inference

inference service documentation.

Service Summary

total resources: 17

Resources

agent_chat_completions
async_invocations
batch_files
batch_results
batches
chat_completions
dedicated_inference_accelerators
dedicated_inference_ca
dedicated_inference_gpu_model_config

dedicated_inference_sizes
dedicated_inference_tokens
dedicated_inferences
embeddings
image_generations
messages
models
responses