SambaNova is launching support for the Responses API across the SambaNova platform — SambaCloud, SambaStack, and SambaManaged — giving AI engineers a cleaner way to connect modern coding agents to fast, production-ready models. /v1/responses support starts with gpt-oss-120b, MiniMax M2.5, and MiniMax M2.7.

TL;DR

SambaNova's Responses API (/v1/responses) is now live across SambaCloud, SambaStack, and SambaManaged.

Unlike Chat Completions, it's built for agentic workflows: tool calls, streaming events, multi-step loops, and reasoning-aware pipelines.

Codex CLI, Cline, and OpenCode all support the Responses API shape and can connect to SambaNova directly.