Vai al contenuto
AI.info

tools

SambaNova Cloud

SambaCloud is a hosted API platform for running open-source AI models, with OpenAI-compatible endpoints, model integrations, and token-based pricing.

SambaNova Cloud

In inglese

SambaCloud provides hosted inference for models including DeepSeek, Llama, Qwen, Gemma, MiniMax, and gpt-oss. Developers can access the models through an OpenAI-compatible API, a web playground, integrations, and starter kits.

Plans include Free, Developer, and Enterprise options. Usage is billed by model and token volume; Enterprise customers can request subscription pricing, custom rate limits, on-request models, and features such as BYOC. It is an inference service, not a tool for training or hosting arbitrary model code.

Features

  • OpenAI-compatible API endpoints
  • Hosted inference for open-source models
  • Web playground for testing models
  • Support for text, image, and audio-capable models
  • Integrations with CrewAI, Hugging Face, Cline, and AWS
  • Automatic prompt caching for MiniMax-M2.7
  • Production and preview model access
  • Enterprise options including BYOC and custom rate limits

Use cases

  • Build applications with hosted open-source language models
  • Prototype prompts and model calls in the web playground
  • Add model inference to coding and agent workflows
  • Run support bots using repeated documentation prompts
  • Create applications that reuse long prompts with prompt caching

Pros

    Cons

      Capabilities

      • Choice of models — “Choose your model and run!” source
      • No code retained — “SambaCloud never sees or collects any of your data or user prompts, ensuring full data privacy.” source
      • API — “With the SambaNova OpenAI compatible endpoints, simply set OPENAI_API_KEY to your SambaNova API Key.” source
      • Runs models for you — “It delivers the fastest inference speeds on large open-source models — including Llama, DeepSeek, and Qwen — using SambaNova's proprietary Reconfigurable Dataflow Unit (RDU) AI chip.” source

      Get it

      Security

      • SOC 2 Type II — “We hold SOC 2 Type 2 and ISO 27001 certifications, reflecting our commitment to robust security controls, rigorous risk management, and continuous improvement.” source
      • SOC 2 — “We hold SOC 2 Type 2 and ISO 27001 certifications, reflecting our commitment to robust security controls, rigorous risk management, and continuous improvement.” source
      • ISO 27001 — “We hold SOC 2 Type 2 and ISO 27001 certifications, reflecting our commitment to robust security controls, rigorous risk management, and continuous improvement.” source

      Pricing

      Prices checked
      2026-09-25

      MiniMax-M2.7

      • 0.06 USD per 1M tokens (cached input)
      • 0.60 USD per 1M tokens (input)
      • 2.40 USD per 1M tokens (output)

        DeepSeek-V3.1

        • 3 USD per 1M tokens (input)
        • 4.50 USD per 1M tokens (output)

          DeepSeek-V3.2

          • 3 USD per 1M tokens (input)
          • 4.50 USD per 1M tokens (output)

            gemma-4-31B-it

            • 0.38 USD per 1M tokens (input)
            • 1.15 USD per 1M tokens (output)

              gpt-oss-120b

              • 0.22 USD per 1M tokens (input)
              • 0.59 USD per 1M tokens (output)

                Meta-Llama-3.3-70B-Instruct

                • 0.60 USD per 1M tokens (input)
                • 1.20 USD per 1M tokens (output)

                  MiniMax-M3

                  • 0.60 USD per 1M tokens (input)
                  • 2.40 USD per 1M tokens (output)
                    Official website