Ember-1: pricing, context and benchmarks

What you need to know about Ember-1

Fireworks AI, based in United States, put Ember-1 online on September 24, 2026. It accepts text and images as input and produces text. Its context window reaches 1,048,576 tokens, larger than 93 % of the models in the registry, and it can write up to 943,718 tokens in one go.

It is a recent model: real-world feedback and independent scores are still scarce.

Ember-1 pricing

On OpenRouter, Ember-1 costs $3 per million input tokens and $15 per million output tokens. Counting three tokens read for every token written, its average price is $6 per million, more expensive than 91 % of paid models (7.9 times the median of $0.76).

A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0135. At 1,000 tasks a day, budget $405 a month. The price calculator redoes this with your own volumes.

Tokens already sent and cached are billed at $0.3 per million.

Performance and benchmarks

Epoch AI does not yet publish a capabilities index for Ember-1. We therefore show no made-up performance rating: only price, context and features count towards its score.

Features, privacy and local use

• It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
• It can answer in an enforced JSON format (structured outputs).
• It is a reasoning model: it "thinks" before answering, which helps on hard tasks but uses more output tokens.

Its weights are not published: it can only be used through the Fireworks AI API or a broker such as OpenRouter, which means sending your data off your machines.