图像模型

tokenhub/image-demo

—

bailian/qwen-image-3.0

$0.03/张

Qwen-Image-3.0 是阿里巴巴 2026 年 8 月正式发布的生图模型, 支持文生图与参考图输入, 可精准渲染小至 10px 的文字与细节, 在图文一致性、复杂结构与画面质感上较前代全面提升。

bailian/qwen-image-3.0-pro

$0.04/张

Qwen-Image-3.0-Pro 是阿里巴巴 2026 年 8 月正式发布的生图旗舰模型 (Qwen-Image 3.0 系列高端档), 支持文生图与参考图输入, 可精准渲染小至 10px 的文字与细节, 在图文一致性、复杂结构、文字渲染与画面质感上全面领先。

openai/gpt-5.6-luna

$32.00/M

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.

openai/gpt-5.6-sol

$32.00/M

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.

openai/gpt-5.6-terra

$32.00/M

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, offering strong performance at roughly half the cost of Sol.

volcengine/doubao-seedream-5.0-pro

$0.05/张

Doubao-Seedream-5.0-pro是字节跳动2026年7月发布的图像创作旗舰模型。相比前代在图文匹配、结构合理性、文字渲染与画面美感等基础能力上全面提升，具备四大突破：复杂信息可视化、交互式精准编辑（点选/圈选/草图渲染/图层分离/多图融合）、真实影像与人像质感、原生多语种（十余种语言）输入生成。支持文生图、图生图、参考图一致性编辑，面向企业级专业视觉创作。

google/gemini-3.1-flash-lite-image

$30.00/M

Gemini 3.1 Flash Lite Image is Google's most cost-efficient image generation and editing model, supporting text-to-image, image editing, and multi-image composition. Outputs generated at 1K resolution across 14 aspect ratios, at the lowest price point in the Nano Banana family.

microsoft/mai-image-2.5-pro

$106.00/M

MAI-Image-2.5-Pro is the flagship of Microsoft's MAI image family, designed for complex compositions with strong object and character consistency, accurate material properties and coherent spatial reasoning. Best suited for photorealistic scenes, rich documentary-style imagery and demanding creative work. Supports text-to-image generation and image-to-image editing.

google/gemini-3-pro-image

$120.00/M

Nano Banana Pro is Google's most advanced image-generation and editing model, built on Gemini 3 Pro. GA release of gemini-3-pro-image-preview. It generates context-rich graphics from infographics and diagrams to cinematic composites, with 2K/4K output, multi-image blending, identity preservation, and localized edits.

google/gemini-3.1-flash-image

$60.00/M

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google's state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. GA release of gemini-3.1-flash-image-preview, combining advanced contextual understanding with fast, cost-efficient inference.

microsoft/mai-image-2.5

$47.00/M

MAI-Image-2.5 is Microsoft's image generation and editing model. It excels at precise, surgical edits with consistency - targeted object edits, layout adaptation, text updates and artifact cleanup - while preserving visual consistency across iterations. Supports text-to-image generation and image-to-image editing with free aspect ratios up to 1 megapixel.

microsoft/mai-image-2.5-flash

$26.00/M

MAI-Image-2.5-Flash is the low-latency variant of Microsoft's MAI image family, optimized for fast, high-volume image generation and editing. Produces diverse, coherent images across creative and design scenarios with median generation times several times faster than comparable models. Supports text-to-image generation and image-to-image editing.

openai/gpt-5.5

$32.00/M

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.

openai/gpt-image-2

$30.00/M

GPT-image-2 is OpenAI's latest cutting-edge image generation model. Key value adds include better performance, quality, editing controls, and face preservation. The model supports high input_fidelity and adding/removing one aspect of the image while retaining others. This model includes improvements in aspect ratio, resolution, and editing capabilities.

openai/gpt-5.4-mini

$32.00/M

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, while reducing latency and cost for large-scale deployments.

openai/gpt-5.4-nano

$32.00/M

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.

openai/gpt-5.4

$32.00/M

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.The model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.

openai/gpt-5.4-pro

$32.00/M

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs. Optimized for step-by-step reasoning, instruction following, and accuracy, GPT-5.4 Pro excels at agentic coding, long-context workflows, and multi-step problem solving.

volcengine/doubao-seedream-5.0-lite

$0.035/张

Doubao-Seedream-5.0-lite是字节跳动发布的最新图像创作模型。该模型首次搭载联网检索功能，能融合实时网络信息，提升生图时效性。同时，模型的聪明度进一步升级，能够精准解析复杂指令和视觉内容。此外，模型在世界知识广度、参考一致性及专业场景生成质量上均有增强，可更好地满足企业级视觉创作需求。

openai/gpt-5.1

$32.00/M

OpenAI's enhanced GPT-5.1 model with improved reasoning and multimodal capabilities. Features 256K context with better instruction following and coding performance.

openai/gpt-image-1.5

$32.00/M

GPT Image 1.5 is our latest image generation model, with better instruction following and adherence to prompts.

openai/gpt-5.2

$32.00/M

OpenAI's latest GPT-5.2 model with 512K context window. Most advanced capabilities including enhanced reasoning, full multimodal support, and web search integration.

volcengine/doubao-seedream-4.5

$0.04/张

Seedream 4.5 是字节跳动最新推出的图像多模态模型，整合了文生图、图生图、组图输出等能力，融合常识和推理能力。相比前代4.0模型生成效果大幅提升，具备更好的编辑一致性和多图融合效果，能更精准的控制画面细节，小字、小人脸生成更自然，图片排版、色彩更和谐，美感提升

google/gemini-2.5-flash-image

$30.00/M

Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations.

openai/gpt-5

$32.00/M

OpenAI's next-generation flagship model with 256K context window and advanced multimodal capabilities. Features enhanced reasoning, agentic workflows, and state-of-the-art performance across all benchmarks.

openai/gpt-5-mini

$32.00/M

Cost-effective GPT-5 variant with 256K context. Balanced performance for everyday tasks while maintaining strong reasoning and vision capabilities at reduced cost.

openai/gpt-5-nano

$32.00/M

Ultra-efficient GPT-5 variant optimized for maximum throughput at minimal cost. Features 128K context and low-latency design for high-volume automation tasks.