Parasail
Inference cloud for AI-native startups: serverless open and frontier models behind one OpenAI-format API, plus dedicated endpoints.
Overview
Parasail models are available through Nautili. Requests to them use the same routing, governance and observability as every other request.
Models
- UI-TARS 7B bytedance/ui-tars-1.5-7bView model: UI-TARS 7B
- 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 Pro 0423deepseek/deepseek-v4-proView model: DeepSeek V4 Pro 0423
- DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813View model: DeepSeek V4 Pro 0813
- 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
- Gemma 3 27Bgoogle/gemma-3-27b-itView model: Gemma 3 27B
- Gemma 3 4Bgoogle/gemma-3-4b-itView model: Gemma 3 4B
- Gemma 4 26B A4B google/gemma-4-26b-a4b-itView model: Gemma 4 26B A4B
- Gemma 4 31Bgoogle/gemma-4-31b-itView model: Gemma 4 31B
- MythoMax 13Bgryphe/mythomax-l2-13bView model: MythoMax 13B
- Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instructView model: Meta: Llama 3.2 3B Instruct
- Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instructView model: Meta: Llama 3.3 70B Instruct
- Meta: Llama 4 Maverickmeta-llama/llama-4-maverickView model: Meta: Llama 4 Maverick
- MiniMax M3minimax/minimax-m3View model: MiniMax M3
- MiniMax M3.1 Flashminimax/minimax-m3.1-flashView model: MiniMax M3.1 Flash
- Mistral: Mistral Nemomistralai/mistral-nemoView model: Mistral: Mistral Nemo
- Mistral: Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instructView model: Mistral: Mistral Small 3.2 24B
- Kimi K2.6moonshotai/kimi-k2.6View model: Kimi K2.6
- Kimi K3moonshotai/kimi-k3View model: Kimi K3
- gpt-oss-120bopenai/gpt-oss-120bView model: gpt-oss-120b
- gpt-oss-20bopenai/gpt-oss-20bView model: gpt-oss-20b
- Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instructView model: Qwen2.5 VL 72B Instruct
- Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507View model: Qwen3 235B A22B Instruct 2507
- Qwen3 Coder Nextqwen/qwen3-coder-nextView model: Qwen3 Coder Next
- Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instructView model: Qwen3 Next 80B A3B Instruct
- Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instructView model: Qwen3 VL 235B A22B Instruct
- Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instructView model: Qwen3 VL 8B Instruct
- Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3bView model: Qwen3.5-35B-A3B
- Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17bView model: Qwen3.5 397B A17B
- Qwen3.5-9Bqwen/qwen3.5-9bView model: Qwen3.5-9B
- Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3bView model: Qwen3.6 35B A3B
- Qwen3.8 27Bqwen/qwen3.8-27bView model: Qwen3.8 27B
- Llama 3 8B Lunarissao10k/l3-lunaris-8bView model: Llama 3 8B Lunaris
- Cydonia 24B V4.1thedrummer/cydonia-24b-v4.1View model: Cydonia 24B V4.1
- Skyfall 36B V2thedrummer/skyfall-36b-v2View model: Skyfall 36B V2
- UnslopNemo 12Bthedrummer/unslopnemo-12bView model: UnslopNemo 12B
- GLM 5.2z-ai/glm-5.2View model: GLM 5.2
- 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
Integration
Point your existing SDK or tool at your Nautili endpoint and key. Nautili routes requests to Parasail models within your policies.
Managed: use Nautili-issued credentials.
Connect your stack to Nautili
Route across supported providers through one control layer.