All Together Models
Llama 3.1 405B (Together)
The world's largest open model, delivered with high throughput via Together AI.
DeepSeek V4 Pro (Together)
Flagship DeepSeek model for coding, reasoning, and agentic work.
Gemma 4 31B Instruct (Together)
Open Gemma instruction model for efficient chat and self-hosted deployments.
Llama 3.3 70B Turbo (Together)
Compact Llama instruction model for fast chat and local deployment.
Qwen3 Coder 480B A35B FP8 (Together)
Massive coding agent model for complex repositories and full-stack development.
Qwen3.7 Max (Together)
Flagship Qwen model for complex reasoning, coding, and agentic workflows.
MiniMax M3 (Together)
MiniMax multimodal coding model for long-context reasoning and agent tasks.
Kimi K3 (Together)
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work.
Nemotron 3 Ultra 550B (Together)
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy.
GPT OSS 120B (Together)
Open-weight GPT model for self-hosted reasoning and instruction-following workloads.
GLM 5.2 (Together)
Open flagship GLM for long-horizon coding agents and million-token context work.
