OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 5.5 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 22, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Llama-3 Chat (70B) This page | ||||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Yes, Llama-3 Chat (70B) can stream responses as they are generated.
Yes, Llama-3 Chat (70B) supports both function calling and structured outputs.
Llama-3 Chat (70B) was built by Meta.
No. Its listed capabilities are function calling, streaming, and structured outputs, with no support for image or video inputs.
It is accessed via the v1/chat/completions endpoint.
