Claude Fable 5 is Anthropic's Mythos-class model released for general use, built for demanding reasoning and long-horizon agentic work. It takes text and image input and produces text output, with a 1M-token context window, up to 128K output tokens and always-on adaptive thinking.
GPT-5.6 Sol Pro is GPT-5.6 Sol run in OpenAI's pro reasoning mode, which performs more model work per request for difficult tasks that justify higher latency and token use. It is the same underlying model, with text and image input, text output and a context window of about 1.05M tokens.
Mistral Uncensored 1.2 is an uncensored 24B fine-tune of Mistral Small 24B, built on Dolphin Mistral 24B, made for open-ended dialogue, roleplay and creative writing with minimal content restrictions. It accepts text and image input, supports function calling and structured output, and has a 128K-token context window.
Kimi K3 is Moonshot AI's open-weight Mixture-of-Experts model with 2.8T total and 104B active parameters and a 1M-token context window. It accepts text, image and video input and produces text, always reasons with low, high or max effort, and is built for long-horizon coding, knowledge work and reasoning.
Claude Opus 4.8 is Anthropic's Opus model for dependable, long-running agentic work and coding. It builds on Opus 4.7 with sharper judgment and more candid flagging of doubts about its own output, and takes text and image input with a 1M-token context window, up to 128K output tokens and adaptive thinking.
Grok 4.5 is xAI's intelligent coding model for agentic software engineering and workflow tasks, with function calling, structured outputs, and a 500K-token context window.
Gemini 3.5 Flash is a Flash model in Google's Gemini 3 series, optimized for real-world tasks at higher speed and lower cost. It supports thinking. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window and up to 65K output tokens.
DeepSeek V4 Pro is an MoE model with 1.6T total parameters (49B active) and a 1M-token context window. It's built for advanced reasoning, coding, and long-running agent tasks, and performs well on knowledge, math, and software engineering benchmarks.
GLM-5.2 is Z.ai's open-weight Mixture-of-Experts model for long-horizon tasks and software engineering. It takes text input and output with a 1M-token context window and up to 128K output tokens, and offers multiple thinking effort levels to balance performance and latency.
Qwen 3.7 Max is the largest model in the Qwen 3.7 series, with deep thinking, function calling, prompt caching, and multimodal input support for images and video. It excels at programming, office and productivity tasks, and long-running autonomous agent workflows.
GPT-5.5 is OpenAI's GPT-5 series model for coding and complex professional work. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and reasoning effort from none to xhigh.
MiniMax-M3 is MiniMax's natively multimodal Mixture-of-Experts model with about 428B total and 23B active parameters. It takes text, image and video input and produces text, with a context window of up to 1M tokens, and can also operate a desktop computer.
Gemma 4 26B A4B Uncensored is a community fine-tune of Google DeepMind's Gemma 4 26B A4B, modified to reduce refusals. The base model is a Mixture-of-Experts model with 25.2B total and 3.8B active parameters; this variant takes text input and produces text output.
Qwen 2.5 7B Instruct running in a Trusted Execution Environment (TEE). A compact model with strong coding, math, and multilingual capabilities supporting 29+ languages, with hardware attestation evidence available for independent verification.
Gemma 4 31B is the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family, with about 30.7B parameters. It takes text and image input and produces text output, with a 256K-token context window, configurable thinking, native function calling and pretraining on over 140 languages.
Llama 3.3 70B is Meta's multilingual instruction-tuned text model, released in December 2024. It takes text input and produces text and code with a 128K-token context window, officially supports eight languages, and is built for assistant-style chat.
Nomic Embed Text is an open-source English text embedding model from Nomic AI with a context of up to 8,192 tokens and fully released training data. It produces 768-dimensional embeddings that can be shortened, and expects task prefixes such as search_query and search_document for retrieval, clustering and classification.
gpt-oss-120b is OpenAI's open-weight Mixture-of-Experts language model with 117B total and 5.1B active parameters, released under the Apache 2.0 license. It takes text input and produces text output with a 128K-token context window, configurable low, medium and high reasoning, full chain-of-thought access and native tool use including function calling and structured outputs.
DeepSeek-V3.2 uses DeepSeek Sparse Attention for efficient long contexts, with strong reasoning and tool use.
DeepSeek V4 Flash 0731 is the July 31, 2026 official release of DeepSeek V4 Flash, a Mixture-of-Experts model with 284B total and 13B active parameters and a 1M-token context window. It keeps the preview's architecture and size but is re-post-trained for much stronger agentic performance, with low, high and max reasoning effort.
Moonshot AI's open-weight multimodal agentic model has 1T total and 32B active parameters, built for long-horizon coding and tool use.
Qwen3.5-397B-A17B is a multimodal Mixture-of-Experts model from Alibaba's Qwen team, with 397B total parameters and 17B active per token. It takes text, image and video input and produces text, with a 262K-token native context window (extendable to about 1M), a default thinking mode, tool calling and support for 201 languages and dialects.
Qwen's dense 27B vision-language model supports reasoning, coding and tool-driven tasks.
HauhauCS's Aggressive adaptation of Qwen3.8-27B retains text and visual capabilities while modifying refusal behavior.
Qwen3 32B is a dense 32.8B-parameter model in the Qwen3 family from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking mode, supports 119 languages, and has a native 32K-token context window (131K with YaRN).
GLM-5.1 is Z.ai's open-weight Mixture-of-Experts model for agentic engineering, with 744B total and 40B active parameters. It takes text input and output with a 200K-token context window and up to 128K output tokens, and is tuned for coding agents and long-running tool use.
Z-Image Turbo is the distilled, speed-focused variant of Z-Image, a 6B-parameter open-weight image model from Alibaba's Tongyi-MAI team built on a single-stream diffusion transformer. It generates images from a text prompt in 8 sampling steps, with photorealistic output and English and Chinese text rendering.
BGE-EN-ICL is an English text embedding model from BAAI (Beijing Academy of Artificial Intelligence), built on a 7B-parameter Mistral architecture. It supports in-context learning: adding a task instruction and a few example query and answer pairs to a query helps it adapt to new retrieval tasks, and it also works zero-shot.
BGE-M3 is a multilingual text embedding model from BAAI (Beijing Academy of Artificial Intelligence), built from XLM-RoBERTa-large. It supports more than 100 languages and inputs up to 8,192 tokens, and one model provides dense, sparse (lexical) and multi-vector retrieval, producing 1,024-dimensional dense embeddings.
Chroma1-HD is an 8.9B-parameter open-weight text-to-image model by lodestones (Lodestone Rock), derived from Black Forest Labs' FLUX.1 [schnell] and released under Apache 2.0. It is intended as a neutral base for fine-tuning and generates images from a text prompt, including adult content.
Orpheus TTS is an open-source text-to-speech model from Canopy Labs, built on Llama 3.2 3B as a speech language model. It produces human-like speech with natural intonation, supports emotion control through simple tags and zero-shot voice cloning, and streams audio for real-time use.
DeepSeek V4 Flash 0731 Fast is a faster serving variant of DeepSeek V4 Flash 0731, DeepSeek's July 2026 release of its 284B-parameter Mixture-of-Experts model with 13B active parameters. The model has a 1M-token context window and is re-post-trained for stronger agentic performance, with low, high and max reasoning effort.
DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.
DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.
DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.
Gemma 3 27B Instruct is the 27-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output, with a 128K-token context window and support for over 140 languages, for tasks such as chat, summarization, question answering and image understanding.
Gemma 4 26B A4B Instruct is the Mixture-of-Experts model in Google DeepMind's open-weight Gemma 4 family, with 25.2B total and 3.8B active parameters per token. It takes text and image input and produces text output, with a 256K-token context window, configurable thinking and native function calling.
Gemma 4 Uncensored is an uncensored variant of Google Gemma 4 26B, a Mixture-of-Experts model with 26B total parameters and only 4B active per token. Fine-tuned for uncensored chat without content filtering, it supports 256K context, coding, and general-purpose conversation.
Kokoro is an open-weight text-to-speech model from hexgrad with 82 million parameters, built on the StyleTTS 2 and ISTFTNet architectures. Released under Apache 2.0, it offers 54 voices across 8 languages and is designed to give natural speech while staying fast and inexpensive to run.
Llama 3.2 3B is a small multilingual text model from Meta, instruction tuned for assistant-style chat and agentic tasks such as knowledge retrieval, summarization and prompt rewriting. It takes text input and produces text and code with a 128K-token context window, and officially supports eight languages.
Multilingual E5 Large Instruct is a text embedding model from Microsoft researchers, initialized from XLM-RoBERTa-large with 24 layers and 1,024-dimensional embeddings. It covers about 100 languages and takes inputs up to 512 tokens, with each query paired with a one-sentence task instruction to guide retrieval and similarity tasks.
MiniMax-M2.5 is MiniMax's open-weight large language model for coding, agentic tool use and search, and office work. It takes text input and produces text output, and is built for complex multi-step agentic tasks and deliverable outputs such as Word, PowerPoint and Excel documents.
MiniMax-M2.7 is MiniMax's open-weight model of about 229B parameters, built for agentic and professional work. It handles software engineering (debugging, refactoring, code security), complex agent harnesses with tool search, and editing of Word, Excel and PowerPoint files.
Mistral Small 3.2 is a 24B open-weight model from Mistral AI that accepts text and image input, released in June 2025 as a minor update to Mistral Small 3.1. It improves instruction following, produces fewer repetitive or infinite generations, and has a more robust function-calling template.
Mistral Uncensored Roleplay is an uncensored 24B fine-tune of Mistral Small 24B for character-driven roleplay, immersive storytelling and open-ended creative writing with minimal content restrictions. It accepts text and image input, supports function calling and has a 128K-token context window.
Kimi K2.5 is Moonshot AI's open-weight, natively multimodal Mixture-of-Experts model with 1T total and 32B active parameters and a 256K-token context window. It accepts text and image input, offers thinking and instant modes, and is built for coding, visual coding, agent swarm workflows and office tasks.
Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built on Kimi K2.6, with 1T total parameters and 32B active parameters. It always operates in thinking mode, supports text and image input, and targets long-horizon software engineering, agentic task decomposition, and multi-turn coding workflows with 256K context.
Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback.
Hermes 3 405B is Nous Research's full-parameter fine-tune of Meta's Llama 3.1 405B, focused on aligning the model to the user with strong steering and control. It improves agentic behavior, roleplay, reasoning, multi-turn conversation and long-context coherence, and supports function calling and JSON structured outputs.
Llama Nemotron Embed VL 1B v2 is NVIDIA's multimodal embedding model for question-answering retrieval over documents. It pairs a Llama 3.2 1B language model with a SigLIP2 image encoder (about 1.7B parameters total) and embeds text queries and document pages given as images, text or both, including tables, charts and infographics, as 2,048-dimensional vectors.
NVIDIA Nemotron 3 Nano 30B is a compact and efficient language model from NVIDIA, optimized for fast inference while maintaining strong performance across diverse tasks.
NVIDIA Nemotron 3 Ultra is built for frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads while supporting up to 1M token context.
NVIDIA Nemotron 3.5 Super VL is an open multimodal vision-language model for specialized agents. Its 120B-parameter Mixture-of-Experts design (12B active) understands text, images, documents, GUIs, and video, combining reasoning, instruction following, and tool use for long-running agentic workflows.
Qwen 3 235B A22B Instruct 2507 is the July 2025 update of Alibaba's Qwen3 Mixture-of-Experts model, with 235B total and 22B active parameters. This variant runs in non-thinking mode only, answering directly without reasoning blocks, and has a native 262K-token context window.
Qwen 3 235B A22B Thinking 2507 is the July 2025 update of Alibaba's Qwen3 Mixture-of-Experts model, with 235B total and 22B active parameters. This variant always thinks before answering, for complex reasoning tasks, and has a native 262K-token context window.
Qwen 3 Coder 480B Turbo is a faster serving variant of Qwen3 Coder 480B A35B Instruct, Alibaba's Qwen team's Mixture-of-Experts coding model with 480B total and 35B active parameters. The model has a native 262K-token context window and is built for agentic coding, tool calling and repository-scale work.
Qwen 3 Next 80B is a Mixture-of-Experts model from Alibaba's Qwen team with 80B total and 3B active parameters, using hybrid Gated DeltaNet and gated attention layers with multi-token prediction for efficient long-context work. It takes text input and output with a native 262K-token context window.
Qwen3-TTS 0.6B is the smaller text-to-speech model in Alibaba's Qwen team's Qwen3-TTS series, built on a multi-codebook language model with a 12Hz speech tokenizer. It speaks 10 languages including Chinese, English, Japanese and Spanish, supports streaming output, and balances quality with efficiency, with variants for preset voices and 3-second voice cloning.
Qwen3-TTS 1.7B is the larger text-to-speech model in Alibaba's Qwen team's Qwen3-TTS series, built on a multi-codebook language model with a 12Hz speech tokenizer. It speaks 10 languages including Chinese, English, Japanese and Spanish, supports streaming output and instruction-based style control, with variants for preset voices, voice design from a text description and 3-second voice cloning.
Qwen 3.6 35B A3B is a fast mixture-of-experts model with 35B total parameters and ~3B active per token. Strong at agentic coding, STEM reasoning, and tool use, with a native 256K context window.
Qwen 3.8 2.4T is Alibaba's open-weight 2.4-trillion-parameter MoE model (95B active), with major gains in software engineering, research, and long-horizon agentic tasks. It is text-only, requires thinking mode, and supports a 262K-token context window.
Qwen 3.8 27B is an open-weight dense model from Alibaba's Qwen team with 27B parameters and a vision encoder, using hybrid Gated DeltaNet and gated attention layers. It takes text, image and video input with a native 262K-token context window and is built for coding, professional and research work, and long-horizon agentic tasks, with adjustable thinking effort.
Qwen3 Embedding 0.6B is the smallest text embedding model in Alibaba's Qwen team's Qwen3 Embedding series, with 28 layers and a 32K-token context. It supports more than 100 natural and programming languages, takes optional task instructions, and produces embeddings of up to 1,024 dimensions that can be set to a smaller size.
Qwen3 Embedding 8B is the largest text embedding model in Alibaba's Qwen team's Qwen3 Embedding series, with 36 layers and a 32K-token context. It supports more than 100 natural and programming languages, takes optional task instructions, and produces embeddings of up to 4,096 dimensions that can be set anywhere from 32 to 4,096.
Qwen3-VL 235B A22B Instruct is Alibaba's Qwen vision-language Mixture-of-Experts model with about 236B total and 22B active parameters. It takes image, video and text input and produces text, with a native 256K-token context, OCR in 32 languages, GUI agent abilities and long-video understanding.
Chatterbox HD is a text-to-speech model from Resemble AI's Chatterbox family. The open-source Chatterbox models are built on a 0.5B Llama backbone and support zero-shot voice cloning from a short reference clip and control over emotional intensity, with a PerTh watermark in generated audio.
WAI-Illustrious-SDXL is a community anime checkpoint by the Civitai creator WAI0731, fine-tuned from OnomaAI's Illustrious XL, an SDXL-based model. It generates anime and illustration-style images from a text prompt, including adult content.
Lustify SDXL is a community fine-tune of SDXL by the Civitai creator coyotte for photorealistic images, including adult content. It understands both natural-language prompts and Danbooru-style tags, and generates images from a text prompt.
Lustify v7 (GGWP) is a release of Lustify, a community fine-tune of SDXL by the Civitai creator coyotte for photorealistic images, including adult content. It understands both natural-language prompts and Danbooru-style tags, and generates images from a text prompt.
Lustify v8 (APEX) is a release of Lustify, a community fine-tune of SDXL by the Civitai creator coyotte for photorealistic images, including adult content. It understands both natural-language prompts and Danbooru-style tags, and generates images from a text prompt.
Stable Diffusion 3.5 Large is Stability AI's 8B-parameter Multimodal Diffusion Transformer (MMDiT) text-to-image model, with improved image quality, typography and complex prompt understanding. It generates images from a text prompt.
HunyuanImage 3.0 is Tencent's open-weight native multimodal image model, unifying understanding and generation in one autoregressive framework. It uses a Mixture-of-Experts design with 80B total and 13B active parameters, generates images from a text prompt and can use reasoning to expand sparse prompts.
Hy4 Preview is a 770B-parameter Mixture-of-Experts flagship model from the Tencent Hy team, with 49B parameters active per token and a 1M-token context window. It is post-trained for software engineering, office and data analysis, game development, and scientific research, with strong long-horizon reasoning, tool use, and agentic performance.
Muse Spark Open is an open-weight reasoning model from Meta for coding and agentic workflows. It supports tool calling and native image understanding in a single checkpoint, using a sparse Mixture-of-Experts architecture with 816B total / 42B active parameters and a 1M-token context window.
Grok 4.20 is xAI's reasoning model built for speed and agentic tool calling, with low hallucination rates and strict prompt adherence. It takes text and image input and produces text output, with a 1M-token context window, function calling and structured outputs.
Grok 4.20 Multi-Agent is a variant of xAI Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks.
Grok 4.3 is xAI's fast, reliable model with strong tool calling and instruction following, suited to agentic workflows. It takes text and image input and produces text output, with a 1M-token context window, function calling, structured outputs and reasoning effort from none to xhigh.
Grok 4.6 is xAI's model for coding, agentic tasks and knowledge work, designed for long, multi-step work such as research, codebase tasks and turning an idea into a working application. It takes text and image input and produces text output, with a 500K-token context window, function calling, structured outputs and low to xhigh reasoning effort.
Grok 4.7 is xAI's model for software engineering and professional knowledge work, especially long-running tasks. Compared with Grok 4.6 it uses a larger base model trained longer on harder tasks and checks its own output more carefully, and it takes text and image input with a 500K-token context window and low to xhigh reasoning effort.
xAI's fast coding model trained specifically for agentic coding, currently in early access.
MiMo-V2.6-Flash is Xiaomi's efficiency-balanced omnimodal model: a sparse Mixture-of-Experts with 309B total and 15B activated parameters, natively understanding text, image, video, and audio with a 1M-token context window. Trained with mixed reinforcement learning across coding, general agents, visual, and cybersecurity tasks, it is built for long-horizon coding, tool use, and computer use.
GLM-4.6 is Z.ai's open-weight Mixture-of-Experts model with 355B total and 32B active parameters. It takes text input and output with a 200K-token context window and up to 128K output tokens, and is built for agentic coding, front-end development, reasoning, writing and role-play.
GLM-4.7 is Z.ai's open-weight Mixture-of-Experts model with 355B total and 32B active parameters. It takes text input and output with a 200K-token context window and up to 128K output tokens, and is built for agentic coding, UI generation, tool use, reasoning and writing.
GLM-4.7-Flash-Heretic is an uncensored experimental variant of GLM-4.7-Flash, optimized for creative freedom and unfiltered dialogue with fast inference speed.
GLM-5 is Z.ai's open-weight Mixture-of-Experts model with 744B total and 40B active parameters, built for complex systems engineering and long-horizon agentic tasks. It takes text input and output with a 200K-token context window and up to 128K output tokens.
The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528.
DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2.
DeepSeek V3.1 is DeepSeek's hybrid Mixture-of-Experts model with 671B total and 37B active parameters, supporting both thinking and non-thinking modes in a single model. It has a 128K-token context window and improves tool calling and agent tasks over DeepSeek V3.
DeepSeek V4 Flash (Preview) is the April 2026 preview release of DeepSeek's efficiency-focused Mixture-of-Experts model, with 284B total and 13B active parameters and a 1M-token context window. It offers a non-thinking mode and two thinking levels (high and max) for fast reasoning and coding workloads.
DeepSeek-V4-Flash-Vision-Exp is DeepSeek's experimental multimodal model in the V4-Flash family, adding visual understanding to the V4-Flash architecture. It serves a 1M-token (1,048,576) context window and supports image input with visual grounding, tool calling, structured/JSON output, and configurable reasoning effort (low/high/max, or disabled).
Gemma 3 12B Instruct is the 12-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output, with a 128K-token context window and support for over 140 languages, for tasks such as chat, summarization, question answering and image understanding.
Gemma 3 4B Instruct is the 4-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output, with a 128K-token context window and support for over 140 languages, for tasks such as chat, summarization, question answering and image understanding.
Gemma 4 31B Instruct Turbo is a faster serving variant of Gemma 4 31B, the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family. The base model takes text and image input and produces text output, with a 256K-token context window, configurable thinking and native function calling.
Granite 4.2 8B is IBM's 8B-parameter dense reasoning model in the open-weight Granite 4.2 family, for reasoning, code generation, tool calling and agentic workflows. It takes text input and produces text output with a 128K-token native context, and offers full thinking, non-thinking and low-effort thinking modes per request.
Ling 3.0 Flash is inclusionAI's hybrid reasoning model, a hybrid-linear Mixture-of-Experts with 124B total and 5.1B active parameters built for efficient agentic workflows such as coding and deep research. It takes text input and output with a 256K-token context window, and its thinking mode can be turned off per request.
Ling 3.0 Flash VL is inclusionAI's multimodal version of Ling 3.0 Flash, a Mixture-of-Experts model with 124B total and 5.5B active parameters. It takes text, image and video input and produces text with a context of up to 256K tokens, and is built for document and chart understanding, GUI agents and long-video question answering.
Meta Llama 3.1 70B Instruct Turbo is a faster serving variant of Llama 3.1 70B Instruct, Meta's multilingual instruction-tuned text model. The model has a 128K-token context window, officially supports eight languages and supports tool use.
Meta Llama 3.1 8B Instruct Turbo is a faster serving variant of Llama 3.1 8B Instruct, Meta's small multilingual instruction-tuned text model. The model has a 128K-token context window, officially supports eight languages and supports tool use.
Llama 3.3 70B Instruct is Meta's 70B-parameter multilingual instruction-tuned model, tuned for assistant-style dialogue in English, German, French, Italian, Portuguese, Hindi, Spanish and Thai. It takes text input and produces text and code with a 128K-token context window. This Turbo variant is a faster serving variant of Llama 3.3 70B Instruct.
Llama 4 Scout is Meta's natively multimodal Mixture-of-Experts model with 17B active parameters, 16 experts and 109B total parameters. It takes text and image input and produces text and code with a context window of up to 10M tokens, and is built for assistant chat and visual reasoning such as captioning and image question answering.
Llama Guard 4 is a natively multimodal safety classifier with 12 billion parameters trained jointly on text and multiple images. Llama Guard 4 is a dense architecture pruned from the Llama 4 Scout pre-trained model and fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It itself acts as an LLM: it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.
Muse Glimmer 30B is an open-weight multimodal model from Meta Superintelligence Lab, distilled from Muse Spark. It is a dense 30B transformer that takes text and image input and produces text with a context window of at least 131K tokens, built for local and coding agents, tool calling and multimodal reasoning on a single consumer GPU or Mac.
Phi-4 is Microsoft's 14B-parameter dense decoder-only language model, trained on a blend of synthetic data, filtered public web content and academic books and Q&A data with a focus on reasoning. It takes text input and produces text output with a 16K-token context window and is intended primarily for English.
12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware.
Nemotron Content Safety 3.5 is a multimodal safety classifier developed by NVIDIA. A compact safety model that handles text, images, and custom policies. It outputs a safe/unsafe classification plus a reasoning trace, and can be used as an inference-time guardrail, as a judge for LLM safety testing and evaluation, or with the accompanying training dataset to post-train models for safer behavior.
NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single GPU, delivering high accuracy for reasoning, tool use, and instruction following.
NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substantial leap in agentic capability over its predecessor Nemotron 3 Nano, with up to 4x higher throughput on a 1M-token context.
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.
Qwen3.5-35B-A3B is an efficient Mixture-of-Experts model from Alibaba's Qwen3.5 series with 35B total parameters and only 3B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Delivers strong performance on reasoning, coding, and vision-language tasks at a fraction of the compute cost.
Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It features a 262K token context window, thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Excels at reasoning, coding, instruction following, and long-context tasks.
Qwen2.5 is a model pretrained on a large-scale dataset of up to 18 trillion tokens, offering significant improvements in knowledge, coding, mathematics, and instruction following compared to its predecessor Qwen2. The model also features enhanced capabilities in generating long texts, understanding structured data, and generating structured outputs, while supporting multilingual capabilities for over 29 languages.
Qwen3 14B is a dense 14.8B-parameter model in the Qwen3 family from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking mode, supports 119 languages, and has a native 32K-token context window (131K with YaRN).
Qwen3 30B A3B is a Mixture-of-Experts model in the Qwen3 family with 30.5B total and 3.3B active parameters from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking mode, supports 119 languages, and has a native 32K-token context window (131K with YaRN).
Qwen3 VL 30B A3B Instruct is a Mixture-of-Experts vision-language model from Alibaba's Qwen team. It takes text, image and video input and produces text with a native 256K-token context window, and handles visual agent tasks, visual coding, 2D and 3D grounding, long video understanding and OCR in 32 languages.
Qwen3.5-27B is Alibaba's largest dense Qwen3.5 model, delivering near-frontier quality across reasoning, coding, and instruction following. It features a 262K token context window (extensible to 1M), thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Best suited for production deployments and complex enterprise tasks requiring top-tier performance.
L3 8B Lunaris v1 Turbo is a faster serving variant of Lunaris v1, Sao10K's 8B generalist and roleplay model. Lunaris is a merge of four Llama 3 8B fine-tunes on Meta Llama 3 8B Instruct, aimed at better creativity and logic than Sao10K's Stheno v3.2.
L3.1 70B Euryale v2.2 is Sao10K's fine-tune of Meta Llama 3.1 70B Instruct for creative writing and roleplay. Compared with v2.1 it was trained on more roleplay and creative writing data, with added data for system-prompt adherence and reasoning.
Hy4 Preview is a 770B-parameter Mixture-of-Experts model from the Tencent Hy Team, with 49B parameters active per token and a 1M-token context window. It uses Gated DeepSeek Sparse Attention with IndexCache and is post-trained for software engineering, office and data analysis, game development and scientific research, with adjustable reasoning effort.
Inkling Small is a smaller model in Thinking Machines Lab's Inkling family, a Mixture-of-Experts with 276B total and 12B active parameters. Like Inkling, it accepts text, image and audio input and generates text, with a context of up to 1M tokens and variable thinking effort.
MiMo-V2.6-Pro is the flagship of Xiaomi's MiMo-V2.6 series: a sparse Mixture-of-Experts model with 1.02T total and 42B activated parameters, natively omnimodal across text, image, video and audio, with a 1M-token context window. Trained with large-scale mixed reinforcement learning and groupwise agentic grading, it is built for demanding agentic work including long-horizon coding, multi-tool agents and cybersecurity tasks.
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.
DeepSeek V4.1 Flash Fast is a lower-latency serving tier of DeepSeek V4.1 Flash, the same model served for faster output. It is a Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window, with strong reasoning, coding, and agentic performance.
GLM-5.2 Fast is a lower-latency serving tier of GLM-5.2, Z.ai's model for long-horizon tasks, served for faster output. It takes text input and output with a 1M-token context window, and offers stronger coding than GLM-5.1 with multiple thinking effort levels to balance performance and latency.
GLM-5.3 Fast is a lower-latency serving tier of GLM-5.3, Z.ai's reasoning model for complex software engineering and long-horizon agent tasks. It shares GLM-5.2's base model with improved post-training for coding, and supports text input and output with a 1M-token context window.
Gemma 4 12B Instruct is the instruction-tuned 12B model in Google DeepMind's Gemma 4 family of open models. It is a dense 11.95B-parameter multimodal model with configurable thinking modes, native function calling, and support for over 140 languages.
Gemma 4 31B Instruct NVFP4 is a 4-bit NVFP4 quantization of Gemma 4 31B IT, Google DeepMind's 30.7B-parameter dense open model, with both weights and activations quantized. It supports text and image input, configurable thinking, and function calling.
Abliterated Large V2 is Abliteration AI's reasoning model derived from Z.ai's GLM-5.3, with refusal behavior removed through abliteration and further fine-tuning. It takes text input and output with a 1M-token context window, always reasons at low, high or max depth, and is aimed at red teaming, security research and agent testing.
Aion 3.0 is a roleplay and storytelling system from AionLabs, built on the GLM model family, in which several specialized models contribute to each response. It takes text input and output with a 128K-token context window and up to 32K output tokens, and supports reasoning.
Aion 3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict at lower cost. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.
Aion 3.5 is a roleplay and storytelling system from AionLabs, built on the GLM model family, in which several specialized models contribute to each response. Compared with Aion 3.0 it doubles the context window to 256K tokens, with up to 32K output tokens.
Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict at lower cost. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.
Wan 2.7 Pro is the high-fidelity tier of Wan 2.7, Alibaba's unified image generation and editing model family, with a focus on text rendering, brand colors and consistent multi-image output. This variant generates images from a text prompt at up to 4K resolution.
Wan 2.7 is Alibaba's unified image generation and editing model family. This standard tier has the same features as Wan 2.7 Pro, including text rendering and brand colors, with faster generation and a maximum resolution of 2048x2048. This variant generates images from a text prompt.
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work such as long code refactors, front-end development, and finance and analysis tasks. It features a 1M token context window, 128K max output tokens, always-on adaptive thinking, and strong multimodal capabilities, and tends to be more concise in its plans and summaries.
Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong document and vision understanding.
Claude Opus 4.5 is Anthropic's frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection.
Claude Opus 4.6 is Anthropic's Opus model for demanding coding, long-running agentic work and knowledge work such as research, financial analysis and building documents. It takes text and image input and produces text output, with a 1M-token context window, up to 128K output tokens and adaptive thinking with effort controls.
Claude Opus 4.7 is Anthropic's Opus model for advanced software engineering, especially complex, long-running coding tasks. It builds on Opus 4.6 with more precise instruction following, verification of its own outputs and higher-resolution vision, and offers a 1M-token context window, up to 128K output tokens and adaptive thinking.
Claude Opus 4.8 Fast is Claude Opus 4.8 run in Anthropic's fast mode, the same model weights with a faster inference configuration that raises output speed by up to 2.5x. Capabilities are unchanged: text and image input, text output, a 1M-token context window and adaptive thinking for agentic work and complex coding.
Claude Opus 5 is Anthropic's Opus model for daily professional work, with gains over Opus 4.8 in software engineering, knowledge work and scientific research. It checks its own work and iterates until a task succeeds, and takes text and image input with a 1M-token context window, up to 128K output tokens and adaptive thinking.
Claude Opus 5 Fast is Claude Opus 5 run in Anthropic's fast mode, the same model weights with a faster inference configuration that raises output speed by up to 2.5x. Capabilities are unchanged: text and image input, text output, a 1M-token context window and adaptive thinking for coding, knowledge work and research.
Claude Opus 5.5 is Anthropic's Opus model for long-running agentic coding and knowledge work. Compared with Opus 5 it uses fewer tokens per task and writes more clearly, and it takes text and image input with a 1M-token context window, up to 128K output tokens and always-on adaptive thinking.
Claude Opus 5.5 Fast serves the same Opus 5.5 model with faster output generation, a 1M token context window, up to 128K output tokens, adaptive thinking, vision, and tool calling.
Claude Sonnet 4.5 is Anthropic's balanced model offering strong performance on coding, reasoning, and general tasks with good speed and cost efficiency.
Claude Sonnet 4.6 is Anthropic's best combination of speed and intelligence, offering strong performance on coding, reasoning, and general tasks with excellent speed and cost efficiency. It features a 1M token context window and 64K max output tokens.
Claude Sonnet 5 is Anthropic's Sonnet model built for agentic work: planning, using tools such as browsers and terminals, coding, reasoning and knowledge work. It takes text and image input and produces text, with a 1M-token context window, up to 128K output tokens and adaptive thinking, and improves on Sonnet 4.6.
Claude Sonnet 5.5 is Anthropic's Sonnet model, balancing speed and intelligence for well-scoped everyday work such as building features, fixing bugs and creating documents, slides and spreadsheets. It improves on Sonnet 5 in coding, token efficiency and clear writing, with a 1M-token context window, up to 128K output tokens and adaptive thinking.
FLUX.2 [max] is the top tier of Black Forest Labs' FLUX.2 image model family. FLUX.2 pairs a Mistral-3 vision-language model with a rectified flow transformer for generation and editing in one architecture. This variant generates images from a text prompt and can ground generation in real-time web context.
FLUX.2 [pro] is the production tier of Black Forest Labs' FLUX.2 image model family. FLUX.2 pairs a Mistral-3 vision-language model with a rectified flow transformer for generation and editing in one architecture. This variant generates images from a text prompt at up to 4 megapixels.
Seed 2.1 Turbo is one of ByteDance Seed's two Seed 2.1 models (with Pro), an agent model for general agents, end-to-end coding and multimodal understanding. It understands text, images and video with a 256K-token context window and supports deep thinking, GUI tasks, tool calling and structured output.
Seedream 4.5 is ByteDance Seed's image generation and editing model, scaled up from Seedream 4.0 with stronger typography, dense text rendering and closer preservation of reference details. This variant generates images from a text prompt.
Seedream 5.0 Lite is ByteDance Seed's unified multimodal image generation model with deep thinking and online search, which it uses to interpret the intent behind a prompt and depict current topics. This variant generates images from a text prompt.
Eleven Turbo v2.5 is a low-latency text-to-speech model from ElevenLabs that generates speech in 32 languages. It is built for real-time and conversational uses where fast audio output matters more than maximum expressiveness.
Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower latency.
Gemini 3.1 Flash TTS is Google's low-latency text-to-speech model that turns text into natural, expressive speech in more than 70 languages. It supports native multi-speaker dialogue and audio tags written into the text to steer style, pace and delivery, and its audio carries a SynthID watermark.
Gemini 3.1 Pro Preview is the preview release of Google's Gemini 3.1 Pro, a reasoning model for software engineering and agentic workflows that need precise tool use. It refines the Gemini 3 Pro series with better thinking, improved token efficiency and more grounded, factually consistent answers. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window and up to 65K output tokens.
Gemini 3.5 Flash-Lite is the fastest, most cost-efficient Gemini 3.5 model with 1M context, ideal for everyday questions, summarization, and lightweight coding tasks.
Gemini 3.6 Flash is a Flash model in Google's Gemini 3 series designed for agentic work, with strengths in code generation, agentic execution and spatial reasoning. It suits fast agentic loops with complex coding cycles. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window and up to 65K output tokens.
Gemini 3.7 Flash is a Flash model in Google's Gemini 3 series of natively multimodal reasoning models, built as a workhorse for coding and agentic work. It improves on Gemini 3.6 Flash in coding and web development, supports low, medium and high thinking levels, and has a 1M-token context window with up to 65K output tokens.
Gemini 3.8 Flash is a Flash model in Google's Gemini 3 series, engineered for long-horizon software engineering, autonomous agents and complex enterprise workflows at Flash-level speed and cost. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window, up to 65K output tokens and low, medium and high thinking levels.
Gemini 4 Argon is Google's frontier model for complex workflows across software engineering, enterprise knowledge work, and cybersecurity defense, with a unified 1M token context window and tunable thinking.
Gemini Embedding 2 is Google's natively multimodal embedding model, in preview. It maps text, images, video, audio and PDF documents into a single embedding space across more than 100 languages, accepting up to 8,192 text tokens, with 3,072-dimensional output that can be shortened through Matryoshka Representation Learning.
Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) is the speed- and cost-focused model in Google DeepMind's Nano Banana image family, built for high-volume generation and editing. This variant generates images from a text prompt.
Gradium TTS is a real-time streaming text-to-speech model from Gradium, built for voice agents. It speaks English, French, German, Spanish and Portuguese with mid-sentence code-switching, works with instant and professional voice clones, and reads hard cases such as phone numbers and email addresses without separate text normalization.
Ideogram 4.0 is Ideogram's 9.3B-parameter open-weight text-to-image model, a single-stream diffusion transformer trained from scratch. It is built for in-image text and design layouts, with structured JSON prompts, bounding-box placement, hex color palettes and output up to 2K, including very wide aspect ratios.
Ideogram 4.5 is Ideogram's image generation and editing model, built for precise multi-turn edits that change part of an image while leaving the rest untouched. This variant generates images at native 2K from a text prompt, optionally guided by up to five reference images.
ImagineArt 1.5 Pro is ImagineArt's image model for realistic, cinematic images at native 4K resolution. It generates images from a text prompt and optional reference images, with a focus on lighting, composition, color placement and sharp in-image text.
Mercury 2 is Inception's diffusion-based reasoning language model, which generates by refining many tokens in parallel rather than one at a time. It takes text input and output with a 128K-token context window and supports tunable reasoning depth, native tool calling and schema-aligned JSON output.
Mercury 3 is Inception's most capable diffusion-based reasoning model, generating over 1,000 tokens per second with a 1M-token context window, tunable reasoning, tool calling, and structured output support.
Inworld TTS-1.5 Max is a text-to-speech model from Inworld AI for real-time, expressive voice applications. It speaks 15 languages, supports voice cloning from a sample, and is the higher-quality option in the TTS-1.5 family, alongside the lower-latency TTS-1.5 Mini.
Krea 2 Large is the larger tier of Krea 2, Krea's foundation image model built from scratch for aesthetics and creative control over style. It is more than twice the size of Krea 2 Medium with lighter post-training, giving rawer, more textured output suited to photorealism, and generates images from a text prompt with optional style references and moodboards.
Krea 2 Medium is the smaller, faster tier of Krea 2, Krea's foundation image model built from scratch for aesthetics and creative control over style. Its post-training keeps output stable across generations and suits illustration, anime and painting, and it generates images from a text prompt with optional style references and moodboards.
Uni-1 is Luma AI's unified understanding and generation model. It processes text and images in one interleaved sequence so that understanding of the prompt guides generation. This variant generates images from a text prompt, optionally guided by up to nine reference images.
Uni-1 Max is the higher-quality tier of Uni-1, Luma AI's unified understanding and generation model. It processes text and images in one interleaved sequence so that understanding of the prompt guides generation. This variant generates images from a text prompt, optionally guided by up to nine reference images.
Muse Image is Meta's image generation and editing model, the first from Meta Superintelligence Labs. It works with Meta's Muse Spark reasoning model to plan layouts, draw on web context and combine multiple references, and renders legible in-image text. This variant generates images from a text prompt.
Muse Wonder is a reasoning model from Meta Superintelligence Labs for long-running personal and professional agentic work, released in October 2026 as a larger class of model than the Muse Spark family. It accepts text, images, audio, video and PDF documents and returns text, with a context window of about 1M tokens. It is built to plan, call tools in parallel, keep track of what matters across a long task and try another approach when it hits a blocker.
MiniMax M3.1 Flash is a frontier model for coding, agentic workflows, and complex reasoning, with a 1M-token context window, text, image, and video input, and tunable thinking depth from low to max (max by default).
Clone your voice from a short recording and generate natural speech in it across 30+ languages.
OpenAI's multimodal flagship model with vision capabilities, strong reasoning, and broad knowledge. Popular for its balanced performance across tasks. Version: 2024-11-20.
OpenAI's cost-efficient small model that delivers GPT-4 level intelligence at a fraction of the cost. Ideal for high-volume applications requiring strong reasoning. Version: 2024-07-18.
GPT-5.2 is OpenAI's GPT-5 series model for complex professional work. It takes text and image input and produces text output, with a 400K-token context window, up to 128K output tokens and reasoning effort from none to xhigh.
GPT-5.3 Codex is OpenAI's coding model built on GPT-5.3 and optimized for agentic coding tasks in Codex and similar environments. It takes text and image input and produces text output, with a 400K-token context window, up to 128K output tokens and low to xhigh reasoning effort.
GPT-5.4 is OpenAI's GPT-5 series model for coding and complex professional work. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and reasoning effort from none to xhigh.
GPT-5.4 Mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use.
GPT-5.4 Pro is a version of OpenAI's GPT-5.4 that uses more compute to think harder and give more precise answers on complex, high-stakes tasks. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and medium to xhigh reasoning effort.
GPT-5.5 Pro is a version of OpenAI's GPT-5.5 that uses more compute to think harder and give more precise answers on complex tasks. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and medium to xhigh reasoning effort.
GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 family, built for complex professional work such as reasoning, coding and agentic workflows. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and reasoning effort from none to max.
GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced.
GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.
GPT-6 Astra is the top tier of OpenAI's GPT-6 family, built for demanding work such as complex reasoning, coding, computer use, research and document creation. It takes text and image input and produces text, with a 1.05M-token context window (up to 922K input and 128K output tokens) and configurable reasoning effort.
GPT-6 Astra with pro reasoning mode for difficult tasks that benefit from more model work. Supports text and image inputs with a 1.05M token context window. Pro mode can use more tokens and take longer than standard Astra.
GPT-6 Luna is OpenAI's most efficient GPT-6 model for focused, high-volume tasks. It is suited for chat, classification, and lightweight agentic workflows, with a 1.05M token context window (922K input, 128K output), text and image inputs, and capable reasoning for its price tier.
GPT-6 Sol is built for complex coding and agentic workflows. It is OpenAI's GPT-6 coding and agent model, with a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from none through max.
GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from low through max.
GPT-6.1 Sol Ultrafast is the same model served in OpenAI's Ultrafast mode, up to 8x faster. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from low through max.
GPT Image 1.5 is OpenAI's image generation model that takes text and image input, with improved instruction following and prompt adherence over earlier GPT Image models. This variant generates images from a text prompt.
text-embedding-3-large is OpenAI's larger text embedding model for search, clustering, recommendations and classification. It accepts up to 8,192 input tokens and returns 3,072-dimensional embeddings by default, which can be shortened with the dimensions parameter to trade accuracy for storage.
text-embedding-3-small is OpenAI's smaller, more efficient text embedding model for search, clustering, recommendations and classification. It accepts up to 8,192 input tokens and returns 1,536-dimensional embeddings by default, which can be shortened with the dimensions parameter.
Qwen 3.6 Plus Uncensored is an uncensored variant of Qwen3.6 Plus, the vision-language Plus model from Alibaba's Qwen team. The base model accepts text, image and video input with a 1M-token context window and supports switchable thinking and function calling.
Qwen 3.7 Plus is a multimodal agent model from Alibaba's Qwen team, built on the Qwen3.7 text model and able to operate graphical interfaces and the command line. It accepts text, image and video input with a 1M-token context window and supports switchable thinking and function calling.
Qwen 3.8 Flash is an efficient multimodal model from Alibaba's Qwen team, built on the open-weight Qwen3.8 Flash Next Mixture-of-Experts model with 125B total and 6B active parameters. It accepts text, image and video input with a 1M-token context window, supports function calling and structured output, and has a thinking mode that can be turned off.
Qwen 3.8 Max is Alibaba's flagship 2.4-trillion-parameter MoE model, with major gains over Qwen 3.7 Max in software engineering and office-productivity workflows and strong long-horizon, multi-agent performance. It accepts both text and vision-language input (images and video), operates in thinking mode only, and supports a 1M-token context window.
Qwen-Image is a 20B-parameter open-weight MMDiT image foundation model from Alibaba's Qwen team, released under Apache 2.0. It generates images from a text prompt across many styles, with particular strength in rendering complex text, including Chinese.
Qwen-Image-2.0 is an image model from Alibaba's Qwen team that unifies generation and editing in one smaller, faster model, with instructions up to 1K tokens for infographics and native 2K resolution. This variant generates images from a text prompt.
Qwen-Image-2.0 Pro is the Pro tier of Qwen-Image-2.0, an image model from Alibaba's Qwen team that unifies generation and editing. It accepts instructions up to 1K tokens for infographics and has native 2K resolution. This variant generates images from a text prompt.
Qwen-Image-2.1 Pro is the Pro tier of Qwen-Image-2.1, a 7B-parameter unified text-to-image and image editing model from Alibaba's Qwen team. It supports native transparent (RGBA) output, up to 10 reference images and 2K resolution. This variant generates images from a text prompt.
Qwen-Image-2.1 Turbo is an accelerated 8-step checkpoint of Qwen-Image-2.1, a 7B-parameter unified text-to-image and image editing model from Alibaba's Qwen team. It supports native transparent (RGBA) output, up to 10 reference images and 2K resolution. This variant generates images from a text prompt.
Qwen-Image-3.0 is the third-generation image model from Alibaba's Qwen team, built for dense layouts such as infographics, newspapers and storyboards. It accepts prompts up to 4.5k tokens and renders text as small as 10px, with native text in 12 languages. This standard tier is a faster version of Qwen-Image-3.0 Pro. This variant generates images from a text prompt.
Recraft V4 is Recraft's rebuilt image model focused on design taste, prompt accuracy and production-grade composition. This standard tier generates 1K images from a text prompt for everyday design work and fast iteration.
Recraft V4 Pro is the Pro tier of Recraft V4, Recraft's rebuilt image model focused on design taste and prompt accuracy. It generates 2K images from a text prompt with finer detail and better anatomy and realism in complex scenes, for high-detail, print-ready visuals.
Grok Text to Speech is xAI's text-to-speech model for long-form and real-time speech generation. It offers built-in voices with distinct styles, speaks 20 languages, and uses inline and wrapping speech tags such as [laugh], [pause] and <whisper> to control delivery.
GLM-5 Turbo is a fast inference model from Z.ai tuned for strong performance in agent-driven environments and production coding workflows.
GLM-5V-Turbo is Z.ai's first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks with image, video, and text inputs.
Claude Haiku 4.5 is Anthropic's small, fast model for real-time, low-latency work such as chat assistants, customer support agents and pair programming. It takes text and image input and produces text output, with a 200K-token context window, up to 64K output tokens and extended thinking.
Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.
Seed 2.0 Mini is the throughput-optimized model in ByteDance Seed's Seed 2.0 family, built for low-latency, high-concurrency and batch workloads. It supports multimodal understanding, tool calling and four thinking levels from minimal to high, with a 256K-token context window.
Seed 2.0 Pro is the general agent model in ByteDance Seed's Seed 2.0 family that focuses on long-chain reasoning and robustness in complex, multi-step workflows. It supports adjustable deep thinking, multimodal understanding and tool calling, with a 256K-token context window and up to 128K output tokens.
Gemini 2.5 Flash is Google's thinking model built for price-performance, suited to large-scale processing, low-latency, high-volume tasks and agentic use cases. It takes text, image, video and audio input and produces text output, with a 1M-token context window and up to 65K output tokens.
Gemini 3.1 Flash-Lite is Google's low-latency, cost-effective multimodal model for high-frequency, lightweight tasks such as high-volume agentic workflows and simple data extraction. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window, up to 65K output tokens and thinking support.
Gemma 4 31B Instruct Ultra is a speed-optimized serving variant of Gemma 4 31B, the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family. The base model takes text and image input and produces text output, with a 256K-token context window, configurable thinking and native function calling.
GPT OSS 120B Ultra is a speed-optimized serving variant of gpt-oss-120b, OpenAI's open-weight Mixture-of-Experts language model with 117B total and 5.1B active parameters. The base model takes text input and produces text output with a 128K-token context window, configurable reasoning effort and native tool use.
Gemini 2.5 Flash-Lite is Google's cost-efficient multimodal model in the Gemini 2.5 family, built for high-frequency, lightweight tasks such as high-volume classification and simple data extraction. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window and thinking support.
Gemini 2.5 Pro is Google's thinking model for reasoning over complex problems in code, math and STEM. It can analyze large datasets, codebases and documents using long context, taking text, image, video, audio and PDF input and producing text output, with a 1M-token context window and up to 65K output tokens.
GPT-4.1 is OpenAI's non-reasoning model that excels at instruction following and tool calling, with broad knowledge across domains. It takes text and image input and produces text output, with a 1M-token context window, up to 32K output tokens and low latency without a reasoning step.
GPT-4.1 Mini is a smaller, faster version of OpenAI's GPT-4.1, built for instruction following and tool calling without a reasoning step. It takes text and image input and produces text output, with a 1M-token context window and up to 32K output tokens.
GPT-4.1 Nano is the fastest, most cost-efficient version of OpenAI's GPT-4.1, built for instruction following and tool calling without a reasoning step. It takes text and image input and produces text output, with a 1M-token context window and up to 32K output tokens.
GPT-5 is OpenAI's reasoning model for coding, reasoning and agentic tasks across domains, with configurable reasoning effort (minimal, low, medium and high). It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens.
GPT-5 Mini is a faster, more cost-efficient version of OpenAI's GPT-5 reasoning model, suited to well-defined tasks, precise prompts and high-volume, low-latency workloads. It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens.
GPT-5 Nano is the fastest, lowest-cost version of OpenAI's GPT-5 reasoning model, suited to summarization and classification tasks. It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens.
GPT-5.1 is OpenAI's GPT-5 series model for coding and agentic tasks, with configurable reasoning effort that includes a non-reasoning setting. It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens.
GPT-5.4 Nano is the lowest-cost GPT-5.4-class model from OpenAI, designed for simple, high-volume tasks where speed and cost matter most, such as classification and data extraction. It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens.
GPT-5.6 Luna is OpenAI's GPT-5.6 model for cost-sensitive, high-volume workloads, roughly matching the nano tier of earlier GPT-5 families. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and reasoning effort from none to max.
o3 is OpenAI's well-rounded reasoning model for complex tasks across domains. It takes text and image input and produces text output, with a 200K-token context window and up to 100K output tokens.
o3-mini is OpenAI's small reasoning model, offering strong reasoning at the cost and latency targets of o1-mini. It takes text input and produces text output, with a 200K-token context window and up to 100K output tokens.
o4-mini is OpenAI's fast, cost-efficient reasoning model, optimized for efficient performance in coding and visual tasks. It takes text and image input and produces text output, with a 200K-token context window and up to 100K output tokens.
Free access to Gemma 4 26B A4B on limited shared capacity. Anonymous route; account opt-in required.
Free access to Llama 3.1 8B Instruct on limited shared capacity. Anonymous route; account opt-in required.
Free access to Mistral Small 3.1 24B on limited shared capacity. Anonymous route; account opt-in required.
Free access to Qwen3 30B A3B on limited shared capacity. Anonymous route; account opt-in required.
Free access to GPT OSS 120B on limited shared capacity. Anonymous route; account opt-in required.
Free access to GPT OSS 20B on limited shared capacity. Anonymous route; account opt-in required.
Free access to North Mini Code on limited shared capacity. Anonymous route; account opt-in required.
Free access to Dots3 Note Preview on limited shared capacity. Anonymous route; account opt-in required.
Free access to LFM 2.5 2.6B on limited shared capacity. Anonymous route; account opt-in required.
Free access to Laguna S 2.1 on limited shared capacity. Anonymous route; account opt-in required.
Free access to Beam on limited shared capacity. Anonymous route; account opt-in required.
Free access to GLM 4.5 Flash on limited shared capacity. Anonymous route; account opt-in required.
DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.
DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.
Kimi K3 is Moonshot AI's open-weight Mixture-of-Experts model with 2.8T total and 104B active parameters and a 1M-token context window. It accepts text, image and video input and produces text, always reasons with low, high or max effort, and is built for long-horizon coding, knowledge work and reasoning.
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.
MiniMax-M3 is MiniMax's natively multimodal Mixture-of-Experts model with about 428B total and 23B active parameters. It takes text, image and video input and produces text, with a context window of up to 1M tokens, and can also operate a desktop computer.
Qwen 3.8 2.4T is Alibaba's open-weight 2.4-trillion-parameter MoE model (95B active), with major gains in software engineering, research, and long-horizon agentic tasks. It is text-only, requires thinking mode, and supports a 262K-token context window.
Qwen 3 Coder 480B Turbo is a faster serving variant of Qwen3 Coder 480B A35B Instruct, Alibaba's Qwen team's Mixture-of-Experts coding model with 480B total and 35B active parameters. The model has a native 262K-token context window and is built for agentic coding, tool calling and repository-scale work.
One ID for free inference. Automatically selects a healthy, eligible free model that fits your request, prioritizing model quality and using observed success rates to break ties. No paid fallback.
Pricing sources are shown per model. Privacy and moderation labels come from published provider metadata and stay separate from AnonRouter's own no-payload-log policy.
