Guide

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Legacy model retained for compatibility with older integrations

Gemini 2.5 Pro Preview 05-06 from Google - text, image, audio, video, pdf input, 1,048,576 token context

Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight image‑text grounding tasks. It offers a 32 k‑token context window, enabling rich multimodal...

Maestro Reasoning is Arcee's flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32 B tuned with DPO and chain‑of‑thought RL for step‑by‑step logic. Compared to the earlier 7 B...

Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...

Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context window, enabling multi‑file...

Phi-4-reasoning-plus is an enhanced 14B parameter model from Microsoft, fine-tuned from Phi-4 with additional reinforcement learning to boost accuracy on math, science, and code reasoning tasks. It uses the same dense decoder-only transformer architecture as Phi-4, but generates longer, more comprehensive outputs structured into a step-by-step reasoning trace and final answer. While it offers improved benchmark scores over Phi-4-reasoning across tasks like AIME, OmniMath, and HumanEvalPlus, its responses are typically ~50% longer, resulting in higher latency. Designed for English-only applications, it is well-suited for structured reasoning workflows where output quality takes priority over response speed.

Speech generation model for controllable voice, narration, and audio delivery

Speech generation model for controllable voice, narration, and audio delivery

Mercury Coder is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 Haiku...

Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks. It introduces a dual-mode architecture—thinking and non-thinking—allowing dynamic switching between high-precision logical reasoning and efficient dialogue generation. This makes it well-suited for multi-turn chat, instruction following, and complex agent workflows.

DeepSeek Prover V2 is a 671B parameter model, speculated to be geared towards logic and mathematics. Likely an upgrade from [DeepSeek-Prover-V1.5](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V1.5-RL) Not much is known about the model yet, as DeepSeek released it on Hugging Face without an announcement or description.

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...

Multimodal model for complex analysis, long-context understanding, tool use, and model distillation

Flagship DeepSeek model for coding, reasoning, and agentic work

Qwen3 235B-A22B from Fireworks AI - text input, 128,000 token context

Qwen instruction model for multilingual chat, reasoning, and tool use

Venice Small from Venice AI - text input, 32,000 token context

Qwen reasoning model for deliberate problem solving, math, and coding

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen 3 Coder 480b from Venice AI - text input, 256,000 token context

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...

Qwen 3 235B Instruct from Synthetic - text input, 256,000 token context

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

DeepSeek-R1T-Chimera is created by merging DeepSeek-R1 and DeepSeek-V3 (0324), combining the reasoning capabilities of R1 with the token efficiency improvements of V3. It is based on a DeepSeek-MoE Transformer architecture and is optimized for general text generation tasks. The model merges pretrained weights from both source models to balance performance across reasoning, efficiency, and instruction-following tasks. It is released under the MIT license and intended for research and commercial use.

DeepSeek-R1T-Chimera is created by merging DeepSeek-R1 and DeepSeek-V3 (0324), combining the reasoning capabilities of R1 with the token efficiency improvements of V3. It is based on a DeepSeek-MoE Transformer architecture and is optimized for general text generation tasks. The model merges pretrained weights from both source models to balance performance across reasoning, efficiency, and instruction-following tasks. It is released under the MIT license and intended for research and commercial use.

OpenAI image model for production generation, edits, and brand-safe visual workflows

OpenAI image model for production generation, edits, and brand-safe visual workflows

Gemini 2.5 Flash Preview 04-17 from Google - text, image, audio, video, pdf input, 1,048,576 token context

OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...

OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...