Every Model.
One Gateway.

Auto-router

Anthropic

claude-fable-5

AI

Auto-router

Anthropic

claude-haiku-4-5-20251001

Fastest model with near-frontier intelligence

Auto-router

Anthropic

claude-opus-4-1

test

Auto-router

Anthropic

claude-opus-4-1-20250805

AI

Auto-router

Anthropic

claude-opus-4-5-20251101

Premium model combining maximum intelligence with practical performance

Auto-router

Anthropic

claude-opus-4-6

Our most intelligent model for building agents and coding

Auto-router

Anthropic

claude-opus-4-7

Most powerful model for complex reasoning and coding

Auto-router

Anthropic

claude-opus-5

1

Auto-router

Anthropic

claude-sonnet-4-5-20250929

Highest intelligence across most tasks with exceptional agent and coding capabilities

Auto-router

Anthropic

claude-sonnet-4-6

The best combination of speed and intelligence

Auto-router

Anthropic

claude-sonnet-5

Anthropic's most agentic Sonnet model, closing much of the gap to Opus 4.8 on coding, agentic, and knowledge-work tasks at Sonnet-tier pricing.

Deepgram

nova-2

Deepgram

nova-3

Auto-router

Deepseek

deepseek-v4-flash

DeepSeek-V4-Flash is a fast, capable model supporting thinking and non-thinking modes with 1M context. Accepts text inputs and produces text outputs.

Auto-router

Deepseek

deepseek-v4-pro

DeepSeek-V4-Pro is a powerful flagship model supporting thinking and non-thinking modes with 1M context. Accepts text inputs and produces text outputs.

Auto-router

Gemini

gemini-2.5-flash

best model in terms of price-performance, offering well-rounded capabilities. 2.5 Flash is best for large scale processing, low-latency, high volume tasks that require thinking, and agentic use cases.

Auto-router

Gemini

gemini-2.5-flash-image

Gemini 2.5 Flash Image is optimized for image understanding and generation and offers a balance of price and performance. Gemini 2.5 Flash Image uses the speed and cost-effectiveness of Gemini 2.5 Flash to provide fast and efficient image generation and editing capabilities.

Auto-router

Gemini

gemini-2.5-flash-lite

The most cost-efficient and fastest model in the 2.5 family, optimized for extreme low-latency and high-throughput scenarios.

Auto-router

Gemini

gemini-2.5-pro

state-of-the-art thinking model, capable of reasoning over complex problems in code, math, and STEM, as well as analyzing large datasets, codebases, and documents using long context.

Auto-router

Gemini

gemini-3-flash-preview

Gemini 3 Flash combines Gemini 3 Pro's reasoning capabilities with the Flash line's levels on latency, efficiency, and cost

Auto-router

Gemini

gemini-3-pro-image-preview

The gemini-3-pro-image-preview model, also known as Nano Banana Pro, is Google's image generation and editing model. It launched in late 2025. Built on the Gemini 3 Pro architecture, it has a Thinking Mode. This mode allows the model to reason through complex instructions. It results in higher accuracy and factuality compared to earlier versions. The model supports resolutions up to 4K. It is the first to integrate Grounding with Google Search.

Auto-router

Gemini

gemini-3-pro-preview

Gemini 3 Pro Preview is our most powerful agentic and coding model.

Auto-router

Gemini

gemini-3.1-pro-preview

Gemini 3.1 Pro is our most advanced reasoning Gemini model, capable of solving complex problems.

Auto-router

Gemini

gemini-3.5-flash

Newest and most capable Speed oriented Frontier model from Google.

Auto-router

Gemini

gemini-3.7-flash

Gemini 3.7 Flash is Google's fast, cost-efficient multimodal model released August 2026, featuring a 1M-token context window, tunable thinking (reasoning) levels, and improved coding and agentic performance over Gemini 3.6 Flash.

Auto-router

Gemini

imagen-4.0-fast-generate-001

This is the Low Latency variant. It is designed for high-speed generation.

Auto-router

Gemini

imagen-4.0-generate-001

This Standard model balances quality and speed. It supports resolutions up to 2K (2048x2048) and multilingual prompts in 9 languages.

Auto-router

Gemini

imagen-4.0-ultra-generate-001

This is the Highest Quality model. It offers image fidelity and text rendering and is optimized for premium production needs. This model generates one image at a time.

Grok

grok-4-0709

Grok Models

Grok

grok-4-fast

Grok Models

Grok

grok-4-fast-reasoning

Grok-4 Fast Reasoning – optimized for quick structured reasoning and planning tasks

Groq

llama-3.1-8b-instant

Llama 3.1 8B on Groq provides low-latency, high-quality responses suitable for real-time conversational interfaces, content filtering systems, and data analysis applications. This model offers a balance of speed and performance with significant cost savings compared to larger models. Technical capabilities include native function calling support, JSON mode for structured output generation, and a 128K token context window for handling large documents.

Groq

llama-3.3-70b-versatile

Llama-3.3-70B-Versatile is Meta's advanced multilingual large language model, optimized for a wide range of natural language processing tasks. With 70 billion parameters, it offers high performance across various benchmarks while maintaining efficiency suitable for diverse applications.

Groq

meta-llama/llama-4-scout-17b-16e-instruct

Llama 4 Scout is Meta's natively multimodal model that enables text and image understanding. With a 17 billion parameter mixture-of-experts architecture (16 experts), this model offers industry-leading performance for multimodal tasks like natural assistant-like chat, image recognition, and coding tasks. With a 128K token context window and support for 12 languages (Arabic, English, French, German, Hindi, Indonesian, Italian, Portuguese, Spanish, Tagalog, Thai, and Vietnamese), the model delivers exceptional capabilities, especially when paired with Groq for fast inference.

Groq

openai/gpt-oss-120b

GPT-oss-120b is the most powerful open-weight model. A 120B-parameter open-weight Mixture-of-Experts model delivering state-of-the-art reasoning, coding, and tool-use performance

Groq

openai/gpt-oss-20b

GPT-oss-120b is the most powerful open-weight model. A 120B-parameter open-weight Mixture-of-Experts model delivering state-of-the-art reasoning, coding, and tool-use performance

Minimax

minimax-m3

MiniMax-M3 is an open-weight, natively multimodal Mixture-of-Experts model with ~428B total parameters (~23B activated), built on MiniMax Sparse Attention (MSA) for efficient long-context processing. Accepts text, image, video, and PDF inputs and produces text outputs, with a deep thinking mode for complex reasoning.

Auto-router

Mistral

codestral-latest

Lightweight, fast, and proficient in over 80 programming languages.

Auto-router

Mistral

magistral-medium-latest

Auto-router

Mistral

magistral-small-latest

Lightweight, fast, and proficient in over 80 programming languages.

Auto-router

Mistral

mistral-medium-latest

Auto-router

Mistral

mistral-small-latest

Lightweight, fast, and proficient in over 80 programming languages.

Moonshot

kimi-k2.5

Kimi K2.5 is Moonshot AI's multimodal model supporting text, image, and video input, with thinking and non-thinking modes, and both dialogue and agent tasks. Context length 256K with support for long thinking and deep reasoning. Supports automatic context caching, ToolCalls, JSON Mode, Partial Mode, and internet search.

Moonshot

kimi-k2.6

Kimi K2.6 is Moonshot AI's latest and most intelligent model, with stronger and more stable long-horizon code generation, significantly improved instruction following and self-correction. It features a native multimodal architecture supporting text, image, and video input, thinking and non-thinking modes, and both dialogue and agent tasks. Supports automatic context caching, ToolCalls, JSON Mode, Partial Mode, and internet search.

Moonshot

kimi-k2.7-code

Kimi K2.6 is Moonshot AI's latest and most intelligent model, with stronger and more stable long-horizon code generation, significantly improved instruction following and self-correction. It features a native multimodal architecture supporting text, image, and video input, thinking and non-thinking modes, and both dialogue and agent tasks. Supports automatic context caching, ToolCalls, JSON Mode, Partial Mode, and internet search.

Moonshot

kimi-k2.7-code-highspeed

Kimi K2.6 is Moonshot AI's latest and most intelligent model, with stronger and more stable long-horizon code generation, significantly improved instruction following and self-correction. It features a native multimodal architecture supporting text, image, and video input, thinking and non-thinking modes, and both dialogue and agent tasks. Supports automatic context caching, ToolCalls, JSON Mode, Partial Mode, and internet search.

Moonshot

moonshot-v1-128k

Moonshot V1 128K is Moonshot AI's generation model with a 131,072-token context window, suitable for generating very long texts and handling long-context chat, generation, and tool-calling tasks. Supports ToolCalls, JSON Mode, and Partial Mode.

Moonshot

moonshot-v1-128k-vision-preview

Moonshot V1 128K Vision is Moonshot AI's vision-capable generation model with a 131,072-token context window. It understands image content and outputs text, suited for long-context multimodal chat, image understanding, and tool-calling tasks. Supports ToolCalls, JSON Mode, and Partial Mode.

Moonshot

moonshot-v1-32k

Moonshot V1 32K is Moonshot AI's generation model with a 32,768-token context window, suited for medium-context chat, generation, and tool-calling tasks. Supports ToolCalls, JSON Mode, and Partial Mode.

Moonshot

moonshot-v1-32k-vision-preview

Moonshot V1 32K Vision is Moonshot AI's vision-capable generation model with a 32,768-token context window. It understands image content and outputs text, suited for medium-context multimodal chat, image understanding, and tool-calling tasks. Supports ToolCalls, JSON Mode, and Partial Mode.

Moonshot

moonshot-v1-8k

Moonshot V1 8K is Moonshot AI's generation model with an 8,192-token context window, suited for short-context chat, generation, and tool-calling tasks. Supports ToolCalls, JSON Mode, and Partial Mode.

Moonshot

moonshot-v1-8k-vision-preview

Moonshot V1 8K Vision is Moonshot AI's vision-capable generation model with an 8,192-token context window. It understands image content and outputs text, suited for short-context multimodal chat, image understanding, and tool-calling tasks. Supports ToolCalls, JSON Mode, and Partial Mode.

Neev Cloud

deepseek-v3-2

Balances reasoning capability with output length, designed for Q&A and general agent workflows, optimized for long-context scenarios.

Neev Cloud

glm-4-7

Flagship GLM model with stronger coding, reliable multi-step reasoning, improved agentic workflows, and enhanced front-end generation quality.

Neev Cloud

gpt-oss-120b

OpenAI’s open-weight model designed for powerful reasoning, agentic tasks, and versatile developer use cases.

Neev Cloud

gpt-oss-20b

Compact open-weight Mixture-of-Experts model optimized for cost-efficient deployment and agentic workflows.

Neev Cloud

llama-3.1-8b-instant

Low-latency model suitable for real-time conversational interfaces, content filtering, and general analysis.

Neev Cloud

llama-3.3-70b-versatile

Advanced multilingual large language model optimized for a wide range of natural language tasks with strong performance and efficiency.

Neev Cloud

minimax-m2.7

MiniMax-M2.7 is a high-performance long-context open-weight model optimized for engineering, reasoning, and professional conversational tasks.

Neev Cloud

minimax-m2.7-highspeed

MiniMax-M2.7-highspeed delivers the same performance as MiniMax-M2.7 with significantly faster inference and lower latency.

Open Router

cognitivecomputations/dolphin-mistral-24b-venice-edition:free

ljkjhgfd

Open Router

cognitivecomputations/dolphin3.0-mistral-24b:free

dolphin

Open Router

deepseek/deepseek-chat-v3-0324:free

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.

Open Router

deepseek/deepseek-r1-0528-qwen3-8b:free

DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and Gemini 2.5 Pro.

Open Router

deepseek/deepseek-r1:free

DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.

Open Router

google/gemini-3-flash-preview

bjsdahfkjasjdfk;jso

Open Router

google/gemma-3n-e2b-it:free

mono

Open Router

mistralai/devstral-small-2505:free

wd

Open Router

mistralai/mistral-small-3.2-24b-instruct:free

aed

Open Router

moonshotai/kimi-k2:free

asdc

Open Router

openai/gpt-4o

GPT-4o is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.

Open Router

openai/gpt-5.4-mini

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.

Open Router

qwen/qwen3-coder:free

qwen/qwen3-coder:free

Open Router

tencent/hunyuan-a13b-instruct:free

sadv

Open Router

z-ai/glm-4.5-air:free

qwen/qwen3-coder:free

Auto-router

Openai

gpt-4.1

GPT-4.1 is our flagship model for complex tasks. It is well suited for problem solving across domains.

Auto-router

Openai

gpt-4.1-mini

GPT-4.1 mini provides a balance between intelligence, speed, and cost that makes it an attractive model for many use cases.

Auto-router

Openai

gpt-4.1-nano

GPT-4.1 nano is the fastest, most cost-effective GPT-4.1 model.

Auto-router

Openai

gpt-4o

GPT-4o provides a balance between intelligence, speed, and cost that makes it an attractive model for many use cases.

Auto-router

Openai

gpt-4o-2024-08-06

gpt-4o-2024-08-06 model which is fast, Intelligent model for all purpose tasks. It accepts both text and image inputs, and produces text outputs.

Auto-router

Openai

gpt-4o-mini

GPT-4o mini (“o” for “omni”) is a fast, affordable small model for focused tasks. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is ideal for fine-tuning, and model outputs from a larger model like GPT-4o can be distilled to GPT-4o-mini to produce similar results at lower cost and latency.

Auto-router

Openai

gpt-4o-mini-2024-07-18

gpt-4o-mini-2024-07-18 is a fast, affordable small model for focused tasks. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is ideal for fine-tuning, and model outputs from a larger model like GPT-4o can be distilled to GPT-4o-mini to produce similar results at lower cost and latency.

Auto-router

Openai

gpt-5

GPT-5 model which is fast, Intelligent model for all purpose tasks. It accepts both text and image inputs, and produces text outputs.

Auto-router

Openai

gpt-5-mini

GPT-5-mini model which is fast, Intelligent model for all purpose tasks. It accepts both text and image inputs, and produces text outputs.

Auto-router

Openai

gpt-5-nano

GPT-5-nano model which is fast, Intelligent model for all purpose tasks. It accepts both text and image inputs, and produces text outputs.

Auto-router

Openai

gpt-5.1

GPT-5.1 is a frontier-grade OpenAI model with stronger general-purpose reasoning and better instruction following than GPT-5. It accepts text and image inputs and produces text outputs.

Auto-router

Openai

gpt-5.2

GPT-5.2 is our best general-purpose model, part of the GPT-5 flagship model family. Our most intelligent model yet for both general and agentic tasks

Auto-router

Openai

gpt-5.3-codex

GPT-5.3-Codex is OpenAI's most capable agentic coding model to date, optimized for agentic coding tasks in Codex and similar environments. Supports low/medium/high/xhigh reasoning effort.

Auto-router

Openai

gpt-5.4

GPT-5.4 is our most advanced general-purpose model in the GPT-5 family. Optimized for complex reasoning, long-context agentic workflows, multimodal processing, and superior code generation.

Auto-router

Openai

gpt-5.4-mini

GPT-5.4 mini is a fast, cost-efficient, tool-capable model designed for scalable agent workflows and real-time automation.

Auto-router

Openai

gpt-5.4-nano

GPT-5.4 nano is an ultra-fast, low-cost model optimized for simple tasks, high-scale automation, and lightweight tool usage.

Auto-router

Openai

gpt-5.5

GPT-5.5 is OpenAI's most advanced frontier model, optimized for complex real-world work including agentic reasoning, long-context workflows, tool use, and high-performance code generation. It can plan, execute, and complete multi-step tasks with minimal guidance while maintaining strong context over long durations.

Auto-router

Openai

gpt-5.5-pro

GPT-5.5 Pro uses more compute to think harder and provide consistently better answers.

Auto-router

Openai

gpt-5.6-luna

GPT-5.6 Luna is OpenAI's fastest and most affordable model in the GPT-5.6 family. Built for high-volume, latency-sensitive workloads like chat, classification, and lightweight agentic tasks, it delivers strong reasoning at the lowest cost in the lineup — with a 1M+ token context window and 128K max output.

Auto-router

Openai

gpt-5.6-sol

GPT-5.6 Sol is OpenAI's flagship frontier model for complex reasoning and professional work. 1.05M context, knowledge cutoff Feb 2026.

Auto-router

Openai

gpt-5.6-terra

GPT-5.6 Terra balances intelligence and cost in the GPT-5.6 family. 1.05M context, knowledge cutoff Feb 2026.

Auto-router

Openai

gpt-6-astra

GPT-6 Astra is OpenAI's most capable broadly deployed model, built for the hardest end-to-end work. It excels at complex reasoning, coding, computer use, research, and document creation, and is OpenAI's first model to reach the Critical level of cybersecurity capability under its Preparedness Framework.

Auto-router

Openai

gpt-image-1

GPT Image 1 is a natively multimodal language model that accepts both text and image inputs, and produces image outputs.

Auto-router

Openai

gpt-image-1-mini

A cost-efficient version of GPT Image 1. It is a natively multimodal language model that accepts both text and image inputs, and produces image outputs.

Auto-router

Openai

gpt-image-1.5

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

Auto-router

Openai

gpt-image-2-2026-04-21

You are the world's best creative graphic designer and illustration specialist with industry experience of two decades.

Auto-router

Openai

o1

The o1 series of models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user.

Auto-router

Openai

o3-mini

o3-mini is our newest small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini supports key developer features, like Structured Outputs, function calling, and Batch API.

Auto-router

Openai

o4-mini

o4-mini is our latest small o-series model. It's optimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks.