Explore 854 AI models with transparent per-token pricing — ChatGPT, Claude, Gemini, DeepSeek, Qwen and more, all through one unified API.
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
OpenAI (133) · Anthropic (28) · Google (83) · Grok (26) · Qwen (141) · DeepSeek (38) · Z.AI (65) · ByteDance (46) · Llama (50) · AI21 (2) · Microsoft (14) · Cohere (19) · Mistral (10) · Yi (6) · Moonshot AI (34) · StepFun (4) · Nvidia (17) · Minimax (31) · Perplexity (4) · Baichuan (5) · Ideogram (9) · Jina AI (13) · Stable diffusion (1) · Hunyuan (5) · Baidu (23) · Flux (5) · Meituan (2) · Xiaomi (14) · InclusionAI (7) · BAAI (5) · Agnes (4) · Meta (3) · KLing (2) · Poolside (2) · Dots Studio (1) · Liquid (1) · Stealth (1)
AIHubMix Smart Router: Fill in the model name as auto, and the gateway will automatically…
GLM-5.3 is Z.AI’s coding and agentic reasoning model, built for complex software…
GLM-5.3 is Z.ai’s reasoning model for coding and agentic workflows, designed for complex…
Gemini 3.7 Flash is Google’s natively multimodal reasoning model for coding, agents, web…
Developed by Stealth, Ox Alpha is a reasoning model designed for coding, sustained…
Dots3-Note Preview is an open-weight mixture-of-experts model developed by Dots Studio…
Gemini 3.7 Flash free version: Free model resources are limited and provided only for…
GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks. With a truly usable…
DeepSeek-V4-Flash-0731(deepseek-v4-flash-0731) is an open-source MoE large language model…
DeepSeek’s officially released new multimodal visual-understanding model…
DeepSeek V4 Pro 0813 is DeepSeek’s high-performance general-purpose reasoning and agent…
Grok 4.6 is xAI’s (SpaceXAI) flagship multimodal reasoning model for coding, long-running…
DeepSeek V4 Flash 0731 Fast is a high-speed deployment of DeepSeek’s agentic model…
MAI-Thinking-1 is Microsoft’s first inference model in the MAI series, built for…
GPT-5.6 Sol (limited-time 50% off) is OpenAI’s frontier reasoning model for complex…
Seedance 2.5 is ByteDance Seed’s next-generation unified multimodal audio-video…
GPT-5.6 Luna is designed for cost-sensitive, high-volume workloads. It roughly…
GPT‑5.6 Sol sets a new standard for both intelligence and efficiency, achieving…
GPT-5.6 Terra is designed for workloads that balance intelligence and cost. It roughly…
Agnes 2.5 Flash is Agnes AI’s fast and efficient language model, an upgraded, fully…
Agnes 2.5 Pro is Agnes AI’s paid inference model and the commercially stable version of…
Agnes 2.5 Pro Alpha is Agnes AI’s paid inference model, suitable for advanced coding…
Agnes Image 2.1 Flash is Agnes AI’s high-performance image generation and image editing…
Grok 4.5 was trained on datasets spanning knowledge in coding, science, engineering, and…
LFM-2.5-2.6B is a compact reasoning model developed by Liquid, featuring a generous…
MiniMax H3 (minimax-h3) is a general-purpose omni-modal generation model developed by the…
Muse Glimmer 30B is a dense causal language model distilled from Muse Spark, designed for…
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, featuring…
Qwen3.8-2.4T-A95B is Alibaba’s most powerful Qwen model to date. It is a…
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and…
Gemini 3.6 Flash provides sustained frontier-level intelligence optimized for real-world…
Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, featuring 1.3B active…
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, featuring…
Qwen Image 3.0(qwen-image-3.0) is an image generation and editing model developed by…
Qwen Image 3.0 Pro (qwen-image-3.0-pro) is Alibaba Cloud Qwen’s flagship image generation…
Qwen 3.8 Max(qwen3.8-max) is Alibaba Cloud’s flagship native vision-language model, built…
Claude Sonnet 5 is the next generation of Anthropic's Sonnet model family. It is a…
Kimi K3 is Kimi’s flagship model for long-horizon coding and end-to-end knowledge work…
Developed by Inclusionai, ling-3.0-flash-free is a 124B-parameter Mixture-of-Experts…
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It…
Qwen 3.8 Max Preview(Qwen3.8-Max-Preview) is the latest-generation foundation model in…
Google's newest, most compact, and most cost-effective image generation and editing…
Gemini 3.5 Flash-Lite is a low-latency, cost-effective multimodal model optimized for…
Gemini 3.5 Flash-Lite free version: Free model resources are limited and provided only…
Gemini 3.6 Flash free version: Free model resources are limited and provided only for…
GLM-5.2-Fast-Preview is the high-speed version of Zhipu AI’s flagship model GLM-5.2…
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It…
qwen-audio-3.0-tts-flash is a high-performance speech synthesis large model optimized for…
qwen-audio-3.0-tts-plus is a high-performance speech synthesis large model designed for…
Anthropic's most capable widely released model, for the most demanding reasoning and…
jina-reranker-v3.5 is a 0.6B-parameter multilingual listwise document reranker and a…
Claude Opus 4.8 is Anthropic’s newest and most powerful publicly available model. It is…
The Hy3 official version is honed for real-world business scenarios, using a…
A new generation of large models moving toward production-grade intelligence…
Balancing performance and cost, comprehensively upgrading coding, agent, and multimodal…
MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With…
Gemini 3.5 Flash provides sustained frontier-level intelligence optimized for real-world…
Fast coding model trained specifically for agentic coding workflows.
MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With…
MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With…
HappyHorse-1.1-I2V supports image-to-video generation, further enhancing visual texture…
HappyHorse-1.1-R2V supports reference-based video generation, further improving the…
HappyHorse-1.1-T2V supports text-to-video generation, further enhancing text semantic…
coding glm 5.2 free (coding-glm-5.2-free) is a free coding-focused API route offered by…
coding-kimi-k3-free is the open and free version of coding-kimi-k3. To maintain reliable…
gemini-3.1-flash-image (Nano Banana 2) features professional-grade visual intelligence…
Developed by OpenAI, gpt-oss-20b-free is an open-weight 21B parameter model released…
Kimi K2.7 Code is Kimi’s most intelligent Coding model, capable of completing programming…
High-Speed version of Kimi K2.7 Code model, with output speed of approximately 180…
Gemini-3-Pro-Image (Nano Banana Pro) is a high-performance image generation and editing…
GPT-4o Transcribe Diarize is an automatic speech recognition (ASR) model with built-in…
The gpt-audio model is OpenAI's first officially released (generally available) audio…
Using the Hunyuan Sheng 3D 3.1 model, it can generate higher-precision and higher-quality…
VIDEO 3.0 Omni: All-in-One Multimodal Input, Voice-Driven Characters, Direct Audio-Visual…
Kling Video O1 is a major unified multimodal video model launched by Kuaishou. It…
Designed for agent development scenarios, it natively supports tool invocation…
NVIDIA-Nemotron-Nano-9B-v2-free is a large language model trained from scratch by NVIDIA…
Hunyuan Hy3 preview is designed for agent workloads, adopting a MoE architecture with…
The MiniMax M3 is a flagship programming model built for real-world productivity. As a…
Developed by Nvidia, Nemotron-Nano-12B-V2-VL-Free is a 12-billion-parameter open…
The Qwen 3.7 series' mid-to-high cost-performance "Plus" model builds on strong text…
The Qwen 3.7 series' mid-to-high cost-performance "Plus" model builds on strong text…
step-3.7-flash is stepfun's flagship inference model, designed for high-complexity tasks…
The claude-opus-4-8-think model has adaptive thinking mode pre-enabled; the default…
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model built on a hybrid…
Developed by Nvidia, NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model…
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model featuring…
The Max model, the largest and most capable in the Qwen3.7 series, is currently offering…
GPT-image-2 is OpenAI's latest cutting-edge image generation model. Key value adds…
Developed by NVIDIA, Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal…
Currently, the special resources for this model are limited, but due to its popularity…
ERNIE 5.1 is the latest model in the Wenxin series, with comprehensive upgrades to its…
gemini-3.1-flash-lite is currently Google's latest and most cost-effective model…
gemini-3.1-flash-lite is currently Google's latest and most cost-effective model…
Grok 4.3 is amongst the leading models in intelligence and well priced when comparing to…
HappyHorse-1.0-I2V supports image-to-video generation, featuring highly faithful dynamic…
HappyHorse-1.0-R2V supports reference-guided video generation, offering more stable…
HappyHorse-1.0-T2V supports text-to-video generation, featuring highly faithful dynamic…
HappyHorse-1.0-Video-Edit supports video editing, allows editing videos via natural…
Developed by Cohere, north-mini-code-free is the debut model of the North family and…
GPT-5.5 raises the baseline for complex production workflows. It’s a strong fit for…
Please note: this model is extremely expensive and very slow. If a request fails due to…
Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poolside…
(This model currently points to the older 0423 version; if you need to request the latest…
(This model currently points to the older 0423 version; if you need to request the latest…
Gemma 4 31B Instruct is a 30.7B dense multimodal model developed by Google DeepMind that…
Cohere's stronger command model for multilingual agents and enterprise workflows
Seedream-5.0-pro is the latest image-creation model released by ByteDance. The model…
ERNIE 5.0 is the next-generation natively multimodal foundation model in the ERNIE…
Kimi K2.6 is Kimi's latest and most intelligent model, with stronger and more stable…
Laguna S 2.1 is the latest coding agent model from Poolside, featuring an impressive…
The Max model Preview version, the largest and most capable model in the Qwen3.6 series…
MiMo-V2.5 is a native, fully multimodal large model designed for agent scenarios; it can…
MiMo-V2.5-Pro is Xiaomi's most powerful model to date. In areas such as general agent…
Claude Opus 4.7 is Anthropic’s latest and most powerful publicly available model. It has…
The claude-opus-4-7-think model has adaptive thinking mode pre-enabled; the default…
GPT Chat Latest points to OpenAI's stable API alias chat-latest that always resolves to…
NVIDIA Nemotron 3 Nano 30B A3B is a highly efficient small language Mixture of Experts…
The Qwen3.6 series 27B native vision-language Dense model. Compared with the 3.5-27B, the…
Qwen 3.6, the native vision-language Plus series model, demonstrates outstanding…
Qwen 3.6, the native vision-language Plus series model, demonstrates outstanding…
Rerank 4 is the most advanced set of reranker models available today, purpose-built to…
Rerank 4 is the most advanced set of reranker models available today, purpose-built to…
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model developed by…
Grok 4.2 is xAI’s latest large language model, built for strong reasoning, multimodal…
Grok 4.2 is xAI’s latest large language model, built for strong reasoning, multimodal…
The Qwen-Image-2.0 series accelerated models integrate image generation and image…
The Qwen-Image-2.0 full-powered models achieve the integration of image generation and…
coding-minimax-m3-free is a free and open version offered by AIHubMix specifically for…
The Doubao large-model team has launched a new-generation professional-grade multimodal…
Seedance 2.0 fast is a next-generation multimodal video-creation model launched by the…
Seedance 2.0 mini is a next-generation, cost-effective video generation model launched to…
GLM-5.1 is Zhipu's latest flagship model, with greatly enhanced coding capabilities and…
GLM-Image is Zhipu AI's new flagship image generation model. The model is trained…
Qwen 3.6, the native vision-language Plus series model, demonstrates outstanding…
Wanxiang 2.7 — image-to-video: performance capabilities comprehensively upgraded…
Wanxiang 2.7 — reference-driven video generation: more stable references for characters…
Wanxiang 2.7 — text-to-video: performance capabilities comprehensively upgraded…
Wanxiang 2.7 — video editing: edit videos using natural-language commands, supporting…
A Mixture-of-Experts model that activates only 4B parameters per inference,delivering…
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text…
GPT-5.4 is our frontier model for complex professional work.Reasoning.effort supports…
Wanxiang 2.7 — image generation and editing: supports text-to-image, text-to-multi-image…
Wanxiang 2.7 — image generation and editing: supports text-to-image, text-to-multi-image…
Claude Sonnet 4.6 delivers frontier intelligence at scale—built for coding, agents, and…
Only supports OpenAI-compatible formats.
Only supports OpenAI-compatible formats.
Doubao Coding model optimized for real-world programming environments that can reliably…
Doubao Coding model optimized for real-world programming environments that can reliably…
gemini-3.1-flash-image-preview (Nano Banana 2) features professional-grade visual…
Gemini 3.1 Pro Preview is designed to further optimize the performance and reliability of…
gemini-3.1-pro-preview-customtools For users who build applications mixing bash and…
Gemini-3.1-pro-preview-search integrates Google's official search functionality; the…
GPT-5.4 mini is a faster, more efficient model that inherits the advantages of GPT-5.4…
GPT-5.4 nano is designed for tasks where speed and cost are most important, such as…
This free model API comes from the OpenAI model deployed on Azure. To prevent abuse, the…
The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that…
Claude sonnet 4.6 does not enable reasoning mode by default. To access its deep reasoning…
Only supports OpenAI-compatible formats.
Only supports OpenAI-compatible formats.
GPT-5.3Chat refers to the GPT-5.3 snapshot currently used in ChatGPT and is optimized for…
GPT-5.3-Codex is optimized for agentic coding tasks in Codex or similar environments…
This free model API comes from the OpenAI model deployed on Azure. To prevent abuse, the…
The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that…
The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that…
The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that…
The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that…
The Qwen3.5 native vision-language Flash series models are designed with a hybrid…
Doubao flagship all-purpose general model, targeting complex reasoning and long-chain…
GPT-5.4 supports configurable reasoning effort only through the /responses endpoint. To…
GPT-5.4 supports configuring reasoning strength only through the /responses endpoint. To…
Please note: this model is extremely expensive and very slow. If a request fails due to…
The Qwen3 series is a next-generation code-generation model with results close to…
xiaomi-mimo-v2-omni-free is the open free version of xiaomi-mimo-v2-omni. To maintain…
xiaomi-mimo-v2-pro-free is the open free version of xiaomi-mimo-v2-pro. To maintain…
xiaomi-mimo-v2.5-free is the open free version of xiaomi-mimo-v2.5. To maintain reliable…
xiaomi-mimo-v2.5-pro-free is the open free version of xiaomi-mimo-v2.5-pro5. To maintain…
Claude Opus 4.6 is Anthropic’s latest state-of-the-art reasoning model. It features an…
coding-glm-5.1-free is the open and free version of coding-glm-5.1. To maintain reliable…
coding-minimax-m2.7-free is a free and open version offered by AIHubMix specifically for…
GLM-5 is an advanced, open-source large language model designed for developers tackling…
GLM-5V-Turbo is Zhipu's first multimodal coding foundation model, built for visual…
MiniMax M2.7 can autonomously build complex Agent Harnesses and, leveraging capabilities…
Claude Opus 4.6 does not enable reasoning mode by default. To access its deep reasoning…
coding-glm-5-free is the open and free version of coding-glm-5. To ensure stable service…
coding-glm-5-turbo-free is the open and free version of coding-glm-5-turbo. To ensure…
coding-minimax-m2.5-free is a free and open version offered by AIHubMix specifically for…
The Doubao 2.0 series is a coding model optimized for real programming environments…
Doubao Coding model optimized for real-world programming environments that can reliably…
Doubao 2.0 series is designed for low-latency, high-concurrency, and cost-sensitive…
gemini-3-flash-preview is Google's latest released, most balanced model, excelling in…
Gemini-3-flash-preview-search integrates Google's official search functionality; the…
GLM-5-Turbo is a foundational model deeply optimized for the OpenClaw scenario. From the…
Supports Claude native interface, can be directly requested in Claude Code.
Claude Opus 4.5 is Anthropic’s latest frontier reasoning model, optimized for complex…
Claude Opus 4.5 does not enable reasoning mode by default. To access its deep reasoning…
Cohere’s Embed 4 is a multilingual multimodal embedding model. It is capable of…
The Ernie-image-Turbo model is an 8-step distilled version of the Ernie-image model, also…
This model is the free trial version of gemini-3.1-flash-image-preview (officially…
MiMo-V2-Omni is designed for complex real-world multimodal interaction and execution…
Xiaomi MiMo-V2-Pro is built for high-intensity agent work scenarios in the real world. It…
Command A is Cohere most performant model to date, excelling at tool use, agents…
gemini-3-flash-preview-free is the free, publicly available version of…
This free model API comes from the OpenAI model deployed on Azure. To prevent abuse, the…
This free model API comes from the OpenAI model deployed on Azure. To prevent abuse, the…
This free model API comes from the OpenAI model deployed on Azure. To prevent abuse, the…
This free model API comes from the OpenAI model deployed on Azure. To prevent abuse, the…
GLM-4.7 is Zhiyuan's latest flagship model. GLM-4.7 enhances coding capabilities…
Veo 3.1 is Google's state-of-the-art model for generating high-fidelity, 8-second 720p…
The glm-4.7-flash free model has usage restrictions to ensure stable service operation: a…
coding-glm-4.7-free is the open and free version of coding-glm-4.7. To ensure stable…
The Doubao video generation model Seedance 1.5 Pro, as a world-leading video generation…
Seedance 1.0 Pro is a foundational video-generation model that supports multi-shot…
Seedance 1.0 Pro Fast is a comprehensive model that delivers rock-bottom prices and peak…
Gemini-3-Pro-Image-Preview (Nano Banana Pro) is a high-performance image generation and…
A Mixture-of-Experts model that activates only 4B parameters per inference,delivering…
GPT-5.2-Codex is an upgraded version of GPT-5.2, optimized for agentic coding tasks in…
Doubao-Seedream-5.0-lite is the latest image-creation model released by ByteDance. For…
GPT Image 1.5 is a new image generation model powered by OpenAI’s flagship visual…
GPT-5.2 is an advanced general-purpose model that improves on GPT-5.1 with more reliable…
GPT-5.2Chat refers to the GPT-5.2 snapshot currently used in ChatGPT and is optimized for…
GPT-5.2 supports configurable reasoning effort only through the /responses endpoint. To…
GPT-5.2 supports configuring reasoning strength only through the /responses endpoint. To…
GPT-5.2 pro is available in the Responses API only to enable support for multi-turn model…
GPT-5 is OpenAI’s most advanced language model, designed for complex tasks that require…
GPT-5.1-Codex-Max is a frontier programming model built for the agent-driven era. Powered…
Doubao's strongest multimodal Agent model Seed1.8 has powerful multimodal capabilities…
GPT-5.1 Chat refers to the GPT-5.1 snapshot currently used in ChatGPT and is optimized…
GPT-5.1-Codex is a version of GPT-5 optimized for agentic coding tasks in Codex or…
GPT-5.1 Codex mini is a smaller, more cost-effective, less-capable version of…
Claude Haiku 4.5 is a fast, affordable, and highly capable AI model, excelling at coding…
Sonnet 4.5 is the best model in the world for agents, coding, and computer usage. It is…
Claude Sonnet 4.5 does not enable reasoning mode by default. To access its deep reasoning…
Grok 4.20 is our newest flagship model with industry-leading speed and agentic tool…
Mistral Large 3 is a MoE model with 67.5B total parameters and 41B active parameters…
Supports Claude native interface, can be directly requested in Claude Code.
Supports Claude native interface, can be directly requested in Claude Code.
Gemini 2.5 Flash Image (Nano-Banana) is a state-of-the-art image generation and editing…
Grok 4.1 is a new conversational model with significant improvements in real-world…
Grok 4.1 is a new conversational model with significant improvements in real-world…
Grok 4.1 is a new conversational model with significant improvements in real-world…
kimi-for-coding-free is a free and open version offered by AIHubMix specifically for Kimi…
MiMo-V2-Flash is a mixture of experts (MoE) language model with a total of 309 billion…
musesteamer-air-image is a text-to-image model developed by the Baidu Search team aimed…
This model has been removed from the platform.
GPT-5 is OpenAI’s most advanced general-purpose model, delivering major improvements in…
DeepSeek-V3.2 is an efficient large language model equipped with DeepSeek Sparse…
DeepSeek-V3.2 is an efficient large language model equipped with DeepSeek Sparse…
GPT-5-Codex is a version of GPT-5 optimized for autonomous coding tasks in Codex or…
DeepSeek-V3.1 non-thinking mode has now been updated to the DeepSeek-V3.1-Terminus…
Thinking mode of DeepSeek-V3.1; DeepSeek V3.1 is a text generation model provided by…
GPT-5 pro uses more compute to think harder and provide consistently better…
GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined…
GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, designed specifically…
GPT-5 Chat points to the GPT-5 snapshot currently used in ChatGPT. GPT-5 is our…
Opus 4.1 is an upgraded version of Claude Opus 4, with improvements mainly in agent…
Only supported through requests to the v1/responses interface. o3-deep-research is OpenAI…
Kimi K2.5 is the smartest model of Kimi to date, achieving open-source state-of-the-art…
The snapshot version of the Tongyi Qianwen 3 series Max model is from January 23, 2026…
The Qwen3 series of compact visual-understanding models achieves an effective fusion of…
The Qwen3 series of compact visual-understanding models achieves an effective fusion of…
The Qwen3 series visual understanding model achieves an effective fusion of thinking and…
The MiniMax M2.5 is a flagship programming model built for real-world productivity. As a…
• Same performance as minimax-m2.5 • Significantly faster inference
Seedream 4.5 is ByteDance's latest multimodal image model, integrating capabilities such…
Sora-2 is the next-generation text-to-video model evolved from Sora, optimized for higher…
Supports Claude native interface, can be directly requested in Claude Code.
coding-minimax-m2.1-free is a free and open version offered by AIHubMix specifically for…
OpenAI voice input and output model, with prices consistent with the official ones. For…
openai声音输入输出模型，价格和官方一致，暂时只展示文字部分价格，声音价格见openai官网；后台扣费和官方一致
MiniMax-M2.1 redefines efficiency for intelligent agents. It is a compact, fast, and…
OpenAI o3 is a powerful model across multiple domains, setting a new standard for coding…
Wan 2.6 - Text-to-Video generation features intelligent storyboard scheduling supporting…
Wan 2.6 - Text-to-Video generation features intelligent storyboard scheduling supporting…
coding-glm-4.6-free is the open and free version of coding-glm-4.6. To ensure stable…
coding-minimax-m2 is a free and open version offered by AIHubMix specifically for MiniMax…
coding-minimax-m2-free is a free and open version offered by AIHubMix specifically for…
FLUX.2 is purpose-built for real-world creative production workflows. It delivers…
FLUX.2 is purpose-built for real-world creative production workflows. It delivers…
Gemini 2.5 Pro is an advanced reasoning model developed by Google, optimized for solving…
GLM-4.6 is Zhipu’s latest flagship model (total parameters 355B, activation parameters…
Zhipu's latest visual reasoning model achieves state-of-the-art visual understanding…
GLM-OCR is a lightweight professional OCR model with only 0.9B parameters, yet multiple…
kimi-for-coding-free is a free and open version offered by AIHubMix specifically for Kimi…
o3-pro This model only supports Requests API interface requests.The model's thinking time…
Qianfan-OCR-Fast is a multimodal large model specialized for OCR, trained primarily on…
Qianfan-OCR-Fast is a multimodal large model specialized for OCR, trained primarily on…
step-3.5-flash is stepfun's flagship inference model, designed for high-complexity tasks…
The newly upgraded Tongyi Wanxiang 2.2 text-to-video offers higher video quality. It…
Tongyi Wanxiang 2.5 - Text-to-Video Preview features a newly upgraded technical…
Tongyi Wanxiang 2.5 - Text-to-Video Preview, newly upgraded model architecture, supports…
gemini-2.5-pro-search integrates Google's official search functionality; the search…
Kimi K2 Thinking is Moonshot AI's most advanced open-source inference model to date…
Gemini 2.5 Flash is Google’s best model in terms of both performance and cost efficiency…
This latest 2.5 Flash model comes with improvements in two key areas we heard consistent…
GLM-4.5V is a vision-language foundational model designed for multimodal agent…
Gemini 2.5 Flash-Lite is a balanced model from Google, optimized for applications that…
Gemini 2.5 Flash-Lite is a balanced model from Google, optimized for applications that…
gemini-2.5-flash-lite latest preview version
gemini-2.5-flash-lite latest preview version
Gemini-2.5-flash defaults to thinking enabled; to disable thinking, request the name…
gemini-2.5-flash-search integrates Google's official search functionality; the search…
Gemini-2.5-flash-preview-05-20 is enabled by default for thinking; to disable it, request…
Gemini-2.5 Flash Preview 05-20 Search integrates Google's official search functionality…
V3 Ultra-Fast Version,The current price is a limited-time 50% discount and will return to…
Imagen 4 is a high-quality text-to-image model developed by Google, designed for strong…
Imagen 4 is a new-generation image generation model designed to balance high-quality…
Imagen 4 is a new-generation image generation model designed to balance high-quality…
Azure OpenAI’s gpt-image-1 image generation API offers both text-to-image generation and…
OpenAI image generation model gpt-image-1-mini Before use, please run pip install -U…
o4-mini is a remarkably smart model for its speed and cost-efficiency. This allows it to…
DeepSeek-OCR is a vision-language model launched by DeepSeek AI, focusing on optical…
Kimi-K2 is a MoE architecture foundational model with extremely powerful coding and agent…
DeepSeek-OCR is a vision-language model launched by DeepSeek AI, focusing on optical…
ERNIE 5.0 is the next-generation natively multimodal foundation model in the ERNIE…
Aihubmix supports the gemini-2.5-flash-image-preview model; you can add extra parameters…
The latest flagship multimodal model supports million-token context, with encoding…
Grok, their latest and greatest flagship model, offers unparalleled performance in…
Grok-4-fast is a cost-effective inference model developed by xAI that delivers…
Grok-4-fast is a cost-effective inference model developed by xAI that delivers…
Kimi-K2 is a MoE architecture foundational model with extremely powerful coding and agent…
Kimi-K2 is a MoE architecture foundational model with extremely powerful coding and agent…
The kimi-k2-turbo-preview model is a high-speed version of kimi-k2, with the same model…
PaddleOCR-VL is an advanced and efficient document parsing model specifically designed…
PP-StructureV3 is an efficient and comprehensive document parsing solution that can…
The Qwen3 series open-source models include hybrid models, thinking models, and…
The Qwen3 series open-source models include hybrid models, thinking models, and…
The Qwen3-VL series’ second-largest MoE model Instruct version offers fast response speed…
The Qwen3-VL series’ second-largest MoE model Thinking version offers fast response…
Veo 3.0 Generate Preview is an advanced AI video generation model that supports…
Veo 3.1 is Google's state-of-the-art model for generating high-fidelity, 8-second 720p…
Veo 3.1 is Google's state-of-the-art model for generating high-fidelity, 8-second 720p…
New model routing capability; request aihubmix-router to automatically route models based…
Lightweight, high-performance model with million-token context and near-flagship-level…
Ultra-lightweight model with million-token context, optimized for speed and low latency…
gemini-2.5-pro latest model
Supports high concurrency. The Gemini 2.5 Pro preview version is here, with higher…
Integrated with Google's official search function.
Integrated with Google's official search function.
Qwen3-Max-Preview is the latest preview model in the Qwen3 series. This version is…
The Tongyi Qianwen 3 series Max model has undergone special upgrades in intelligent agent…
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned model in the Qwen3-Next series…
Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that…
Qwen3-235B-A22B-Instruct-2507
The open-source thinking model based on Qwen3 has significantly improved in logical…
The code generation model based on Qwen3 has powerful Coding Agent capabilities…
The code generation model based on Qwen3 has powerful Coding Agent capabilities…
It has been automatically upgraded to the latest released version, 250324. Automatically…
Meituan has officially released and open-sourced LongCat-Flash-Chat, which utilizes an…
Integrated with Google's official search function.
A 3.8-billion-parameter general vector model (embedding model) for state-of-the-art…
A 3.8-billion-parameter general vector (embedding) model providing state-of-the-art…
Qwen3-235B-A22B is a massive 235B parameter Mixture-of-Experts (MoE) model that operates…
Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3…
The code generation model based on Qwen3 has powerful Coding Agent capabilities, excels…
The code generation model based on Qwen3 has powerful Coding Agent capabilities, excels…
The model provider is the Sophon platform. Qwen2.5-VL-72B-Instruct is the latest…
The new generation Wenxin model, Wenxin 5.0, is a native full-modal large model that…
Ling-1T is the first flagship non-thinking model in the “Ling 2.0” series, featuring 1…
Ring-1T is an open-source idea model with a trillion parameters released by the Bailing…
Based on the dense foundational model of the Qwen3 series, it is specifically designed…
Only supports v1/responses API calls.https://docs.aihubmix.com/en/api/Responses-API codex-…
Seedream 4.0 is a SOTA-level multimodal image creation model based on leading…
Embedding-V1 is a text representation model based on Baidu's Wenxin large model…
Wenxin 4.5 Turbo also has significant improvements in hallucination reduction, logical…
GLM-4.5-X is the high-speed version of GLM-4.5, offering powerful performance with a…
The GME-Qwen2VL series is a unified multimodal Embedding model trained based on the…
gte-rerank-v2 is a multilingual unified text ranking model developed by Tongyi Lab…
Ling-flash-2.0 is a language model from inclusionAI with a total of 100 billion…
Ling-mini-2.0 is a small-sized, high-performance large language model based on the MoE…
Ring-flash-2.0 is a high-performance thinking model deeply optimized based on the…
DeepSearch combines search, reading, and reasoning capabilities to pursue the best…
A general-purpose vector model with 3.8 billion parameters, used for multimodal and…
Multimodal multilingual document reranker, 131K context, 0.6B parameters, for visual…
Llama 4 Maverick is a high-capacity Mixture-of-Experts (MoE) model from Meta, featuring…
Llama 4 Scout is a highly efficient Mixture-of-Experts (MoE) model from Meta, activating…
Qwen-Image is a foundational image generation model in the Qwen series, achieving…
Qwen-Image-Edit is the image editing version of Qwen-Image. Based on the 20B Qwen-Image…
Qwen-Image-Edit is the image editing version of Qwen-Image. Based on the 20B Qwen-Image…
Based on the comprehensive upgrade of Qwen3, this flagship translation large model…
Based on the comprehensive upgrade of Qwen3, this flagship translation large model…
The Qwen3 Embedding model series is the latest proprietary model family from Qwen…
The Qwen3 Embedding model series is the latest proprietary model family from Qwen…
The Qwen3 Embedding model series is the latest proprietary model family from Qwen…
Based on the dense foundational model of the Qwen3 series, it is specifically designed…
Based on the dense foundational model of the Qwen3 series, it is specifically designed…
Based on the dense foundational model of the Qwen3 series, it is specifically designed…
tao-8k是由Huggingface开发者amu研发并开源的长文本向量表示模型，支持8k上下文长度，模型效果在C-MTEB上居前列，是当前最优的中文长文本embeddings模型…
Multi-modal Embeddings Model, multilingual, 1024-dimensional, 865M parameters.
Multimodal multilingual document reranker, 10K context, 2.4B parameters, for visual…
Multi-language ColBERT embeddings model, 560M parameters, used for embedding and…
DeepSeek R1 is a new open-source model with performance on par with OpenAI's o1 and…
Using the Chat Completions API, you can directly access the fine-tuned models and tool…
Using the Chat Completions API, you can directly access the fine-tuned models and tool…
Text Embeddings Model, multilingual, 1024-dimensional, 570M parameters.
Support for the thinking parameter through the original Claude SDK.
Wenxin Large Model 4.5 is a next-generation native multimodal foundational model…
The new version of the Wenxin Yiyan large model significantly improves capabilities in…
MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It adopts…
FLUX-1.1-pro is an AI image generation tool for professional creators and content…
OpenAI's latest fast inference model excels at STEAM tasks and offers exceptional…
Doubao-Seed-1.6 is a brand new multimodal deep reasoning model that supports four types…
Doubao-Seed-1.6-flash is an extremely fast multimodal deep thinking model, with TPOT…
Doubao-Seed-1.6-lite is a brand new multimodal deep reasoning model that supports…
The Doubao-Seed-1.6-thinking model has significantly enhanced reasoning capabilities…
Significantly improved performance on reasoning tasks, including logical reasoning…
Significantly improved performance on reasoning tasks, including logical reasoning…
The model provider is the Sophnet platform. Qwen2-VL-72B-Instruct is the latest iteration…
The model provider is the Sophnet platform. Qwen2-VL-7B-Instruct is the latest…
gpt-oss-120b is a 117B-parameter open-weight Mixture-of-Experts (MoE) language model from…
A text vector model that converts input text information into vector representations so…
A text vector model that converts input text into vector representations to work with a…
Google’s latest multimodal flagship model, combining exceptional coding and reasoning…
Qwen2.5-VL is a visual language model from the Qwen2.5 series, equipped with strong…
OpenAI's most powerful O-series model supports official cache hits that halve the input…
The o1 series of models are trained with reinforcement learning to think before they…
Seed-OSS is a series of open-source large language models developed by ByteDance's Seed…
Doubao-Seed-1.6 is a brand new multimodal deep reasoning model that supports four types…
Doubao-Seed-1.6-flash is an extremely fast multimodal deep thinking model, with TPOT…
The Doubao-Seed-1.6-thinking model has significantly enhanced reasoning capabilities…
Doubao-Seed-1.6-vision is a visual deep-thinking model that demonstrates stronger general…
Doubao-1.5 is a brand-new deep thinking model that excels in specialized fields such as…
Provided by chutes.ai DeepSeek Prover V2 is a 671B parameter model, speculated to be…
Gemini 2.5 Flash Preview TTS is a lightweight, low-latency text-to-speech model designed…
Gemini 2.5 Pro Preview TTS is a high-fidelity text-to-speech model designed for premium…
Gemma 3 models are multimodal, handling text and image input and generating text output…
Gemma 3 models are multimodal, handling text and image input and generating text output…
Gemma 3 models are multimodal, handling text and image input and generating text output…
Gemma 3n is a generative AI model optimized for use in everyday devices, such as phones…
Gemma 3 models are multimodal, handling text and image input and generating text output…
Provided by Groq, the DeepSeek-R1-Distill model is fine-tuned based on an open-source…
OpenAI’s latest TTS model, gpt-4o-mini-tts, uses the same API endpoint (/v1/audio/speech)…
Provided by chutes.ai DeepSeek-R1T-Chimera merges DeepSeek-R1’s reasoning strengths with…
Veo 2.0 is an advanced video generation model capable of producing high-quality videos…
The latest and most powerful inference model from OpenAI; AiHubMix uses both OpenAI and…
o1-mini is faster and 80% cheaper, and is competitive with o1-preview on coding tasks…
The latest version of the GPT-4o model; it is recommended to use this version, as it is…
GPT-4o (“o” stands for “omni”) is a new-generation multimodal model designed for more…
The lightweight version of GPT-4o, which is affordable and fast, suitable for handling…
Mistral Medium 3 is a SOTA & versatile model designed for a wide range of tasks…
The Wenxin large model X1.1 has made significant improvements in question answering, tool…
Mistral's latest open-source small model; provided by chutes.ai.
The Wenxin large model X1.1 has made significant improvements in question answering, tool…
MiniMax-M2 redefines efficiency for intelligent agents. It is a compact, fast, and…
MiniMax-M1 is an open-source large-scale hybrid attention model with 456B total…
Qwen2.5-VL-32B-Instruct is an advanced multimodal model from the Tongyi Qianwen team that…
ERNIE-4.5-300B-A47B is a large language model developed by Baidu based on a Mixture of…
bge-large-en, open-sourced by the Beijing Academy of Artificial Intelligence (BAAI), is…
bge-large-zh, open-sourced by the Beijing Academy of Artificial Intelligence (BAAI), is…
Mistral has launched a new code model - Codestral 25.01…
Wenxin Large Model 4.5 is a next-generation native multimodal foundational large model…
Wenxin 4.5 Turbo also shows significant enhancements in reducing hallucinations, logical…
Wenxin Large Model X1 possesses enhanced abilities in understanding, planning…
KAT-Dev (32B) is an open-source 32B parameter model specifically designed for software…
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and…
Kimi-Dev-72B is a new generation open-source programming large model that achieved a…
Provided by chutes.ai.
An open-source, efficient hybrid Mamba-Transformer MoE model that supports a context…
The Qianfan-QI-VL model is a proprietary image quality inspection and visual…
Strong capability in Chinese domain recognition, comparable to ChatGPT-4.0.
Hunyuan-A13B-Instruct has 8 billion parameters and can match larger models by activating…
Google's latest open-source model; provided by chutes.ai
Google's latest experimental model, currently Google's most powerful model.
BAAI/bge-large-en-v1.5 is a large English text embedding model and part of the BGE (BAAI…
BAAI/bge-large-zh-v1.5 is a large Chinese text embedding model and part of the BGE (BAAI…
BAAI/bge-reranker-v2-m3 is a lightweight multilingual reranking model. It is developed…
Hunyuan-MT-7B is a lightweight translation model with 7 billion parameters, designed to…
Fast and high-quality — top image quality in just 11 seconds per piece, with almost no…
The Ideogram AI drawing interface is now live. This model boasts powerful text-to-image…
The Ideogram AI drawing interface is now live. This model boasts powerful text-to-image…
The Ideogram AI drawing interface is now live. This model boasts powerful text-to-image…
The Ideogram AI drawing interface is now live. This model boasts powerful text-to-image…
V_1 is a text-to-image model in the Ideogram series. It delivers strong text rendering…
The Ideogram AI drawing interface is now live. This model boasts powerful text-to-image…
doubao-embedding-large-text-240915 Doubao Embedding is a semantic vectorization model…
Supports caching, with automatic halving of charges upon a cache hit.
The Tongyi Qianwen series balanced capability model has inference performance and speed…
The Qwen series models with balanced capabilities have inference performance and speed…
Step3 is a multimodal reasoning model released by StepFun. It uses a Mixture‑of‑Experts…
This is the Tongyi Laboratory's multilingual unified text vector model trained based on…
Phi-4-mini-reasoning is a lightweight open model designed for advanced mathematical…
The Qwen series model with the fastest speed and lowest cost, suitable for simple tasks…
Microsoft's latest model
Achieves effective integration of thinking and non-thinking modes, allowing mode…
Microsoft's latest model
Phi-4 is a state-of-the-art open model based on a combination of synthetic datasets…
Claude’s previous generation strongest model
dall-e-3 is an AI image generation model that converts natural language prompts into…
doubao-embedding-text-240715 Doubao Embedding is a semantic vectorization model developed…
Grok's latest model This model ID with beta has been officially taken offline. Using this…
Achieves effective integration of thinking and non-thinking modes, enabling mode…
Achieves effective integration of thinking and non-thinking modes, enabling mode…
Openly deployed by chutes.ai; inference with FP8; zero is the initial preliminary version…
Achieves effective integration of thinking and non-thinking modes, allowing mode…
This model ID with beta has been officially taken offline. Using this model…
Effectively integrates thinking and non-thinking modes, allowing mode switching during…
Effectively integrates thinking and non-thinking modes, allowing mode switching during…
GLM-5 is an advanced, open-source large language model designed for developers tackling…
Command A is Cohere most performant model to date, excelling at tool use, agents…
The Qwen3 series Turbo model effectively integrates thinking and non-thinking modes…
The Qwen3 series Plus model effectively integrates thinking and non-thinking modes…
GLM-Z1-32B-0414 is a reasoning-focused AI model built on GLM-4-32B-0414. It has been…
GLM-4.1V-9B-Thinking is an open-source Vision Language Model (VLM) jointly released by…
GLM-4-32B-0414 is a next-generation open-source model with 32 billion parameters…
GLM-Z1-9B-0414 is a small but powerful model in the GLM series, with only 9 billion…
GLM-4-9B-0414 is a lightweight model in the GLM family, with 9 billion parameters. It…
Janus-Pro deepseek最新发布图片生成模型；是一个新颖的自回归框架，统一了多模态理解和生成。它通过将视觉编码解耦为独立路径来解决以往方法的局限性，同时仍然利用单一的统…
Simply put, it is the intelligent enhanced version of O1.
The smartest version of GPT-4; OpenAI no longer offers it officially. All the 32k…
On February 22, 2025, this model will be officially discontinued. The Perplexity AI…
The latest Mistral Large 2 model is deployed on Azure.
On February 22, 2025, this model will be officially discontinued; Perplexity AI's…
This endpoint is used to describe an image. Supported image formats include JPEG, PNG…
The super-resolution upscale interface of the Ideogram AI drawing model is designed to…
The Qwen3 series open-source models include hybrid models, thinking models, and…
Grok 4.20 Beta is our latest flagship model, offering industry-leading speed and agent…
Grok 4.20 Beta is our latest flagship model, offering industry-leading speed and agent…
Grok 4.20 Beta is our latest flagship model, offering industry-leading speed and agent…
Doubao-1.5-lite, a brand-new generation of lightweight model, offers exceptional response…
Doubao-1.5-pro-256k, a fully upgraded version based on Doubao-1.5-Pro, delivers an…
Doubao-1.5-pro, a brand-new generation of flagship model, features comprehensive…
Doubao-1.5-vision-pro is a newly upgraded multimodal large model that supports image…
Stable Diffusion 3.5 Large, developed by Stability AI, is a text-to-image generation…
Phi-3.5-MoE 是一个轻量级的最先进开放模型，基于用于 Phi-3 的数据集构建——合成数据和经过筛选的公开可用文档，重点关注高质量、推理密集的数据。该模型支持多语言，并具…
Phi-3.5-mini is a lightweight, state-of-the-art open model built upon the dataset used…
Claude Opus 4.6 is Anthropic’s latest state-of-the-art reasoning model. It features an…
来自siliconflow开源部署，模型本身通过知识蒸馏得到的模型
来自siliconflow开源部署，模型本身通过知识蒸馏得到的模型
来自siliconflow开源部署，模型本身通过知识蒸馏得到的模型
Open source deployment from SiliconFlow, the model itself is obtained through knowledge…
Open source deployment from SiliconFlow, the model itself is obtained through knowledge…
Open source deployment from SiliconFlow, the model itself is obtained through knowledge…
Deep Thinking Image Understanding Visual Localization Video Understanding Tool…
Google’s latest experimental model, highly unstable, for experience only. It boasts…
GLM-4.5-AirX is the high-speed version of GLM-4.5-Air, with faster response times…
Since the GPT-3.5-turbo model has been officially deprecated, all requests targeting this…
gpt-oss-20b is a 21-billion parameter open-weight model released by OpenAI under the…
grok-2-vision-1212 is the latest vision model in the Grok family, delivering outstanding…
Model optimized for code and document search, 768-dimensional, 137M parameters.
On February 22, 2025, this model will be officially discontinued. The Perplexity AI…
Llama-3.1-Nemotron-Ultra-253B is a 253 billion parameter reasoning-focused language model…
Ignore the displayed price on the page; the actual charge for this model request is…