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 | 5.3 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
LLaMA-2 Chat (70B) This page | ||||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Yes, LLaMA-2 Chat (70B) can stream responses as they are generated.
Yes, LLaMA-2 Chat (70B) supports both function calling and structured outputs.
LLaMA-2 Chat (70B) was built by Meta.
No. Its listed capabilities are function calling, streaming, and structured outputs, with no image input support.
It is accessed through the v1 endpoint.
