Inference provider
Explore models served by Fireworks AI. Compare capabilities, context, privacy, and pricing across its available routes.
In this catalog
Across the catalog
Per 1M text tokens
Tokens per request
Kimi K3 is Moonshot AI's open-weight Mixture-of-Experts model with 2.8T total and 104B active parameters and a 1M-token context window. It accepts text, image and video input and produces text, always reasons with low, high or max effort, and is built for long-horizon coding, knowledge work and reasoning.
Kimi K3 is Moonshot AI's open-weight Mixture-of-Experts model with 2.8T total and 104B active parameters and a 1M-token context window. It accepts text, image and video input and produces text, always reasons with low, high or max effort, and is built for long-horizon coding, knowledge work and reasoning.
Access 2 models served through Fireworks AI on AnonRouter's privacy-first gateway, including Kimi K3 and Kimi Latest. Fireworks open-model Chat Completions use its default zero-data-retention policy; service metadata is logged and prompt caches may remain briefly in volatile memory.
