claude-sonnet-4-20250514

200K context | $15 / MTokens | Direct/Fusion

The hybrid reasoning model further expands the advantages of programming and agent capabilities and provides better support for regional compliance scenarios.

ClaudeCode text Inference FIM

claude-3-7-sonnet-20250219

coding | $15 / MTokens | Direct/Fusion

Claude-3-7-Sonnet-20250219 is an upgraded AI model by Anthropic, released on Feb 19, 2025. It’s easy to use, gives accurate answers, writes well, and works smoothly with tools. Great for daily tasks and work

ClaudeCode text Inference Visual Tools FIM

claude-opus-4-5-20251101

$25 / MTokens | Direct/Fusion

It’s intelligent, efficient, and the best model in the world for coding, agents, and computer use. It’s also meaningfully better at everyday tasks like deep research and working with slides and spreadsheets.

ClaudeCode text Tools Coder

claude-opus-4-1-20250805

coding | $75 / MTokens | Direct/Fusion

It scores 74.5% on SWE - bench Verified for coding. It excels in multi - file refactoring, research, and data analysis. Available on API and platforms, with the same price as Opus 4.

ClaudeCode text image Inference Visual Tools FIM Math

claude-opus-4-20250514

200K context | $75 / MTokens | Direct/Fusion

Hybrid reasoning model supports the execution of tasks with higher complexity, further expanding the advantages of programming and agent capabilities; better support for regional compliance scenarios

ClaudeCode text Inference Visual Tools

claude-sonnet-4-5-20250929

200K context | $15 / MTokens | Direct/Fusion

Anthropic’s top model for agents/coding, boasting 30hrs autonomous task runtime, enhanced programming & computer skills. New "Imagine with Claude" and 200K context. Cost-effective vs peers .

Anthropic text Inference

claude-haiku-4-5-20251001

$5 / MTokens | Direct/Fusion

Claude-Haiku-4-5-20251001 is Anthropic’s latest lightweight AI model, blending cutting-edge performance with exceptional speed and cost-efficiency. It matches Claude Sonnet 4’s capabilities in coding, computer use, and agentic workflows while being over twice as fast and costing just one-third as much.

ClaudeCode text Inference Visual

gpt-5-mini-2025-08-07

$2 / MTokens | Direct/Fusion

GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.

Openai text image Visual

o4-mini-2025-04-16

$4.4 / MTokens | Direct/Fusion

It is a lightweight version of o3, capable of handling text, images and audio. It can intelligently use and combine various tools in ChatGPT. In the AIME 2024 and 2025 math competition questions, its accuracy rates reached 93.4% and 92.7% respectively.

Openai text Inference

gpt-4.1-2025-04-14

gpt-4.1 | $8 / MTokens | Direct/Fusion

It shines in coding, scoring 54.6% on SWE - bench Verified. With a 1 - million - token context window, it handles long texts well. It also follows instructions better, setting new standards in the AI field.

Openai text Inference Tools

gpt-5-mini-2025-08-07

$2 / MTokens | Direct/Fusion

GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.

Azure text image Visual

gpt-4o-2024-11-20

$10 / MTokens | Direct/Fusion

Launched on November 20, 2024, GPT-4o from OpenAI offers 128K context window and up to 16.4K output tokens. With a knowledge cut-off in October 2023, it's better at creative writing and file analysis. Available via API

Openai text Inference

gpt-5.2-chat-latest

$14 / MTokens | Direct/Fusion

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, GPT-5.2 shows improvements over the previous GPT-5.1 in: - General intelligence - Instruction following - Accuracy and token efficiency - Multimodality—especially vision - Code generation—especially front-end UI creation - Tool calling and context management in the API - Spreadsheet understanding and creation

Openai text Inference

gpt-5-chat-latest

$10 / MTokens | Direct/Fusion

GPT-5 Chat points to the GPT-5 snapshot currently used in ChatGPT. We recommend GPT-5 for most API usage, but feel free to use this GPT-5 Chat model to test our latest improvements for chat use cases.

Openai text image Visual

gpt-image-1

$40 / MTokens | Direct/Fusion

GPT - image - 1 is OpenAI's latest image - generation API, launched in April 2025. It is based on the GPT - 4o architecture, excels in high - fidelity image generation with diverse styles, and has strong text - rendering ability.

Openai image Inference

gpt-4o

$10 / MTokens | Direct/Fusion

GPT-4o (“o” for “omni”) is our versatile, high-intelligence flagship model. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is the best model for most tasks, and is our most capable model outside of our o-series models.

Openai text image Visual

o3-mini-2025-01-31

$4.4 / MTokens | Direct/Fusion

a cost - effective reasoning model. It's 24% faster than its predecessors, excels in STEM, especially math, coding, and science. With adjustable reasoning levels, it's available on ChatGPT and API for various user tiers.

Openai text Inference

gpt-4.1-2025-04-14

$8 / MTokens | Direct/Fusion

It shines in coding, scoring 54.6% on SWE - bench Verified. With a 1 - million - token context window, it handles long texts well. It also follows instructions better, setting new standards in the AI field.

Azure text Inference Tools

gpt-4.1-mini-2025-04-14

gpt-4.1-mini | $1.6 / MTokens | Direct/Fusion

by OpenAI is a cost - effective, lightweight model. It uses 60% fewer parameters than GPT - 4o yet keeps 82% of its MMLU score. tasks, ideal for developers and businesses.

Openai text Inference

gpt-4-turbo-2024-04-09

gpt-4 | $30 / MTokens | Direct/Fusion

Released on April 9, 2024, GPT-4-Turbo-2024-04-09 is a notable model by OpenAI. With 128K context, it handles long texts well. It has built - in image understanding, updated 2023 data, and costs $10 per million input tokens and $30 per million output tokens.

Openai text Inference Visual

gpt-5-chat-latest

$10 / MTokens | Direct/Fusion

GPT-5 Chat points to the GPT-5 snapshot currently used in ChatGPT. We recommend GPT-5 for most API usage, but feel free to use this GPT-5 Chat model to test our latest improvements for chat use cases.

Azure text image Visual

gpt-4o-2024-08-06

$10 / MTokens | Direct/Fusion

OpenAI's advanced model. It supports structured output like JSON Schema, which simplifies data generation. It's 50% cheaper for input and 33% for output tokens, making it cost - effective for various tasks.

Azure text Inference

gpt-5.2-2025-12-11

$14 / MTokens | Direct/Fusion

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, GPT-5.2 shows improvements over the previous GPT-5.1 in: - General intelligence - Instruction following - Accuracy and token efficiency - Multimodality—especially vision - Code generation—especially front-end UI creation - Tool calling and context management in the API - Spreadsheet understanding and creation

Openai text Inference

gpt-5.2

$14 / MTokens | Direct/Fusion

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, GPT-5.2 shows improvements over the previous GPT-5.1 in: - General intelligence - Instruction following - Accuracy and token efficiency - Multimodality—especially vision - Code generation—especially front-end UI creation - Tool calling and context management in the API - Spreadsheet understanding and creation

Openai text Inference

gpt-5-2025-08-07

$10 / MTokens | Direct/Fusion

GPT-5 is our flagship model for coding, reasoning, and agentic tasks across domains.

Openai text image Visual

gpt-4o-2024-11-20

$10 / MTokens | Direct/Fusion

Launched on November 20, 2024, GPT-4o from OpenAI offers 128K context window and up to 16.4K output tokens. With a knowledge cut-off in October 2023, it's better at creative writing and file analysis. Available via API

Azure text Inference

gpt-4o-mini

$0.6 / MTokens | Direct/Fusion

a cost-efficient small model by OpenAI. It scores 82% on MMLU, outperforming some models. With 128k context window, it supports text & vision in API, priced affordably for various AI applications.

Openai text image Visual

sora-2

$0.1 / One Times | Direct/Fusion

OpenAI's Sora 2 elevates AI video generation with synchronized audio, enhanced physical realism, and character consistency. It accepts text/images/videos as inputs, offers precise storyboard control, and a mobile app.

Openai video Inference Tools

gpt-5-2025-08-07

$10 / MTokens | Direct/Fusion

GPT-5 is our flagship model for coding, reasoning, and agentic tasks across domains.

Azure text image Visual

gpt-5

$10 / MTokens | Direct/Fusion

OpenAI’s flagship 2025 model (52T params) with 400K context. Excels in math (94.6% AIME), coding (74.9% SWE-bench), and video understanding. Reduces hallucinations, offers tiered pricing, and links Google services .

Openai text Inference

o1-2024-12-17

$60 / MTokens | Direct/Fusion

Compared with the o1-preview version, it has significant improvements in accuracy, efficiency and flexibility, and also has new features such as function calling, vision capabilities and structured outputs.

Openai text Inference

gpt-3.5-turbo-0125

gpt | $1.5 / MTokens | Direct/Fusion

It has a 16K context window, higher accuracy in response formatting, and fixed non - English encoding bugs. With input price cut by 50% and output by 25%, it's great for chatbots, content gen, and code doc tasks.

Openai text Inference

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

$0.6 / MTokens | Direct/Fusion

a cost-efficient small model by OpenAI. It scores 82% on MMLU, outperforming some models. With 128k context window, it supports text & vision in API, priced affordably for various AI applications.

Openai text Inference Visual

gpt-4.1

$8 / MTokens | Direct/Fusion

GPT-4.1 excels at instruction following and tool calling, with broad knowledge across domains. It features a 1M token context window, and low latency without a reasoning step.

Openai text image Visual

o4-mini-2025-04-16

$4.4 / MTokens | Direct/Fusion

It is a lightweight version of o3, capable of handling text, images and audio. It can intelligently use and combine various tools in ChatGPT. In the AIME 2024 and 2025 math competition questions, its accuracy rates reached 93.4% and 92.7% respectively.

Azure text Inference

gpt-4o-2024-08-06

$10 / MTokens | Direct/Fusion

OpenAI's advanced model. It supports structured output like JSON Schema, which simplifies data generation. It's 50% cheaper for input and 33% for output tokens, making it cost - effective for various tasks.

Openai text Inference

gpt-5-mini

$2 / MTokens | Direct/Fusion

GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.

Openai text image Visual

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

$0.6 / MTokens | Direct/Fusion

a cost-efficient small model by OpenAI. It scores 82% on MMLU, outperforming some models. With 128k context window, it supports text & vision in API, priced affordably for various AI applications.

Azure text Inference Visual

gpt-4o-2024-05-13

128K context | $15 / MTokens | Direct/Fusion

It can process text, audio, and images. With a 128K context window, it matches GPT - 4 Turbo on text and code, yet is faster and 50% cheaper on API. It excels in vision and audio understanding.

Openai text Inference

gemini-2.5-pro

$10 / MTokens | Direct/Fusion

DeepMind’s flagship, boasting 1M-token context (upgradable to 2M) and strong multimodality. Excels in math reasoning (92% AIME 2024), coding (63.8% SWE-bench), with 89.8% Global MMLU for multilingual tasks .

GoogleVertexAI text Inference

gemini-3-pro-preview

$12 / MTokens | Direct/Fusion

Gemini 3 is most intelligent model family to date, built on a foundation of state-of-the-art reasoning. It is designed to bring any idea to life by mastering agentic workflows, autonomous coding, and complex multimodal tasks.

GoogleVertexAI text Inference Tools

gemini-3-pro-image-preview

$0.2 / One Times | Direct/Fusion

Gemini 3 is most intelligent model family to date, built on a foundation of state-of-the-art reasoning. It is designed to bring any idea to life by mastering agentic workflows, autonomous coding, and complex multimodal tasks.

GoogleVertexAI text image Visual

gemini-2.5-flash

$2.5 / MTokens | Direct/Fusion

Gemini 2.5 Flash, launched by Google, is a cost - effective model. It can reason before replying, enhancing accuracy. Ideal for large - scale, low - latency, high - data - volume tasks needing thought, it offers adaptable thinking for a balance between performance and cost.

GoogleVertexAI text Inference

veo3.1

$1.5 / One Times | Direct/Fusion

Veo3-Fast, a Google DeepMind AI video generator, turns text/image prompts into 720p videos with synced audio (dialogue, effects) 2x faster than standard Veo3. At ~2-3 mins per clip, it’s 5x more cost-effective, ideal for social content and rapid prototyping globally

GoogleVertexAI video Visual

gemini-2.5-flash-lite

$0.4 / MTokens | Direct/Fusion

DeepMind’s fastest, most cost-efficient 2.5 model (preview 2025), with 1M-token context and multimodality. Excels at high-volume/latency-sensitive tasks (translation, classification), supporting search & code execution .

GoogleVertexAI text Inference