Fireworks
Fast inference platform for open-weight models.
Overview
Fireworks models are available through Nautili. Requests to them use the same routing, governance and observability as every other request.
Models
- DeepSeek V4 Flash 0423deepseek/deepseek-v4-flashView model: DeepSeek V4 Flash 0423
- DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731View model: DeepSeek V4 Flash 0731
- DeepSeek V4 Flash 0731 (batch)deepseek/deepseek-v4-flash-0731:batchView model: DeepSeek V4 Flash 0731 (batch)
- DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-expView model: DeepSeek V4 Flash Vision Exp
- DeepSeek V4 Flash Vision Exp (batch)deepseek/deepseek-v4-flash-vision-exp:batchView model: DeepSeek V4 Flash Vision Exp (batch)
- DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813View model: DeepSeek V4 Pro 0813
- DeepSeek V4 Pro 0813 (batch)deepseek/deepseek-v4-pro-0813:batchView model: DeepSeek V4 Pro 0813 (batch)
- DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashView model: DeepSeek V4.1 Flash
- DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017View model: DeepSeek V4.1 Flash 1017
- Ember-1fireworks/ember-1View model: Ember-1
- Muse Glimmer 30Bmeta/muse-glimmer-30bView model: Muse Glimmer 30B
- Muse Glimmer 30B (batch)meta/muse-glimmer-30b:batchView model: Muse Glimmer 30B (batch)
- Muse Spark Openmeta/muse-spark-openView model: Muse Spark Open
- MiniMax M3.1 Flashminimax/minimax-m3.1-flashView model: MiniMax M3.1 Flash
- Kimi K2.6moonshotai/kimi-k2.6View model: Kimi K2.6
- Kimi K2.7 Codemoonshotai/kimi-k2.7-codeView model: Kimi K2.7 Code
- Kimi K3moonshotai/kimi-k3View model: Kimi K3
- Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightningView model: Nemotron 3.5 Lightning
- GLM 5.2z-ai/glm-5.2View model: GLM 5.2
- GLM 5.2 (batch)z-ai/glm-5.2:batchView model: GLM 5.2 (batch)
- GLM 5.3z-ai/glm-5.3View model: GLM 5.3
- GLM 5.3 Flashz-ai/glm-5.3-flashView model: GLM 5.3 Flash
- GLM 5.3 Flash (batch)z-ai/glm-5.3-flash:batchView model: GLM 5.3 Flash (batch)
- GLM 5.3 (batch)z-ai/glm-5.3:batchView model: GLM 5.3 (batch)
Integration
Point your existing SDK or tool at your Nautili endpoint and key. Nautili routes requests to Fireworks models within your policies.
Managed: use Nautili-issued credentials.
Connect your stack to Nautili
Route across supported providers through one control layer.