Model vendor
Fireworks models: API pricing and providers
1 Fireworks model with Fireworks's published list rates and the providers that serve each one. You call them through INFRO on a provider account you connect; that account bills you, and INFRO adds 0% to model spend.
Rates checked 2026-10-05.
Fireworks models
| Model | Modality | List rate | Providers |
|---|---|---|---|
| Ember-1 fireworks/ember-1 Kimi K3 derivative with shorter reasoning traces | Text | $3.00 per 1M input tokens and $15 per 1M output tokens, with cached input at $0.30 per 1M tokens | 2 |
Fireworks models: questions
- Which Fireworks models does this reference list?
- 1 Fireworks model: 1 text. Each has its own page with Fireworks's list rate and the providers that serve it.
- Which providers serve Fireworks models?
- Fireworks AI and OpenRouter. You connect your own account with any of them; INFRO routes between the ones you connect.
- What is the lowest Fireworks input rate listed?
- Ember-1, at $3.00 per 1M input tokens and $15 per 1M output tokens, with cached input at $0.30 per 1M tokens on Fireworks's list (checked 2026-10-05).
- Does INFRO add a markup to Fireworks model usage?
- No. Your Fireworks or provider account bills usage directly; INFRO charges a software subscription and takes 0% of model spend.
Other model vendors
- Alibaba 25
- Amazon 4
- Anthropic 12
- AssemblyAI 2
- Black Forest Labs 7
- Bria 2
- ByteDance 15
- Canopy Labs 3
- Cartesia 1
- Clarity AI 1
- Cloudflare 3
- Cohere 4
- Deepgram 4
- DeepSeek 3
- ElevenLabs 10
- fal 1
- Fish Audio 5
- Google 23
- HeyGen 1
- IC-Light 1
- Ideogram 3
- Inception 1
- Kokoro 1
- Kuaishou 8
- Liquid AI 1
- Luma 3
- Magnific 2
- Meta 3
- Microsoft 7
- MiniMax 15
- Mistral 10
- MMAudio 1
- Moonshot 4
- NVIDIA 4
- OpenAI 37
- Perplexity 5
- PixVerse 2
- Qwen 2
- Real-ESRGAN 1
- Recraft 7
- Runway 4
- Sesame 1
- Stability AI 1
- Suno 1
- Sync 4
- Thinking Machines 1
- Topaz Labs 2
- TypeSafe 1
- Upstage 2
- xAI 16
- Z.ai 15