Llama 3.3 70B (Together)
The most-deployed open-weights chat model in 2025, strong reasoning at 70B with broad inference-provider support.
Llama 3.3 70B (Together) is a efficient AI model from Together AI. It costs $0.880 per million input tokens and $0.880 per million output tokens (blended $0.880/M), with a 128,000-token context window.
Profile inherited from upstream Llama 3.3 70B ↗ — this is a hosted variant of the same open-weights model.
- Strong open chat baseline
- Cheap on Groq/Cerebras
- 128K context
- Wide ecosystem
- Self-hosted production chat
- Cost benchmarking
- RAG
Benchmarks
More from Together AI
See all 10 →Frequently asked questions
How much does Llama 3.3 70B (Together) cost?
Llama 3.3 70B (Together) costs $0.880 per million input tokens and $0.880 per million output tokens, for a blended reference rate of $0.880 per million tokens.
What is Llama 3.3 70B (Together)'s context window?
Llama 3.3 70B (Together) supports up to 128,000 tokens of context in a single request.
What is Llama 3.3 70B (Together) best for?
Llama 3.3 70B (Together) is well suited to Strong open chat baseline, Cheap on Groq/Cerebras and 128K context.
Who makes Llama 3.3 70B (Together)?
Llama 3.3 70B (Together) is developed and served by Together AI.