AI Models | 𝐗𝐀𝐈 𝐑𝐨𝐮𝐭𝐞𝐫

$2.0 in$8.0 out

gpt-4.1

OpenAI's upgraded GPT-4 series model with excellent performance in reasoning and creative tasks

$1.25 in$10 out$0.125 cached

256K tokensCode-Specialized Model

gpt-5.1-codex

OpenAI's 2025 code-specialized model, focused on code understanding, generation, and optimization with caching support

200K tokensLarge Language Model (LLM)

$3 in$15 out

Anthropic

claude-sonnet-4-5-20250929

Anthropic's 2025 flagship model, excelling in code generation, analysis, and writing tasks

$0.15 in$0.6 out

128K tokensMultimodal Large Language Model

gpt-4o-mini

Lightweight version of GPT-4o, providing multimodal capabilities at lower cost

$1.25 in$10 out$0.125 cached

256K tokensCode-Specialized Model

gpt-5.3-codex

OpenAI's 2025 code-specialized model, focused on code understanding, generation, and optimization with caching support

$2.0 in$12.0 out$0.2 cached

gemini-3-pro-preview

Google AI Studio's latest 2025 frontier multimodal model with breakthrough reasoning capabilities and exceptional performance

gpt-4.1-mini

Lightweight version of GPT-4.1, offering excellent performance while being more cost-effective

$0.1 in$0.4 out

gpt-4.1-nano

Ultra-lightweight version of GPT-4.1, offering extreme cost-effectiveness for simple and fast tasks

Image

$2 in$12 out$0.2 cached

65K input / 32K output tokensDefault 1K, optional 2K / 4K, multiple aspect ratios

gemini-3-pro-image-preview

Google AI Studio text-to-image preview model with 1K/2K/4K output, multi-image reference, Thinking + Search Grounding

$0.375 in$3 out$0.0375 cached

256K tokensLightweight Code Model

gpt-5.1-codex-mini

OpenAI's 2025 lightweight code model, offering faster response times and lower costs while maintaining high-quality code capabilities

128K tokensCode-Specialized Model

$1 in$2 out

Moonshot AI

kimi-for-coding

Moonshot AI's Kimi code-specialized model, focused on code understanding, generation, and optimization

$0.8 in$8 out

128K tokensReasoning-Enhanced Model

doubao-seed-1.6-thinking

ByteDance's Doubao reasoning model with powerful deep thinking and reasoning capabilities

300K tokensMultimodal Large Language Model

$0.8 in$3.2 out

AWS Bedrock

nova-pro

AWS's high-performance multimodal model supporting text and image understanding

$0.8 in$2 out

256K tokensLarge Language Model (LLM)

doubao-seed-1-8-251215

ByteDance's Doubao 1.8 flagship model with comprehensive and balanced large language model capabilities

$2 in$3 out$0.4 cached

DeepSeek

deepseek-v3

DeepSeek's latest flagship model V3.2, 685B parameters, reasoning capabilities rivaling GPT-5, 128K context

doubao-seed-1.6

ByteDance's Doubao flagship model with comprehensive and balanced large language model capabilities

$1.2 in$3.6 out

128K tokensTranslation-Specialized Model

doubao-seed-translation-250915

ByteDance Doubao translation-specialized model, providing high-quality multilingual translation services

$1.5 in$10 out

2M tokensMultimodal Large Language Model

gemini-2.5-pro

Google AI Studio's 2025 flagship multimodal model with ultra-long context support and powerful multimodal understanding capabilities

$1.2 in$8 out

256K tokensCode-Specialized Model

ark-code-latest

ByteDance Doubao code-specialized model, focused on code understanding, generation, and optimization

$0.15 in$1.5 out

doubao-seed-1.6-flash

Doubao fast version, providing faster response speed and more economical pricing

$2 in$12 out

2M tokensMultimodal Large Language Model

google/gemini-3-pro

Google Vertex AI flagship multimodal model with ultra-long context support and powerful multimodal understanding capabilities

$1.5 in$10 out

2M tokensMultimodal Large Language Model

google/gemini-2.5-pro

Google Vertex AI flagship multimodal model with ultra-long context support and powerful multimodal understanding capabilities

64K tokensReasoning Model

$1.4 in$2.8 out

DeepSeek

deepseek-r1

Chinese open-source reasoning model, rivaling o1 in mathematics, coding, and scientific reasoning with exceptional cost-effectiveness

300K tokensMultimodal Large Language Model

$0.06 in$0.24 out

AWS Bedrock

nova-lite

AWS Nova lightweight version, providing fast and economical multimodal capabilities

$5 in$15 out

xAI

grok-4

xAI's latest flagship model with real-time internet search capabilities and timely knowledge updates

$0.5 in$3 out$0.05 cached

gemini-3-flash-preview

Fast Multimodal

Google AI Studio high-throughput multimodal preview model with low latency and strong cost efficiency

doubao-seed-1-6-lite-251015

Doubao lightweight version, providing ultimate cost-effectiveness for large language model capabilities

$0.035 in$0.14 out

AWS Bedrock

nova-micro

AWS Nova ultra-lightweight version, providing extreme cost-effectiveness for text processing

$0 in$0 out

Tencent

tencent/Hunyuan-MT-7B

Free

Tencent Hunyuan machine translation model with ultra-low cost multilingual translation

Machine Translation7B

$0.2 in$0.5 out

xAI

grok-4-fast

xAI's Grok-4 fast version, providing faster response times while maintaining powerful capabilities

$0 in$0 out

Large Language Model32.8B

qwen3-32b

Free

Alibaba Cloud Qwen 32B parameter large language model, powerful free AI assistant

$1 in$10 out$0.2 cached

Vision-Language Model (VLM)Text + Image

qwen3-vl-plus

Alibaba Qwen 3.0 vision-language model for strong multimodal understanding

128K tokensCode Generation Model

$0.2 in$1.5 out

xAI

grok-code-fast

xAI's code-optimized model designed for rapid code generation and understanding

2M Chinese charactersLarge Language Model (LLM)

$1 in$3 out

Moonshot AI

moonshotai/kimi-k2-instruct-0905

Ultra Fast

Chinese ultra-long context model supporting 2 million characters input, excelling at long document analysis and processing

Rerank

$0.5 in

Large Text Embedding Model2048 dimensions

qwen3-rerank

Alibaba Qwen 3.0 text rerank model for relevance scoring and search result reordering

doubao-embedding-large-text

ByteDance Doubao large text embedding model, providing higher quality text vectorization capabilities

Embedding

$0.7 in$0 out

Vision Embedding ModelImages and Multimodal

doubao-embedding-vision

ByteDance Doubao vision embedding model, supporting vectorization of images and multimodal content

$2 in$6 out

qwen3-max

Alibaba Qwen 3.0 flagship model with strong Chinese capabilities and high cost-effectiveness

$0.15 in$1.5 out$0.03 cached

Vision-Language Model (VLM)Text + Image

qwen3-vl-flash

Alibaba Qwen 3.0 lightweight vision-language model optimized for low latency

Deep Reasoning Open Source

$4 in$16 out$1 cached

Moonshot AI

kimi-k2-thinking

Moonshot AI's reasoning-enhanced model with interleaved thinking and tool-use capabilities, excelling at complex reasoning and agentic tasks

256K tokensReasoning-Enhanced MoE Model

Rerank

$1.8 in

Multimodal Rerank ModelText + Image

qwen3-vl-rerank

Alibaba Qwen 3.0 multimodal rerank model for text-image retrieval reranking

Image

$0.05/ image

Up to 4K (4096x4096)Image Generation

gpt-image-1

OpenAI's latest 2025 image generation model with comprehensively improved understanding capabilities and image quality

$0.5 in$1.5 out

256K tokensMoE (41B/675B)

mistral-large-latest

Mistral AI's flagship MoE open-source model with 675B total parameters, multimodal capabilities and 256K context

Embedding

$0.5 in$0 out

Text Embedding Model1024 dimensions

doubao-embedding-text

ByteDance's Doubao text embedding model for text vectorization and semantic retrieval

Audio

$0.006/ minute

99+ languagesAutomatic Speech Recognition (ASR)

whisper-1

Powerful speech recognition model supporting multilingual transcription and translation

Embedding

$0.00013/ 1K tokens

1M tokensMultimodal Large Language Model

text-embedding-3-large

High-performance text embedding model for semantic search and similarity calculation

gemini-2.5-flash

Multimodal

Google AI Studio's fast multimodal model with ultra-long context support

$0.3 in$2.5 out

1M tokensMultimodal Large Language Model

google/gemini-2.5-flash

Google Vertex AI fast multimodal model with ultra-long context support and enterprise-grade reliability

$0.1 in$0.4 out

1M tokensLightweight Multimodal Model

gemini-2.5-flash-lite

Ultra Fast

Google AI Studio's ultra-lightweight multimodal model with ultra-fast response

$0.1 in$0.4 out

1M tokensLightweight Multimodal Model

google/gemini-2.5-flash-lite

Google Vertex AI ultra-lightweight multimodal model with ultra-fast response and enterprise deployment

$0.2 in$0.2 out

128K tokens14B Parameters

ministral-14b-latest

Mistral AI's most capable edge model with 14B parameters, vision capabilities and reasoning variants

$0.15 in$0.15 out

ministral-8b-latest

Mistral AI's edge-optimized medium model with 8B parameters, vision capabilities and sliding window attention

128K tokens8B Parameters

$0.1 in$0.1 out

ministral-3b-latest

Mistral AI's edge-optimized small model with 3B parameters, vision capabilities and 128K context

128K tokens3B Parameters

Online Search ModelReal-time Web Search

$1 in$1 out

Perplexity

sonar

Perplexity online search model with real-time internet access

Ultra-long Context SupportLarge Language Model

$2.1 in$8.4 out

MiniMax

MiniMax-M2.1

Featured

MiniMax's high-performance large language model with ultra-long context and efficient reasoning, compatible with Claude Code

High-Performance Search ModelAdvanced Reasoning + Real-time Search

$3 in$15 out

Perplexity

sonar-pro

Perplexity high-performance online search model with enhanced reasoning capabilities

200K tokensLarge Language Model (LLM)

$2 in$8 out$0.4 cached

Zhipu AI

glm-4.7

Zhipu AI's latest flagship model with coding capabilities matching Claude Sonnet 4, supporting 200K ultra-long context, deep reasoning and tool calling