in an inference service configured for high throughput.

Deepseek V3

Deepseek V3 achieves state-of-the-art performance among open-source code models on multiple programming languages and various benchmarks.