AIHubMix Smart Router: Fill in the model name as auto, and the gateway will automatically select the optimal model based on the request content; The auto without a suffix uses the default strategy cost_optimized. You can explicitly specify the focus using auto:<strategy>, such as auto (= auto:cost_optimized) cost priority: choose the cheapest as long as the capability meets the standard; auto:balanced balanced: considers capability / cost / latency auto:quality_first quality priority: prioritize selecting the strongest capability for complex reasoning and critical outputs auto:latency_critical low latency priority: prioritize selecting the fastest response
Gemini 4 Neon is the latest model in Google’s Gemini 4 series. It features frontier-level intelligence and can rapidly handle complex software engineering, knowledge work, and scientific research tasks. It has a unified 1-million-token context window, with a maximum single-generation length of up to 1 million tokens.
Genie 4 is Google’s latest real-time interactive world generation model. Through the Interactions API, it can stream controllable video at 24 frames per second in a 16:9 aspect ratio, while simultaneously outputting 48 kHz stereo audio.
Coding GLM 5.5 is a specialized version of GLM-5.5 optimized for AI-powered coding and Coding Agent workflows. It delivers enhanced capabilities in complex reasoning, code generation, and long-running agent tasks. Built on a larger-scale Mixture-of-Experts (MoE) architecture, it incorporates hybrid attention and Loop Transformer technologies to improve reasoning depth, multi-step task execution, and inference efficiency. Coding GLM 5.5 is designed to tackle demanding software engineering challenges, automate complex coding workflows, and power more capable AI agents.
GPT-6.2 Astra is OpenAI’s reasoning model for complex coding, research, and professional work. It accepts text and images and can use tools to develop software, operate computers, and work with documents. Compared with GPT-6.2 Sol’s focus on everyday tasks, Astra is better suited to demanding reasoning and complex, multistep projects.
GPT-6.2 Sol is OpenAI’s general-purpose reasoning model for everyday coding, writing, and multistep agent workflows. It accepts text and images and can use tools for search, code execution, and computer interaction. Compared with GPT-6.2 Astra’s focus on demanding reasoning, Sol is positioned for everyday productivity and agent applications at scale.
MAI-Image-2.7-Flash is a diffusion-based image generation and editing model released by Microsoft, designed for high speed and low cost. Based on this description, it is a speed- and cost-optimized version of the MAI Image 2.7 series, suitable for high-volume workflows.
No description available
Gemini 4 Hydrogen is a Google Gemini 4 model focused on speed and efficiency. Potential use cases include everyday conversations, text processing, and interactive applications where fast responses matter.
Seedream 5.5 is ByteDance’s image generation and editing model for product visuals, advertising, and design assets. It supports precise multi-turn editing and native RGBA output for transparent assets, with improved preservation of unedited regions, more natural lighting and textures, and clearer Chinese and English text, including dense small text.
Hy4 flash is Tencent Hunyuan's latest model, with about one-quarter the parameters of the flagship. While offering lower pricing, it achieves flagship open-source model performance on everyday tasks. It is suitable for programming assistance, agent workflows, document and chart understanding, and other high-frequency, large-scale scenarios in daily office use.
Qwen4-Max is Tongyi Qianwen's next-generation flagship multimodal model, integrating text generation, image and video understanding, and deep reasoning capabilities. It is suitable for programming development, office work, frontend design, and complex agent tasks. The model supports internet search, tool invocation, and structured outputs, is compatible with OpenAI and Anthropic APIs, and helps developers build intelligent applications with multimodal understanding and task-execution capabilities.
Seedance 2.5 Flash is ByteDance’s multimodal video generation model, accepting text, image, audio, and video inputs for frequent creative work and batch content production. It delivers quality close to Seedance 2.5 with twice the generation speed and lower costs, supporting videos up to 30 seconds long at 480p or 720p.
Gemini Decision 1 is designed for judgment and decision-making tasks, helping developers build automated processes and agent workflows that require clear choices.
Coding Qwen4 Max Preview offers lower-cost access to Alibaba Cloud’s Qwen4-Max-Preview through the official Token Plan for coding, frontend design, and agentic tasks. Try it out and share your feedback. This preview service may be unstable and is recommended for testing and evaluation.
ERNIE 5.5 Flash Preview is the latest foundational model in Baidu's Wenxin (ERNIE) series, comprehensively optimized for programming, agents, knowledge work, and deep research. It has 280 billion total parameters, activates 14 billion parameters per token, and supports a 1M-token context window.
Gemini 3.8 Live is a multimodal AI model from Google that delivers a low-latency, audio-to-audio voice interaction experience, enabling real-time conversations without inference delays. It supports interleaved reasoning, asynchronous and synchronous function calling, and built-in proactive audio processing capabilities.
Gemini 2.5 Flash Live is Google's multimodal AI model for real-time interactions, supporting low-latency voice conversations and able to understand user input by combining text, images, or video.
Gemini 4 Carbon is Google DeepMind’s multimodal model for complex coding, long-running agent workflows, and cybersecurity defense. Building on Gemini 4 Argon, it improves software engineering, vulnerability detection and remediation, multimodal understanding, and execution across challenging, multi-step tasks.
Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request. Thinking can...
Browse all models and authors (980)
Popular models
Qwen3.8 Max Preview · Kimi K3 · Qwen3.8 Max · Qwen3.7 Flash · GLM 5.2 · Grok 4.5 · Claude Opus 5 · Claude Sonnet 5 · GPT 5.6 Luna · Gemini 3.6 Flash · DeepSeek V4 Flash · GPT 5.5 · Gemini 3.1 Pro Preview
Browse by model author
OpenAI (148) · Anthropic (33) · Google (98) · Grok (28) · Qwen (156) · DeepSeek (37) · Z.AI (72) · ByteDance (49) · Llama (51) · AI21 (2) · Microsoft (17) · Cohere (21) · Mistral (11) · Moonshot AI (35) · StepFun (5) · Nvidia (17) · Minimax (34) · Ideogram (10) · Jina AI (14) · Stable diffusion (1) · Hunyuan (9) · Baidu (25) · Flux (5) · Meituan (2) · Xiaomi (21) · ElevenLabs (15) · InclusionAI (9) · Agnes (5) · BAAI (4) · Meta (4) · Poolside (4) · TypeSafe (3) · Baseten (2) · Inception (2) · intern-ai (2) · KLing (2) · Liquid (2) · Stealth (2) · Dots Studio (1) · Particle Ai (1) · Recursive (1) · Respan (1) · Sao10k (1) · Thinkingmachines (1) · Upstage (1) · Xingchen Agi (1)
76 free models — no credit card required →
138 models deprecating or retired — dates and replacements →
All models (980)
Auto · Gemini 4 Neon · Genie 4 · Coding GLM 5.5 · GPT 6.2 Astra · GPT 6.2 Sol · Mai Image 2.7 Flash · Coding MiniMax M3.1 Flash · Gemini 4 Hydrogen · Doubao Seedream 5.5 · Hy4 Flash · Qwen4 Max · doubao-seedance-2-5-flash · Gemini Decision 1 · Coding Qwen4 Max Preview · ERNIE 5.5 Flash Preview · Gemini 3.8 Live · Gemini 2.5 Flash Live · Gemini 4 Carbon · Ling 3.2 Flash (free) · Claude Fable 5.2 · Gemini Omni 1.2 Flash · GPT 6.1 Terra · GPT Image 2.6 Flare · GPT Image 2.6 Sunburst · Hy4 · Kimi K3.1 Pro · Kimi K3.1 Pro Highspeed · Particle 1 (free) · Lfm 3 1.7b (free) · Ideogram Vector 1 · DeepSeek V4.1 Flash 1017 · Gemini Omni 1.1 Flash · GLM 5.3 Prime · GPT 6.1 Sol · Grok Imagine Image 2.0 · Jev 1.14 · MiniMax M3.1 Flash · Cohere Rerank V5 Fast · Cohere Rerank V5 Pro · Gemini 4 Argon · Gemini Nano Banana 2.1 · Muse Wonder · Claude Haiku 5.5 · Elephant 1 (free) · Mammoth 1 (free) · Nemotron 3.5 Super VL (free) · Qwen Image 2.1 Pro · Qwen Image 2.1 Turbo · Span 01 Lite (free) · Claude Opus 5.5 · Claude Sonnet 5.5 · GPT 6 Luna · GPT 6 Sol · Mistral Large 4.0 · Gemini 3.8 Flash Lite Tts · Gemini 3.8 Flash Tts · Grok 4.7 · MiMo V2.6 Flash · MiMo V2.6 Pro · MiMo V2.6 Pro Ultraspeed · Qwen3.8 Omni Flash · Decision Model Preview · Jev 1.13 · Jev · Step 5 Preview · Doubao Seedream 5.0 Flash · GLM 5.3 Flashx · GPT 6 Astra · Jina Ocr V1 · Gemini 3.8 Flash · Claude Fable 5.1 · DeepSeek V4.1 Flash · GLM 5.3 Flash · GPT Live Transcribe · Xiaomi Mimo V2.6 Pro (free) · GPT Realtime 2.1 · Coding Kimi K3.1 Pro · Coding Kimi K3.1 Pro Highspeed · GLM 5.3 · Qwen 3.8 27B · GPT Image 2.5 Flare · GPT Image 2.5 Sunburst · Mercury 2.5 Preview · Qwen3.8 Max 2026 09-02 · Coding GLM 5.3 · Coding GLM 5.3 Flash (free) · Hy4 Preview · Coding GLM 5.3 Flash · Coding GLM 5.3 (free) · Muse Spark 1.3 · Qwen3.8 Flash · Gemini 3.7 Flash · Mai Image 2.6 · Mai Image 2.6 Flash · Xiaomi Mimo V2.6 Flash (free) · Agnes 3.0 Flash · MiniMax H3 Max · Agents A1 (free) · GLM 5.2 · Intern S2 (free) · DeepSeek V4 Flash 0731 · DeepSeek V4 Flash Vision Exp · DeepSeek V4 Pro 0813 · Dots 3 Note Preview (free) · Grok 4.6 · Coding Xiaomi Mimo V2.6 Flash · DeepSeek V4 Flash 0731 Fast · Mai Thinking 1 · Wan3.0 Video · Wan3.0 Video Prime · GPT 5.6 Sol Disc · Doubao Seedance 2.5 260628 · GPT 5.6 Luna · GPT 5.6 Sol · GPT 5.6 Terra · Qwen3.8 Max · Agnes 2.5 Flash · Agnes 2.5 Pro · Agnes 2.5 Pro Alpha · Agnes Image 2.1 Flash · Grok 4.5 · Lfm 2.5 2.6b (free) · MiniMax H3 · Qwen3.8 2.4t A95B · Claude Opus 5 · Gemini 3.6 Flash · Nemotron 3.5 Lightning (free) · Qwen Image 3.0 · Qwen Image 3.0 Pro · Claude Sonnet 5 · Kimi K3 · Muse Spark 1.2 · Gemini 3.1 Flash Lite Image · Gemini 3.5 Flash Lite · GLM 5.2 Fast Preview · Muse Spark 1.1 · Qwen Audio 3.0 Tts Flash · Qwen Audio 3.0 Tts Plus · Claude Fable 5 · Jina Reranker V3.5 · Claude Opus 4.8 · Hy3 · Doubao Seed 2.1 Pro · Doubao Seed 2.1 Turbo · Mai Image 2.5 Pro · Gemini 3.5 Flash · Grok Build 0.1 · Mai Image 2.5 · Mai Image 2.5 Flash · Coding Kimi K3 · Happyhorse 1.1 I2v · Happyhorse 1.1 R2v · Happyhorse 1.1 T2v · Coding GLM 5.2 (free) · Coding Kimi K3 (free) · Gemini 3.1 Flash Image · Kimi K2.7 Code · Kimi K2.7 Code Highspeed · Gemini 3 Pro Image · GPT 4o Transcribe Diarize · GPT Audio 1.5 · Hy 3d 3.1 · Kling V3 Omni · Kling Video O1 · Longcat 2.0 · MiniMax M3 · Qwen3.7 Flash · Qwen3.7 Plus · Step 3.7 Flash · Claude Opus 4.8 Thinking · Nemotron 3 Nano Omni 30B A3B (reasoning) (free) · Nemotron 3 Ultra 550B A55B (free) · Qwen3.7 Max · GPT Image 2 · Coding GLM 5.2 · ERNIE 5.1 · Gemini 3.1 Flash Lite · Gemini 3.1 Flash Lite (no think) · Grok 4.3 · Happyhorse 1.0 I2v · Happyhorse 1.0 R2v · Happyhorse 1.0 T2v · Happyhorse 1.0 Video Edit · North Mini Code (free) · GPT 5.5 · GPT 5.5 Pro · DeepSeek V4 Flash · DeepSeek V4 Pro · Gemma 4 31B It (free) · Command A Plus 05 2026 · Doubao Seedream 5.0 Pro · ERNIE 5.0 · Kimi K2.6 · Claude Opus 4.7 · Claude Opus 4.7 Thinking · GPT Chat · Qwen3.6 27B · Qwen3.6 35B A3B · Qwen3.6 Flash · Cohere Rerank V4.0 Fast · Cohere Rerank V4.0 Pro · Gemma 4 26B A4B It (free) · grok-4-20-non-reasoning · Grok 4 20 (reasoning) · Qwen Image 2.0 · Qwen Image 2.0 Pro · Coding MiniMax M3 (free) · Doubao Seedance 2.0 260128 · Doubao Seedance 2.0 Fast 260128 · Doubao Seedance 2.0 Mini 260615 · GLM 5.1 · GLM Image · Qwen3.6 Plus · Wan2.7 I2v · Wan2.7 R2v · Wan2.7 T2v · Wan2.7 Videoedit · CC K2.6 Code Preview · Gemma 4 26B A4B It · Gemma 4 31B It · GPT 5.4 · Wan2.7 Image · Wan2.7 Image Pro · Claude Sonnet 4.6 · Coding Xiaomi Mimo V2.6 Pro · Doubao Seed 2.0 Lite 260428 · Doubao Seed 2.0 Mini 260428 · Gemini 3.1 Flash Image Preview · Gemini 3.1 Pro Preview · Gemini 3.1 Pro Preview Customtools · Gemini 3.1 Pro Preview Search · GPT 5.4 Mini · GPT 5.4 Nano · Qwen3.5 Plus · Claude Sonnet 4.6 Thinking · GPT 5.3 Chat · GPT-5.3-Codex · Qwen3.5 122B A10B · Qwen3.5 27B · Qwen3.5 35B A3B · Qwen3.5 397B A17B · Qwen3.5 Flash · Coding GLM 5.1 · Doubao Seed 2.0 Pro · GPT 5.4 High · GPT 5.4 Low · GPT 5.4 Pro · Qwen3 Coder Next · Claude Opus 4.6 · Coding GLM 5.1 (free) · Coding MiniMax M2.7 (free) · GLM 5 Vision Turbo · MiniMax M2.7 · Claude Opus 4.6 Thinking · Coding GLM 5 (free) · Coding GLM 5 Turbo (free) · Coding MiniMax M2.5 (free) · Doubao Seed 2.0 Code Preview · Doubao Seed 2.0 Lite 260215 · Gemini 3 Flash Preview · Gemini 3 Flash Preview Search · GLM 5 Turbo · CC GLM 5.1 · Claude Opus 4.5 · Claude Opus 4.5 Thinking · Embed V 4.0 · ERNIE 5.5 Flash Preview (free) · ERNIE Image Turbo · Flint V1.0 (free) · Cohere Command A · CC MiniMax M3 · Coding MiniMax M3 · Coding GLM 5 · Coding GLM 5 Turbo · GLM 4.7 · GLM 4.7 Flash (free) · Coding GLM 4.7 (free) · Doubao Seedance 1.5 Pro 251215 · Doubao Seedance 1.0 Pro 250528 · Doubao Seedance 1.0 Pro Fast 251015 · Gemini 3 Pro Image Preview · Gemini Embedding 2 · Deepinfra Gemma 4 26B A4B It · GPT-5.2-Codex · Doubao Seedream 5.0 Lite · GPT Image 1.5 · Doubao Seed 2.1 Pro 260628 · GPT 5.2 · GPT 5.2 Chat · GPT 5.2 High · GPT 5.2 Low · GPT 5.2 Pro · GPT 5.1 · GPT-5.1-Codex Max · GPT 5.1 Chat · GPT-5.1-Codex · GPT-5.1-Codex Mini · Claude Haiku 4.5 · Claude Sonnet 4.5 · Claude Sonnet 4.5 Thinking · Grok 4.20 Multi Agent 0309 · Mistral Large 3 · CC GLM 5 · CC GLM 5 Turbo · Cloudflare Glm 5.2 · Gemini 2.5 Flash Image · grok-4-1-fast-non-reasoning · Grok 4.1 Fast (reasoning) · Grok Code Fast 1 · K2.6 Code Preview (free) · Musesteamer Air Image · Qwen3.6 Plus Preview (free) · Zai Glm 5 Turbo · GPT 5 · DeepSeek V3.2 · GPT-5-Codex · DeepSeek V3.1 Thinking · GPT 5 Pro · GPT 5 Mini · GPT 5 Nano · GPT 5 Chat · Claude Opus 4.1 · O3 Deep Research · Kimi K2.5 · Qwen3 Max 2026 01-23 · Qwen3 VL Plus · CC MiniMax M2.7 · CC MiniMax M2.7 Highspeed · MiniMax M2.5 · MiniMax M2.5 Highspeed · Mm Minimax M2.7 Highspeed · Coding MiniMax M2.7 · Coding MiniMax M2.7 Highspeed · CC MiniMax M2.5 · CC MiniMax M2.5 Highspeed · Coding MiniMax M2.5 · Coding MiniMax M2.5 Highspeed · Doubao Seedream 4.5 · Sora 2 · Sora 2 Pro · CC GLM 4.7 · CC MiniMax M2.1 · Coding GLM 4.7 · Coding MiniMax M2.1 · Coding MiniMax M2.1 (free) · GPT 4o Mini Audio Preview · MiniMax M2.1 · O3 · Wan2.6 I2v · Wan2.6 T2v · CC GLM 4.6 · Coding GLM 4.6 · Coding GLM 4.6 (free) · Coding MiniMax M2 · Coding MiniMax M2 (free) · Flux 2 Flex · Flux 2 Pro · Gemini 2.5 Pro · GLM 4.6 · GLM 4.6 Vision · GLM Ocr · Kimi For Coding (free) · O3 Pro · Qianfan Ocr · Qianfan Ocr Fast · Step 3.5 Flash · Wan2.2 I2v Plus · Wan2.5 I2v Preview · Wan2.5 T2v Preview · Gemini 2.5 Pro Search · Kimi K2 Thinking · GLM 4.5 Vision · Gemini 2.5 Flash Search · Gemini 2.5 Flash Preview 05-20 (no think) · Gemini 2.5 Flash Preview 05-20 Search · GPT Image 1 · GPT Image 1 Mini · O4 Mini · Alicloud Kimi K2 Instruct · DeepSeek Ocr · ERNIE 5.0 Thinking Exp · Flux Kontext Max · Gemini 2.5 Flash Image Preview · GLM 4.5 · GPT 4.1 · Grok 4 · Kimi K2 Instruct · Kimi K2 Turbo Preview · Paddleocr VL 0.9b · Pp Structurev3 · Veo 3.0 Generate Preview · AIHubMix Router · GPT 4.1 Mini · GPT 4.1 Nano · Gemini 2.5 Pro Preview 05-06 · Gemini 2.5 Pro Preview 03-25 · Gemini 2.5 Pro Preview 05-06 Search · Gemini 2.5 Pro Preview 03-25 Search · Qwen3 Max Preview · Qwen3 Next 80B A3B Thinking · Qwen3 235B A22B Instruct 2507 · Qwen3 235B A22B Thinking 2507 · Qwen3 Coder 30B A3B Instruct · Qwen3 Coder 480B A35B Instruct · LongCat-Flash-Chat · Gemini 2.5 Pro Preview 06-05 Search · Jina Embeddings V5 Text Nano · Jina Embeddings V5 Text Small · Qwen3 Coder Flash · Qwen3 Coder Plus · Qwen3 Coder Plus 2025 07-22 · ERNIE 5.0 Thinking Preview · inclusionAI/Ling-1T · inclusionAI/Ring-1T · Bce Reranker Base · Codex Mini · Doubao Seedream 4.0 · Embedding V1 · ERNIE 4.5 Turbo · GLM 4.5 X · Gme Qwen2 VL 2B Instruct · Gte Rerank V2 · inclusionAI/Ling-flash-2.0 · inclusionAI/Ling-mini-2.0 · inclusionAI/Ring-flash-2.0 · Jina Deepsearch V1 · Jina Embeddings V4 · Jina Reranker V3 · Llama 4 Maverick · Llama 4 Scout · Qwen Image · Qwen Image Edit · Qwen Image Max · Qwen Mt Plus · Qwen Mt Turbo · Qwen3 Embedding 0.6b · Qwen3 Embedding 4B · Qwen3 Embedding 8B · Qwen3 Reranker 0.6b · Qwen3 Reranker 4B · Qwen3 Reranker 8B · Tao 8K · Jina Clip V2 · Jina Reranker M0 · Jina Colbert V2 · GPT 4o Search Preview · GPT 4o Mini Search Preview · Jina Embeddings V3 · ERNIE 4.5 · ERNIE 4.5 Turbo VL · MiMo V2 Flash (free) · FLUX-1.1-pro · O3 Mini · Doubao Seed 1.6 · Doubao Seed 1.6 Flash · Doubao Seed 1.6 Lite · Doubao Seed 1.6 Thinking · Qwen3 30B A3B Instruct 2507 · Qwen3 30B A3B Thinking 2507 · Qwen2 VL 72B Instruct · Qwen2 VL 7B Instruct · CC Kimi For Coding · Gemini Embedding 001 · gpt-oss-120b · Qwen 3 235B A22B Thinking 2507 · Qwen/Qwen3-30B-A3B · Qwen/Qwen3-32B · Qwen3 32B · Qwen/Qwen3-14B · Qwen/Qwen3-8B · Embedding 2 · Embedding 3 · Gemini 2.5 Pro Preview 06-05 · Qwen/Qwen2.5-VL-72B-Instruct · O1 · O1 Pro · ByteDance-Seed/Seed-OSS-36B-Instruct · Doubao Seed 1.6 250615 · Doubao Seed 1.6 Flash 250615 · Doubao Seed 1.6 Thinking 250615 · Doubao Seed 1.6 Vision 250815 · Doubao 1.5 Thinking Pro · CC MiniMax M2 · deepseek-ai/DeepSeek-Prover-V2-671B · Gemini 2.5 Flash Preview Tts · Gemini 2.5 Pro Preview Tts · Gemma 3 12B It · Gemma 3 27B It · Gemma 3 4B It · Gemma 3n E4B It · Gemma 3 1B It · DeepSeek R1 Distill Llama 70B · GPT 4o Mini Tts · tngtech/DeepSeek-R1T-Chimera · O1 Preview · O1 Mini · GPT 4o 2024 11-20 · GPT 4o · GPT 4o Mini · AIHubMix Mistral Medium · ERNIE X1.1 Preview · Qwen/QwQ-32B · chutesai/Mistral-Small-3.1-24B-Instruct-2503 · ERNIE X1.1 Preview · MiniMaxAI/MiniMax-M1-80k · Qwen/Qwen2.5-VL-32B-Instruct · baidu/ERNIE-4.5-300B-A47B · Bge Large En · Bge Large Zh · Codestral · ERNIE 4.5 0.3b · ERNIE 4.5 Turbo 128K Preview · ERNIE X1 Turbo · Llama 3.3 70B · moonshotai/Kimi-Dev-72B · moonshotai/Moonlight-16B-A3B-Instruct · Nvidia Nemotron 3 Super 120B A12B · O1 Global · Qianfan Qi VL · Qwen2.5 VL 72B Instruct · tencent/Hunyuan-A13B-Instruct · unsloth/gemma-3-27b-it · gemini-exp-1206 · GPT 4o Zh · Qwen Qwq 32B · unsloth/gemma-3-12b-it · Qwen Max 0125 · BAAI/bge-large-en-v1.5 · BAAI/bge-large-zh-v1.5 · tencent/Hunyuan-MT-7B · Doubao Embedding Large Text 240915 · Kimi Thinking Preview · GPT 4o 2024 08-06 · Qwen Plus 2025 07-28 · Qwen Plus · stepfun-ai/step3 · Text Embedding V4 · AIHubMix Phi 4 Mini (reasoning) · Qwen Turbo · Aihub Phi 4 Multimodal Instruct · Qwen3 30B A3B · Aihub Phi 4 Mini Instruct · Aihub Phi 4 · Claude 3 Opus 20240229 · Dall E 3 · Doubao Embedding Text 240715 · Grok 3 Beta · Qwen3 14B · Grok 3 Fast · Qwen3 8B · deepseek-ai/DeepSeek-R1-Zero · Grok 3 Fast Beta · Grok 3 Mini · Qwen3 4B · Grok 3 Mini Beta · Qwen3 1.7b · Qwen3 0.6b · Alicloud Glm 5 · Command A 03 2025 · Grok 3 Mini Fast Beta · Qwen 3 32B · Qwen Turbo 2025 04-28 · Qwen Plus 2025 04-28 · THUDM/GLM-Z1-32B-0414 · THUDM/GLM-4.1V-9B-Thinking · Text Embedding 004 · THUDM/GLM-4-32B-0414 · THUDM/GLM-Z1-9B-0414 · THUDM/GLM-4-9B-0414 · CC Doubao Seed Code Preview · Doubao Seed Code Preview · deepseek-ai/Janus-Pro-7B · GLM Zero Preview · Qwen 3 235B A22B Instruct 2507 · Coding GLM 4.5 Air · Deepinfra Nvidia Nemotron 3 Nano 30B A3b2 · GLM 4.5 Air · Nvidia Llama 3.1 Nemotron 70B Instruct · Nvidia Llama 3.3 Nemotron Super 49B V1.5 · Nvidia Nemotron 3 Nano 30B A3B · Nvidia Nemotron Nano 12B V2 VL · Nvidia Nemotron Nano 9B V2 · O1 Preview 2024 09-12 · Qwen/QVQ-72B-Preview · Qwen/QwQ-32B-Preview · AIHubMix Mistral Large 2411 · AIHubMix Mistral Large 2407 · Grok 2 1212 · Llama 3.1 70B · Wan2.6 T2i · Bai Qwen3 VL 235B A22B Instruct · CC MiniMax M2 · CC DeepSeek V3 · CC DeepSeek V3.1 · CC ERNIE 4.5 300B A47B · CC Kimi Dev 72B · CC Kimi K2 Instruct · CC Kimi K2 Instruct 0905 · CC Kimi K2 Thinking · Computer Use Preview · GPT Image Test · grok-4.20-beta-0309-non-reasoning · Grok 4.20 Beta 0309 (reasoning) · Grok 4.20 Multi Agent Beta 0309 · Jina Reader · Jina Search · Llama3.1 8B · O1 2024 12-17 · Sf Kimi K2 Thinking · Doubao 1.5 Lite 32K · Doubao 1.5 Pro 256K · Doubao 1.5 Pro 32K · Doubao 1.5 Vision Pro 32K · Doubao Lite 128K · Doubao Lite 32K · Doubao Lite 4K · Doubao Pro 128K · Doubao Pro 256K · Doubao Pro 32K · Doubao Pro 4K · GPT-OSS-20B · Gryphe/MythoMax-L2-13b · MiniMax Text 01 · Mistral Large 2407 · Qwen/Qwen2-1.5B-Instruct · Qwen/Qwen2-57B-A14B-Instruct · Qwen/Qwen2-72B-Instruct · Qwen/Qwen2-7B-Instruct · Qwen/Qwen2.5-32B-Instruct · Qwen/Qwen2.5-72B-Instruct · Qwen/Qwen2.5-72B-Instruct-128K · Qwen/Qwen2.5-7B-Instruct · Qwen/Qwen2.5-Coder-32B-Instruct · Qwen3 235B A22B Thinking 2507 · WizardLM/WizardCoder-Python-34B-V1.0 · AIHubMix Phi 3.5 MoE Instruct · AIHubMix Phi 3.5 Mini Instruct · AIHubMix Phi 3.5 Vision Instruct · AIHubMix Phi 3 Medium 128K · AIHubMix Phi 3 Medium 4K · AIHubMix Phi 3 Small 128K · AIHubMix Codestral 2501 · AIHubMix Cohere Command R · AIHubMix Jamba 1.5 Large · AIHubMix Llama 3.1 405B Instruct · AIHubMix Llama 3.1 70B Instruct · AIHubMix Llama 3.1 8B Instruct · AIHubMix Llama 3.2 11B Vision · AIHubMix Llama 3.2 90B Vision · AIHubMix Llama 3 70B Instruct · AIHubMix Mistral Large · AIHubMix Command R 08 2024 · AIHubMix Command R Plus · AIHubMix Command R Plus 08 2024 · Alicloud Deepseek V3.2 · Alicloud Glm 4.7 · Alicloud Kimi K2 Thinking · Alicloud Minimax M2.5 · Anthropic Opus 4.6 · Azure Deepseek V3.2 · Azure Deepseek V3.2 Speciale · Cbs Glm 4.7 · Cerebras Llama 3.3 70B · Chatglm_lite · Chatglm_pro · Chatglm_std · Chatglm_turbo · Claude 2 · Claude 2.0 · Claude 2.1 · Claude 3 Haiku 20240229 · Claude 3 Haiku 20240307 · Claude 3 Sonnet 20240229 · Claude Instant 1 · Claude Instant 1.2 · Code Davinci Edit 001 · Cogview 3 · Cogview 3 Plus · Command · Command Light · Command Light Nightly · Command Nightly · Command R · Command R 08 2024 · Command R Plus · Command R Plus 08 2024 · Davinci · Davinci 002 · Deepinfra Llama 3.1 8B Instant · Deepinfra Llama 3.3 70B Instant Turbo · Deepinfra Llama 4 Maverick 17B 128e Instruct · Deepinfra Llama 4 Scout 17B 16e Instruct · deepseek-ai/DeepSeek-Coder-V2-Instruct · deepseek-ai/DeepSeek-R1-Distill-Llama-70B · deepseek-ai/DeepSeek-R1-Distill-Llama-8B · deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B · deepseek-ai/DeepSeek-R1-Distill-Qwen-14B · deepseek-ai/DeepSeek-R1-Distill-Qwen-32B · deepseek-ai/DeepSeek-R1-Distill-Qwen-7B · deepseek-ai/DeepSeek-V2-Chat · deepseek-ai/DeepSeek-V2.5 · deepseek-ai/deepseek-llm-67b-chat · deepseek-ai/deepseek-vl2 · Distil Whisper Large V3 En · Doubao 1.5 Thinking Vision Pro 250428 · Dubbing v1 · Dubbing v2 · Eleven Voice Isolator · Eleven English v2 (Speech to Speech) · Eleven Flash v2 · Eleven Flash v2.5 · Eleven Multilingual v2 (Speech to Speech) · Eleven Multilingual v2 · Eleven SFX v3 · Eleven v3 · Eleven v4 · Eleven v4 Turbo · Fx Flux 2 Pro · gemini-2.5-pro-exp-03-25 · gemini-embedding-exp-03-07 · gemini-exp-1114 · gemini-exp-1121 · Gemini Pro · Gemini Pro Vision · Gemma 7B It · GLM 3 Turbo · GLM 4 · GLM 4 Flash · GLM 4 Plus · GLM 4.5 Airx · GLM 4 Vision · GLM 4 Vision Plus · Google Gemma 3 12B It · Google Gemma 3 27B It · Google Gemma 3 4B It · google/gemini-exp-1114 · google/gemma-2-27b-it · GPT 3.5 Turbo · GPT 3.5 Turbo 1106 · GPT 3.5 Turbo 16K · GPT 3.5 Turbo Instruct · GPT 4 · GPT 4 0613 · GPT 4 1106 Preview · GPT 4 Turbo · GPT 4 Turbo 2024 04-09 · GPT 4o 2024 05-13 · GPT 4o Mini 2024 07-18 · GPT 5.6 Sol Pro · gpt-oss-20b · Grok 2 Vision 1212 · Grok Vision Beta · Groq Llama 3.1 8B Instant · Groq Llama 3.3 70B Versatile · Groq Llama 4 Maverick 17B 128e Instruct · Groq Llama 4 Scout 17B 16e Instruct · Jina Embeddings V2 Base Code · Laguna S 2.1 · Laguna Xs 2.1 · Learnlm 1.5 Pro Experimental · Ling 3.0 Flash · Llama 3.1 405B Instruct · Llama 3.1 405B (reasoning) · Llama 3.1 70B Versatile · Llama 3.1 8B Instant · Llama 3.2 11B Vision Preview · Llama 3.2 1B Preview · Llama 3.2 3B Preview · Llama 3.2 90B Vision Preview · Llama 3.3 70B Instruct · Llama2 70B 4096 · Llama2 70B 40960 · Llama2 7B 2048 · Llama3 70B 8192 · Llama3 8B 8192 · Llama3 Groq 70B 8192 Tool Use Preview · Llama3 Groq 8B 8192 Tool Use Preview · meta-llama/Llama-3.2-90B-Vision-Instruct · meta-llama/llama-3.1-405b-instruct:free · meta-llama/llama-3.1-70b-instruct:free · meta-llama/llama-3.1-8b-instruct:free · meta-llama/llama-3.2-11b-vision-instruct:free · meta-llama/llama-3.2-3b-instruct:free · meta/llama-3.1-405b-instruct · meta/llama3-8B-chat · mistralai/mistral-7b-instruct:free · Moonshot V1 128K · Moonshot V1 128K Vision Preview · Moonshot V1 32K · Moonshot V1 32K Vision Preview · Moonshot V1 8K · Moonshot V1 8K Vision Preview · Eleven Music v2 · nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 · O1 Mini 2024 09-12 · Omni Moderation · Qwen Flash · Qwen Flash 2025 07-28 · Qwen Long · Qwen Max · Qwen Max Longcontext · Qwen Plus · Qwen Turbo · Qwen Turbo 2024 11-01 · Qwen2.5 14B Instruct · Qwen2.5 32B Instruct · Qwen2.5 3B Instruct · Qwen2.5 72B Instruct · Qwen2.5 7B Instruct · Qwen2.5 Coder 1.5b Instruct · Qwen2.5 Coder 7B Instruct · Qwen2.5 Math 1.5b Instruct · Qwen2.5 Math 72B Instruct · Qwen2.5 Math 7B Instruct · Qwen3 235B A22B 2507 · Qwen3.8 27B · Scribe v2 · Scribe v2 Realtime · Solar Pro4 · Step 2 16K · Text Ada 001 · Text Babbage 001 · Text Curie 001 · Text Davinci 002 · Text Davinci 003 · Text Davinci Edit 001 · Text Embedding 3 Large · Text Embedding 3 Small · Text Embedding Ada 002 · Text Embedding V1 · Text Moderation 007 · Text Moderation · Text Moderation Stable · Text Search Ada Doc 001 · Tts 1 · Tts 1 1106 · Tts 1 Hd · Tts 1 Hd 1106 · Whisper 1 · Whisper Large V3 · Whisper Large V3 Turbo · DeepSeek R1 Distill Qianfan Llama 8B · Doubao 1.5 Pro 256K 250115 · Doubao 1.5 Pro 32K 250115 · GPT 4o 2024 08-06 Global · GPT 4o Mini Global · Meta Llama 3 70B · Meta Llama 3 8B · O3 Global · O3 Mini Global · O3 Pro Global · Qianfan Chinese Llama 2 13B · Qianfan Llama VL 8B · Inkling 2 Small (free) · Crouton Alpha (free) · Qwen3.8 Flash (free) · Qwen3.8 Max (free) · Gemini 3.8 Flash (free) · GPT Transcribe · Union Alpha (free) · Hy3 (free) · Gemini 3.7 Flash (free) · MiniMax M2.7 (free) · Ox Alpha · Ling 3.0 Tiny (free) · Ling 3.0 Flash (free) · Qwen3.8 Max Preview · Gemini 3.5 Flash Lite (free) · Gemini 3.6 Flash (free) · GPT Oss 20B (free) · Nemotron Nano 9B V2 (free) · Hy3 Preview · Nemotron Nano 12B V2 VL (free) · Nemotron 3 Super 120B A12B (free) · Nemotron 3.5 Content Safety (free) · Laguna Xs 2.1 (free) · Laguna S 2.1 (free) · MiMo V2.5 · MiMo V2.5 Pro · Qwen3.6 Max Preview · Nemotron 3 Nano 30B A3B (free) · Coding Xiaomi Mimo V2.5 · Coding Xiaomi Mimo V2.5 Pro · GPT 5.5 (free) · Coding Xiaomi Mimo V2 Omni · Coding Xiaomi Mimo V2 Pro · GPT Image 2 (free) · Xiaomi Mimo V2 Omni (free) · Xiaomi Mimo V2 Pro (free) · Xiaomi Mimo V2.5 (free) · Xiaomi Mimo V2.5 Pro (free) · Gemini 3.1 Flash Image Preview (free) · MiMo V2 Omni · MiMo V2 Pro · Xing4.0 29B A4B (free) · Gemini 3 Flash Preview (free) · GPT 4.1 (free) · GPT 4.1 Mini (free) · GPT 4.1 Nano (free) · GPT 4o (free) · Veo 3.1 Lite Generate Preview · Doubao Seed 1.8 · MiMo V2 Flash · DeepSeek V3.2 Thinking · Qwen3 VL Flash · Qwen3 VL Flash 2026 01-22 · GPT 4o Audio Preview · Gemini 2.5 Flash · Gemini 2.5 Flash Preview 09 2025 · Gemini 2.5 Flash Lite · Gemini 2.5 Flash Lite (no think) · Gemini 2.5 Flash Lite Preview 09 2025 · Gemini 2.5 Flash Lite Preview 09 2025 (no think) · Gemini 2.5 Flash (no think) · DeepSeek V3 Fast · Imagen 4.0 · Imagen 4.0 Fast Generate 001 · Imagen 4.0 Generate 001 · Imagen 4.0 Ultra Generate 001 · Imagen 4.0 Ultra · DeepSeek-OCR · grok-4-fast-non-reasoning · Grok 4 Fast (reasoning) · Kimi K2 0711 · Qwen3 VL 235B A22B Instruct · Qwen3 VL 235B A22B Thinking · Qwen3 VL 30B A3B Instruct · Qwen3 VL 30B A3B Thinking · Veo 3.1 Fast Generate Preview · Veo 3.1 Generate Preview · Qwen3 Max · Qwen3 Next 80B A3B Instruct · Claude 3.7 Sonnet · Veo 2.0 Generate 001 · Kat Dev · V3 · V_2 · V_2_TURBO · V_2A · V_2A_TURBO · V_1 · V_1_TURBO · Sonar · Grok 3 · GPT 4 32K · Llama 3.1 Sonar Huge 128K Online · Llama 3.1 Sonar Large 128K Online · DESCRIBE · UPSCALE · Baichuan3 Turbo · Baichuan3 Turbo 128K · Baichuan4 · Baichuan4 Air · Baichuan4 Turbo · DeepSeek V3 · Stable Diffusion 3.5 Large · Dall E 2 · DeepSeek V3 · google/gemma-2-9b-it:free · GPT 3.5 Turbo 0301 · GPT 3.5 Turbo 0613 · GPT 3.5 Turbo 16K 0613 · GPT 4 0125 Preview · GPT 4 0314 · GPT 4 32K 0314 · GPT 4 32K 0613 · GPT 4 Turbo Preview · GPT 4 Vision Preview · L3.1 Euryale 70B · Llama 3.1 Sonar Small 128K Online · Mercury 2.5 · Wan3.0 Video (free) · Wan3.0 Video Prime (free) · Yi Large · Yi Large Rag · Yi Large Turbo · Yi Lightning · Yi Medium · Yi VL Plus