Every AI model, one API key.

Claude Opus 4.5 Thinking

Deep thinking version of Opus 4.5

Anthropic · Language · 200K

Claude Opus 4.6

Powerful Claude model for demanding tasks

Claude Opus 4.6 Thinking

Deep thinking version of Opus 4.6

Anthropic · Language · 200K

Claude Opus 4.7

Anthropic's flagship model for complex reasoning, programming, agent execution, and visual understanding

DeepSeek · Reasoning · 64K

DeepSeek R1

DeepSeek R1 reasoning model

Streaming Reasoning

$0.448 / 1M tok

DeepSeek · Reasoning · 64K

DeepSeek R1 (0528)

Lightweight R1 reasoning version

Streaming Reasoning

$0.408 / 1M tok

DeepSeek V3

Standard DeepSeek V3 chat model

$0.206 / 1M tok

DeepSeek V3.1 Terminus

Stable upgrade of V3.1 with improved agent performance

$0.408 / 1M tok

DeepSeek V3.2

Latest DeepSeek V3.2 chat model

$0.206 / 1M tok

DeepSeek V3.2 Experimental

Experimental V3.2 with sparse attention

$0.206 / 1M tok

GPT-5.4

Streaming Vision Function calling Reasoning +1

OpenAI's GPT-5.4 delivers powerful capabilities in complex reasoning, coding, and professional knowledge work.

$0.700 / 1M tok

–60%

GPT-5.5

Streaming Vision Function calling Reasoning +1

OpenAI's advanced reasoning model for agentic coding, knowledge work, scientific research, and complex multi-step task execution.

–72%

GPT-Image-2

OpenAI · Image · 4K

Next-gen AI image generation with near-perfect text rendering, native 4K output, and deep world knowledge

$0.016 / image

GPT-Image-2 (Official Channel)

OpenAI · Image · 4K

GPT-Image-2 via official channel with higher quality

$0.0082 / image

Google / DeepMind · Image · HD

Nano Banana (Gemini 2.5 Flash Image)

Google's original fast image generation and editing model.

$0.0398

Google / DeepMind · Image · 4K (2X RATE)

Nano Banana 2

Google's Gemini 3.1 Flash Image architecture. Vibrant, high-fidelity visuals with reasoning capabilities. Accurate text rendering, charac…

$0.08

Google / DeepMind · Image · HD

Nano Banana Pro

Google's state-of-the-art high-fidelity image generation and editing model. Maximum reasoning depth for compositional complexity.

$0.15

Seedance 2.0

ByteDance · Video · 720P

Advanced video generation with facial recognition and manipulation

$0.168 / second

Seedance 2.0

ByteDance · Video · 480P

ByteDance's most advanced text-to-video model. Cinematic output with native audio, multi-shot editing, real-world physics, and director-l…

$0.303 / s

Seedance 2.0 Face

ByteDance · Video · 720P

Specialized version focused on advanced facial recognition and manipulation

$0.168 / second

Seedance 2.0 Fast

ByteDance · Video · 480P

Accelerated Seedance 2.0 with the same routing and capabilities as Seedance 2.0; tiered pricing by resolution and uploaded-video modes

$0.059 / second

Seedance 2.0 Fast Face

ByteDance · Video · 720P

Accelerated facial generation for real-time applications

$0.136 / second

Sora 2

OpenAI · Video · 720P

AI video model balancing quality and cost with synchronized audio

$0.136 / second

Sora 2

OpenAI · Video · 720P

OpenAI's state-of-the-art video model. Richly detailed, dynamic clips with audio from natural language or images.

$0.100 / s

Sora 2 Pro

OpenAI · Video · 720P

Premium Sora 2 with higher priority

$0.204 / gen

ElevenLabs · Speech · TTS

ElevenLabs V3

ElevenLabs V3 Alpha API for multilingual text-to-dialogue with audio tags and expressive voice capabilities.

Multilingual

Gemini 3 Flash Preview

Fast preview version of Gemini 3

Gemini 3 Flash Preview (No Thinking)

Gemini 3 Flash without thinking mode

Gemini 3 Pro Image (Nano Banana Pro)

Google · Image · 4K

Advanced image generation and editing with enhanced reasoning, world knowledge grounding, and high-fidelity output

Gemini 3 Pro Preview

Gemini 3 Pro preview with thinking support

Gemini 3 Pro Preview Thinking

Google · Reasoning · 1M

Deep thinking version of Gemini 3 Pro

Gemini 3.1 Pro Preview

Latest Gemini 3.1 Pro with enhanced capabilities

o4 Mini

Compact reasoning model

$0.880 / 1M tok

Anthropic · Language · 200K

Claude Haiku 4.5

Fast response version for quick tasks

$0.800 / 1M tok

Claude Haiku 4.5 Thinking

Thinking version of fast Haiku model

$0.800 / 1M tok

Anthropic · Language · 1M

Claude Sonnet 4.5

Balanced Claude 4.5 model for complex reasoning

Anthropic · Reasoning · 1M

Claude Sonnet 4.5 Thinking

Deep thinking version of Sonnet 4.5

Anthropic · Language · 1M

Claude Sonnet 4.6

Balanced performance and speed

Anthropic · Reasoning · 1M

Claude Sonnet 4.6 Thinking

Enhanced reasoning version of Sonnet 4.6

Black Forest Labs · Image · UP TO 2K

FLUX1.1 [pro] ultra

Professional-grade image quality with up to 2K resolution and improved photo realism.

$0.07

GPT-4o Mini Transcribe

OpenAI · Language · 128K

Lightweight audio transcription model

GPT-4o Transcribe

OpenAI · Language · 128K

Audio transcription and understanding model

$2.00 / 1M tok

GPT-5

OpenAI flagship model with enhanced reasoning

GPT-5 Mini

Lightweight version of GPT-5, cost-effective

$0.200 / 1M tok

GPT-5 Nano

Ultra-lightweight GPT-5 model

$0.040 / 1M tok

GPT-5 Pro

Professional enhanced GPT-5 version

$12.00 / 1M tok

GPT-5 Search API

GPT-5 with web search integration

GPT-5 Search API (2025-10-14)

GPT-5 Search snapshot version

GPT-5.1

GPT-5.1 base model with enhanced reasoning

GPT-5.1 (2025-11-13)

GPT-5.1 snapshot from November 2025

GPT-5.1 Chat Latest

Latest GPT-5.1 chat-optimized model

GPT-5.1 Codex

Code-optimized GPT-5.1 model

GPT-5.1 Codex Mini

Lightweight code-optimized model

$0.200 / 1M tok

GPT-5.2

GPT-5.2 base model

GPT-5.2 Chat Latest

Latest GPT-5.2 chat-optimized model

GPT-5.2 Codex

Streaming Reasoning Long context

Advanced code generation and reasoning model

GPT-5.2 Pro

Most powerful GPT-5.2 model for complex tasks

$16.80 / 1M tok

OpenAI · Image · 1536X1024

GPT-Image-1

AI generative model integrating text and image understanding for high-quality image creation and editing

$0.182 / image

OpenAI · Image · 1536X1024

GPT-Image-1.5

Upgraded version of GPT-Image-1 with higher quality and improved understanding

$0.145 / image

GPT-Image 1.5

OpenAI · Image · HD

High-fidelity images with strong prompt adherence, preserving composition, lighting, and fine-grained detail.

$0.009 / img

Gemini 2.0 Flash

Fast Gemini 2.0 model

$0.080 / 1M tok

Gemini 2.5 Flash

Fast multimodal model

$0.240 / 1M tok

Gemini 2.5 Flash (No Thinking)

Gemini 2.5 Flash without thinking

$0.240 / 1M tok

Gemini 2.5 Flash Image (Nano Banana)

Google · Image · 4K

Fast, low-latency image creation with natural-language edits, multi-image fusion, and character consistency

$0.037 / image

Gemini 2.5 Flash Lite

Ultra-lightweight Gemini model

$0.080 / 1M tok

Gemini 2.5 Flash Thinking

Google · Reasoning · 2M

Thinking version of Flash 2.5

$0.240 / 1M tok

Gemini 2.5 Pro

Professional version with advanced reasoning

Gemini 2.5 Pro (No Thinking)

Gemini 2.5 Pro without thinking

Gemini 2.5 Pro Thinking

Google · Reasoning · 2M

Deep thinking Gemini 2.5 Pro

Kling 2.5 Turbo Pro

Kling · Video · Video

Kuaishou's fast text-to-video model optimized for rapid iteration. 5s video costs $0.35, additional seconds at $0.07/s.

$0.35

Kling 2.6 Pro

Kling · Video · Video

Cinematic text-to-video with native audio synthesis. Chinese and English voice output with automatic translation.

$0.070 / s

Kling 3.0

Kling · Video · 720P

Kuaishou's flagship AI video model with native 4K output, audio generation, and multi-shot storyboarding. World's first AI video model wi…

$0.168 / s

Kling V3

Kuaishou · Video · 720P

AI video model balancing quality and control for medium to high-quality content

$0.114 / second

Kling V3 Omni

Kuaishou · Video · 720P

Cinematic-grade multimodal video model with multi-camera storytelling and audio-visual integration

$0.114 / second

Kling Video O1

Kuaishou · Video · 720P

Multimodal video model combining generation and editing with high consistency

$0.114 / second

Kling Video v3 Pro

Kling · Video · Video

Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation, with multi-shot support.

OpenAI Codex

Streaming Function calling Long context

Advanced coding capabilities built on GPT-5 Codex models. Supports code generation, debugging, and complex engineering workflows.

$0.700 / 1M tok

–60%

Google / DeepMind · Video · 720P

Veo 3.1

Google's most advanced AI video generation model with synchronized audio.

$0.200 / s

Veo 3.1 Fast

APImart fast Veo 3.1 — text-to-video, image-to-video (frame & reference modes), fixed 8s duration

$0.220 / gen

Veo 3.1 Lite

APImart lightweight Veo 3.1 — text-to-video only, fixed 8s duration, lowest cost for high-volume batch generation

$0.160 / gen

Google / DeepMind · Video · 720P

Veo 3.1 Lite

Google's cost-efficient Veo 3.1 Lite — text-to-video with synchronized audio.

$0.100 / s

Veo 3.1 Quality

APImart high-quality Veo 3.1 — best fidelity for production output, text & frame image-to-video, fixed 8s duration

$0.272 / gen

Whisper-1

OpenAI · Speech · STT

OpenAI's transcription model supporting multiple languages and audio formats

$0.010 / minute

o3

Advanced reasoning model for complex problem solving

o3 Mini

Streaming Reasoning Long context

Lightweight reasoning model

$0.880 / 1M tok

BelugAPI Music

BelugAPI · Music · Music

AI music generation converting text prompts into full vocal and instrumental tracks. Supports V5 model for enhanced realism.

$0.06 / request

BiRefNet

Bilateral reference framework for high-resolution dichotomous image segmentation.

BiRefNet V2 Video

Video background removal using BiRefNet.

Bria RMBG 2.0

Seamless background removal trained on licensed data for commercial use.

Bria Video Background Removal

Automatically remove backgrounds from videos without a green screen.

Claude 3.7 Sonnet Thinking

Legacy Claude 3.7 Sonnet with thinking mode

DeepSeek · Language · 64K

DeepSeek OCR

OCR model for extracting text, tables from images and PDFs

Streaming Vision

$0.046 / 1M tok

ElevenLabs Audio Isolation

ElevenLabs · Music · Music

Isolate vocals, instruments, or specific audio elements from mixed audio tracks.

$0.001 / s

ElevenLabs Scribe

ElevenLabs · Speech · STT

Accurate speech transcription with 99-language support, speaker diarization, and audio-event tagging.

ElevenLabs · Music · Music

ElevenLabs Sound Effect

AI sound effect generation for royalty-free audio production.

$0.0012 / s

ElevenLabs TTS

ElevenLabs · Speech · TTS

High-quality multilingual text-to-speech with natural voice synthesis.

Multilingual

$0.06

FLUX.1 [dev]

Black Forest Labs · Image · HD

12 billion parameter flow transformer for high-quality text-to-image generation. Suitable for personal and commercial use.

$0.025

FLUX.1 [dev] with LoRAs

Black Forest Labs · Image · HD

FLUX.1 [dev] with LoRA support for personalization and specific styles.

$0.035

FLUX.2 [pro]

Black Forest Labs · Image · HD

High-quality image manipulation, style transfer, and sequential editing workflows.

$0.04

Flux 2.0

Latest Flux 12B-parameter flow transformer for high-quality text-to-image generation

$0.020 / megapixel

Flux Kontext

Flux model with contextual understanding for image manipulation, style transfer, and sequential editing workflows

$0.032 / image

Streaming Vision Reasoning

GLM-4.6

Zhipu · Language · 128K

High-performance model for encoding and reasoning

$0.360 / 1M tok

GLM-4.7

Zhipu · Language · 128K

Large language model with code generation and tool invocation

Streaming Vision Function calling

Streaming Vision Reasoning

GLM-5.1

Zhipu · Language · 32K

Flagship AI model for programming, complex reasoning and agent tasks

$0.800 / 1M tok

GPT-3.5 Turbo 16K

OpenAI · Language · 16K

Legacy GPT-3.5 with 16K context

GPT-4 Turbo (1106 Preview)

OpenAI · Language · 32K

GPT-4 Turbo preview version

Streaming Vision

$8.00 / 1M tok

GPT-4.1 Mini

OpenAI · Language · 1M

Compact GPT-4.1 model

$0.320 / 1M tok

GPT-4.1 Nano

OpenAI · Language · 1M

Ultra-compact GPT-4.1 model

$0.080 / 1M tok

Grok Imagine 1.0

xAI's image generation model

$0.026 / image

Grok Imagine 1.0 Edit

xAI's image editing model

$0.026 / image

Grok Imagine Image

xAI · Image · HD

Edit images precisely with xAI's Grok Imagine model.

Grok Imagine Video

xAI · Video · 480P

Generate videos from images with audio using xAI's Grok Imagine Video model.

$0.008 / s

HappyHorse 1.0

Alibaba · Video · 720P

Alibaba Cloud Bailian HappyHorse 1.0 unified entry: auto-routes T2V, I2V, R2V, or video EDIT by parameters; billed by resolution × durati…

$0.221 / second

Hunyuan 3D Pro

Tencent · 3D · 3D mesh

Generate 3D models from images with Hunyuan 3D Pro.

Ideogram V3

Moonshot AI · Language · Chat

Generate high-quality images, posters, and logos with exceptional typography handling.

$0.016 / img

Kimi K2 Instruct

Open-source instruction model for coding and reasoning

Streaming Vision Reasoning

Moonshot AI · Reasoning · Reasoning

Kimi K2 Thinking

Open-source reasoning model for step-by-step thinking

Streaming Vision Function calling Reasoning

BelugAPI · Language · 32K

Free

Meta Llama 3.1 8B

Efficient 8B-parameter Llama 3.1 instruct model tuned for responsive chat. Free to use, with a fair-use rate limit of 10 requests per min…

Free 10 req/min · per user

100% free

MiniMax Hailuo 2.3

MiniMax · Video · 720P

Latest-generation video model with superior visual quality and coherent motion

$0.083 / second

MiniMax Hailuo 2.3 Fast

MiniMax · Video · 720P

High-speed video generation for rapid turnaround at low cost

$0.043 / second

MiniMax · Language · 246K

MiniMax M2.1

High-performance text model for multilingual coding and reasoning

Streaming Vision Reasoning Long context +1

$0.216 / 1M tok

OpenAI GPT OSS 120B

BelugAPI · Language · Chat

120B-parameter open-weight GPT-OSS style model for general chat and reasoning.

BelugAPI · Language · 128K

$0.350 / 1M tok

Qwen 3 235B Instruct

Qwen 3 235B instruct variant (preview); use for evaluation rather than production.

$0.600 / 1M tok

Qwen Image

Alibaba · Image · HD

High-quality image generation with native 2K output and advanced text rendering.

$0.02

Qwen Image 2.0 Pro

Highest-fidelity variant with native 2K resolution, strong detail and text rendering

$0.085 / image

SeedVR2 Image

Upscale images with SeedVR2.

SeedVR2 Video

Upscale videos using SeedVR2 with temporal consistency.

Seedream 4.0

ByteDance · Image · 2K

High-quality image generation model from ByteDance

$0.024 / image

Seedream 4.5

ByteDance · Image · 2K

Upgraded Seedream with enhanced quality

$0.024 / image

Seedream 5.0 Lite

ByteDance · Image · 1K

Lightweight version of Seedream 5.0

$0.020 / image

Seedream V4 / V4.5

ByteDance · Image · HD

ByteDance's unified image generation and editing architecture. Single model for generation and editing.

$0.03

SkyReels V4 Fast

Skywork · Video · 1080P

Unified framework for joint audiovisual generation with 1080p multi-shot video

$0.109 / second

SkyReels V4 Standard

Skywork · Video · 1080P

Standard quality cinema-grade audiovisual generation

$0.150 / second

TTS-1

OpenAI · Speech · TTS

Text-to-speech with natural sounding voices

$0.026 / 1K char

TTS-1 HD

OpenAI · Speech · TTS

Higher quality text-to-speech with premium voices

$0.051 / 1K char

Topaz Upscale

Powerful and accurate image enhancer.

Topaz Video Upscale

Professional-grade video upscaling using Topaz technology.

Trellis

Trellis · 3D · 3D mesh

Generate 3D models from images using Trellis.

Trellis 2

Trellis · 3D · 3D mesh

Generate 3D models from images. Native 3D generative model enabling versatile and high-quality 3D asset creation.

Veo 3.1

Full Veo 3.1 with 4K support and native audio

$0.170 / second

Vidu Q3

Vidu · Video · 720P

Standard Vidu Q3 video generation

$0.136 / second

Vidu Q3 Mix

Vidu · Video · 720P

Advanced video generation with synchronized native audio including dialogue and sound effects

$0.170 / second

Vidu Q3 Pro

Vidu · Video · 1080P

Professional tier for high performance and intelligent optimization

$0.204 / second

Vidu Q3 Turbo

Vidu · Video · 720P

High-speed tier for rapid iteration

$0.082 / second

Wan 2.5

Alibaba · Video · 1080P

Video model with synchronized audio and cinematic visuals

$0.058 / second

Wan 2.5

Alibaba · Video · Video

Alibaba's video generation model.

$0.05

Wan 2.6 I2V

Alibaba · Video · 1080P

Image-to-video variant animating static images with smooth motion and synchronized audio

Wan 2.7

Alibaba · Video · 720P

Next-gen multimodal video model with text-to-video, image-to-video and instruction-based editing

Wan 2.7 Image

Advanced image generation with multimodal input support

$0.037 / image

Wan 2.7 Image

Alibaba · Image · HD

Unified image model for generation and editing with 2K-4K output.

Wan 2.7 Image Pro

Professional version with higher quality output

$0.092 / image

Wan 2.7 R2V

Alibaba · Video · 720P

Reference-to-video variant preserving character appearance and identity from visual anchors

Wan 2.7 Video

Alibaba · Video · Video

Alibaba Tongyi Lab's AI video suite covering four generation modes.

$0.080 / s

Wan 2.7 Video Edit

Alibaba · Video · 1080P

Advanced video editing with natural language instructions and style transfer

Z-Image-Turbo

Fast, efficient, and cost-effective model for rapid image creation and batch processing

$0.017 / image

Z-Image Turbo

Super fast 6B parameter text-to-image model by Tongyi-MAI.

BelugAPI · Language · 128K

Z.ai GLM 4.7

Z.ai GLM 4.7 (preview); use for evaluation rather than production.

$2.25 / 1M tok

o1

First-generation reasoning model