FPT Cloud (BYOK)BYOK

Vietnamese Embedding is a text embedding model from AITeamVN, fine-tuned from BGE-M3 to improve retrieval for Vietnamese. It takes text input and returns embeddings, with an 8,000-token context window.

Quyet 1.0 Large is Chinh Nguyen's calibrated decision model, fine-tuned from Google Gemma-4-31B-it. It reads a state (text, JSON, or a conversation) and a typed question, then returns one option with calibrated probabilities. It does not generate chat text.

DeepSeek-V4-Flash is DeepSeek's open-weight fast mixture-of-experts model for high-throughput chat and coding. It accepts text and image input and returns text. It supports reasoning, tool calling and agentic use.

DeepSeek V4.1 Flash is the open-weight, cost-efficient sparse mixture-of-experts tier of the V4.1 family. It has 552B total parameters with 8B active on input and 16B on output, 1M context, and native vision in with text out. This is the original September 2026 checkpoint.

Saola Small 32B is FPT AI's reasoning-optimized LLM for Vietnamese. It targets finance, banking, STEM and law, with native chain-of-thought for step-by-step problem solving. It takes text input.

Gemma 4 26B A4B is an open-weight model from Google's Gemma 4 family, built from Gemini 3 research to maximize intelligence per parameter. It takes text and image input and generates text. It supports reasoning, tool calling, and coding.

Gemma 4 31B is Google's open-weight dense open reasoning model for complex reasoning, agentic workflows, coding, and multimodal understanding. It takes text and image input and generates text. It supports tool calling and a thinking mode.

Multilingual E5 Large is intfloat's multilingual text embedding model. This build is an optimized variant of intfloat/multilingual-e5-large tuned for lower inference latency. It turns text into embeddings for search and similarity.

Llama 3.3 70B Instruct is Meta's open-weight instruction-tuned model with 70B parameters and a 131072-token context window. It is tuned for multilingual dialogue, with tool use on par with Llama 3.1 70B. It suits chat, reasoning, and coding.

GPT-OSS-120b is OpenAI's open-weight mixture-of-experts reasoning model under the Apache-2.0 license. It has 116.8B total and 5.1B active parameters and a 131,072-token context window. It supports function calling and runs on one 80 GB GPU with MXFP4 weights.

Qwen2.5-VL 7B Instruct is Qwen's open-weight 7B vision-language chat model. It takes images and text as input and answers in text, with streaming support.

Qwen3.8-27B is Alibaba's open-weight dense Qwen3.8 model for agentic coding and complex reasoning, with a native thinking mode. It targets multi-step agent work and large coding tasks.

GLM-5.2 is Z-AI's open-weight flagship reasoning model with a 128K output window. It supports controllable thinking effort, function calling, and MCP integration. It targets long-horizon autonomous coding and agentic tasks.