OpenRouter API를 통해 Fireworks AI 모델을 어떻게 사용합니까?

OpenRouter는 하나의 OpenAI 호환 API를 통해 Fireworks AI 모델 2개를 제공합니다. OpenRouter API 키를 만들고, 클라이언트가 https://openrouter.ai/api/v1을 가리키도록 설정한 다음, 모델을 fireworks/ember-1와 같은 ID로 설정하십시오. 빠른 시작에는 지원되는 모든 SDK의 요청 예제가 있습니다.

Fireworks AI의 모델 중 컨텍스트 창이 가장 큰 모델은 무엇입니까?

Ember-1은 OpenRouter의 모든 Fireworks AI 모델 중 가장 큰 컨텍스트 윈도우를 갖추고 있으며, 요청당 최대 1,048,576개의 토큰을 받을 수 있습니다.

OpenRouter에서 가장 최신인 Fireworks AI 모델은 무엇입니까?

Ember-1은 OpenRouter에 가장 최근에 추가된 Fireworks AI 모델로, 2026년 9월 24일에 등록되었습니다.

Fireworks AI

Access 2 Fireworks AI models through the OpenRouter unified API Ember-1 및 FireLLaVA 13B 포함. Compare pricing, context windows, benchmarks, and capabilities between different Fireworks AI models.

Fireworks AI 처리된 토큰 OpenRouter에서

Fireworks: Ember-1Ember-1
2.38B개 토큰
Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40% fewer tokens than the base model while maintaining comparable quality across Fireworks' evaluations. It is suited for coding, knowledge work, and agentic workflows where reasoning cost and latency matter.
제작: fireworks2026년 9월 24일1.05M 컨텍스트US$3/M 입력 토큰US$15/M 출력 토큰
Fireworks: FireLLaVA 13BFireLLaVA 13B
A blazing fast vision-language model, FireLLaVA quickly understands both text and images. It achieves impressive chat skills in tests, and was designed to mimic multimodal GPT-4. The first commercially permissive open source LLaVA model, trained entirely on open source LLM generated instruction following data.
제작: fireworks2024년 4월 26일4K 컨텍스트

Fireworks AI

Access 2 Fireworks AI models through the OpenRouter unified API Ember-1 및 FireLLaVA 13B 포함. Compare pricing, context windows, benchmarks, and capabilities between different Fireworks AI models.

Fireworks AI 처리된 토큰 OpenRouter에서

Fireworks: Ember-1Ember-1
2.38B개 토큰
Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40% fewer tokens than the base model while maintaining comparable quality across Fireworks' evaluations. It is suited for coding, knowledge work, and agentic workflows where reasoning cost and latency matter.
제작: fireworks2026년 9월 24일1.05M 컨텍스트US$3/M 입력 토큰US$15/M 출력 토큰
Fireworks: FireLLaVA 13BFireLLaVA 13B
A blazing fast vision-language model, FireLLaVA quickly understands both text and images. It achieves impressive chat skills in tests, and was designed to mimic multimodal GPT-4. The first commercially permissive open source LLaVA model, trained entirely on open source LLM generated instruction following data.
제작: fireworks2024년 4월 26일4K 컨텍스트

Fireworks AI

자주 묻는 질문

Fireworks AI

자주 묻는 질문