Fireworks · Products & Services

Products & Services listings from Fireworks on TechiSeek. 17 public listings.

• Zephyr 7B Beta (Fireworks)
  Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series, and is…
• Ministral 3 3B Instruct 2512 API & Playground (Fireworks)
  Mistral's Ministral 3 3B dense model with vision encoder. The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, effic…
• Ministral 3 14B Instruct 2512 API & Playground (Fireworks)
  Mistral's Ministral 3 14B dense model with vision encoder. The largest model in the Ministral 3 family, Ministral 3 14B offers frontier cap…
• Ministral 3 8B Instruct 2512 API & Playground (Fireworks)
  Mistral's Ministral 3 8B dense model with vision encoder. A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficie…
• MiroThinker-1.7 API & Playground (Fireworks)
  MiroThinker-1.7 API & Playground from fireworks.ai provides Specification and Supported Functionality.
• MiniMax M2.7 API & Playground (Fireworks)
  M2.7 is capable of building complex agent harnesses and completing highly elaborate productivity tasks, leveraging Agent Teams, complex Ski…
• Minimax M3 API & Playground (Fireworks)
  MiniMax-M3 is a native multimodal model with 512K context running ~428B parameters and ~23B activated parameters.
• Deepseek R1 05/28 API & Playground (Fireworks)
  05/28 updated checkpoint of Deepseek R1. Its overall performance is now approaching that of leading models, such as O3 and Gemini 2.5 Pro.
• MiniMax-M2.5 API & Playground (Fireworks)
  MiniMax M2.5 is built for state-of-the-art coding, agentic tool use, search, and office work, extensively trained with reinforcement learni…
• MiniMax-M2.1 API & Playground (Fireworks)
  MiniMax M2.1 is built for strong real-world performance across complex, multi-language, and agent-driven workflows, with robust support spa…
• MiMo-V2.6-Pro-RL API & Playground (Fireworks)
  MiMo-V2.6-Pro is a 1T-parameter sparse MoE omnimodal model (text, image, video, audio) with 1M-token context, designed as Xiaomi’s flagship…
• MiniMax-M1-80k API & Playground (Fireworks)
  We introduce MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
• DeepSeek R1 (Fast) API & Playground (Fireworks)
  DeepSeek R1 (Fast) is the speed-optimized serverless deployment of DeepSeek-R1. Compared to the DeepSeek R1 (Basic) endpoint, R1 (Fast) pro…
• DeepSeek Coder 7B Base API & Playground (Fireworks)
  Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and…
• Llama 4 Scout Instruct (Basic) API & Playground (Fireworks)
  The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences.
• DeepSeek R1 (Basic) API & Playground (Fireworks)
  DeepSeek R1 (Basic) is the cost-optimized serverless deployment of DeepSeek-R1. Compared to the DeepSeek R1 (Fast) endpoint, R1 (Basic) pro…
• LLaVA V1.6 Yi 34B (Fireworks)
  LLaVA is an open-source chatbot trained by fine-tuning LLMs on multimodal instruction-following data.