UltraGPT
FFireworks
Every Fireworks model UltraGPT can reach, kept in sync with the live catalog — pricing, context window and capabilities for each one.
1 model from Fireworks Up to 1.05M tokens of context
1
Models tracked
1
Providers
1
Reasoning models
1
See images (vision)
1,049K
Largest context window
0
Free to run
All Fireworks models.
Search and filter this provider's lineup — pricing per million tokens, context window, modalities, reasoning effort and independent benchmark scores where available.
1 of 1 models
Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...
ReasoningTool callingVisionStreamingJSON mode
Context window1.05M tok
Max output943.7K tok
ReleasedSep 24, 2026
Knowledge cutoff—
Text + ImageText
Input$3 / 1M tok
Output$15 / 1M tok
Cache read$0.3 / 1M tok
Effort: max, high, low