AI Model Catalog

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.

This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o ("o" for "omni") is...

The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...

OpenAI GPT-5 chat-tuned, non-reasoning variant — fast vision + chat (no reasoning-mode latency). Points at OpenAI's gpt-5-chat-latest moving alias.

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...

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...

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,...

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...

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...

GPT-5.6 Luna is OpenAI's cost-optimized GPT-5.6 model for high-volume, latency-sensitive workloads. It keeps strong reasoning, a 1,050,000 token context window, and text and image input at the lowest price in the family, and it corresponds to the nano tier of earlier GPT-5 families. Served direct from OpenAI.

GPT-5.6 Sol is the frontier model in OpenAI's GPT-5.6 family, built for complex professional work that demands the highest reasoning. It supports reasoning tokens, a 1,050,000 token context window, and text and image input, and it corresponds to the unsuffixed tier of earlier GPT-5 families. Served direct from OpenAI.

GPT-5.6 Terra is OpenAI's GPT-5.6 model that balances intelligence and cost, with higher reasoning for everyday production workloads. It supports reasoning tokens, a 1,050,000 token context window, and text and image input, and it corresponds to the mini tier of earlier GPT-5 families. Served direct from OpenAI.

OpenAI GPT Image 2 — text-to-image with strong text rendering and instruction following.

GPT-OSS 120B is OpenAI's large open-weight model — strong reasoning and tool use at low cost.

GPT-OSS 20B is OpenAI's compact open-weight model for fast, inexpensive chat and agents.

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...

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,...

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

Google Gemini 3 Pro Image — higher-quality text-to-image generation.

Gemini 3 Pro Image, image-to-image edit variant.

Google Gemini 3.1 Flash Image — fast text-to-image generation with strong text rendering.

Gemini 3.1 Flash Image, image-to-image edit variant.

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Successor to Nano Banana — improved fidelity at a modest cost.

Image-to-image edit with Nano Banana 2.

High-quality text-to-image generation. Premium output, slower than base Nano Banana.

Image-to-image edit at Nano Banana Pro quality.

Google Veo 3.1 text-to-video. 720p/1080p, standard tier. With-audio and 4K cost more.

Google Veo 3.1 Fast — half the cost of standard Veo 3.1 (1080p without audio).

Veo 3.1 Fast image-to-video. Cheaper, quicker alternative for animating images.

Google Veo 3.1 image-to-video. Animate a still image with strong temporal coherence.

Veo 3.1 Lite — the cheapest Veo 3.1 tier; ideal for quick iteration.

Seedance 2.0 fast tier — animate a still image quickly and cheaply.

Seedance 2.0 fast tier — reference-image-guided video at the lower fast-tier rate.

Seedance 2.0 fast tier — text-to-video at lower cost and faster turn-around (720p).

ByteDance Seedance 2.0 image-to-video, standard tier. Animate a still into video.

ByteDance Seedance 2.0 reference-to-video. Use a reference image as style/subject anchor.

ByteDance Seedance 2.0 text-to-video, standard tier. Strong motion and prompt fidelity.

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...

Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral Large 2](/mistralai/mistral-large-2411). The model is able to understand documents, charts and natural images. The model is...

Qwen3 coding specialist (480B-class) with a 1M-token context window. Served direct from Alibaba Cloud Model Studio.

Alibaba's flagship Qwen3 model. Strongest reasoning and instruction following in the Qwen family. Served direct from Alibaba Cloud Model Studio.

Fast, low-cost Qwen3 vision-language model. Served direct from Alibaba Cloud Model Studio.

Qwen3 vision-language model — image understanding plus text generation. Served direct from Alibaba Cloud Model Studio.

Fast, low-cost Qwen3.5 with a 1M-token context window. Served direct from Alibaba Cloud Model Studio.

Balanced flagship-tier Qwen3.5 with a 1M-token context window. Served direct from Alibaba Cloud Model Studio.

Fast, low-cost Qwen3.6 vision-language model — strong agentic coding and reasoning, 1M-token context. A capable step up from 3.5 Flash. Served direct from Alibaba Cloud Model Studio.

Newest Qwen3.7 flagship — strongest agent-level reasoning, coding, and long-horizon execution. Text-only, 1M-token context. Served direct from Alibaba Cloud Model Studio.

Cost-effective Qwen3.7 with full vision-language and agent capabilities. Image+text+video in, 1M-token context. Served direct from Alibaba Cloud Model Studio.

Anthropic's most capable widely released model — most demanding reasoning and long-horizon agentic work. Adaptive thinking always on, 1M-token context. Served direct via the Claude API.

Text-to-image generation — the FLUX.2 base model. Strong prompt adherence and broad style range.

Higher-fidelity FLUX.2 Pro text-to-image. Better detail and prompt adherence than base.

Image-to-image edit at FLUX.2 Pro quality.

Image-to-image edit with FLUX.2 — refine, restyle, or extend an existing image.

xAI Grok's text-to-image generator. Inexpensive default tier.

xAI Grok Imagine — image-to-image edit at the default tier.

Grok Imagine 'Quality' tier — image-to-image edit at higher quality.

Grok Imagine 'Quality' tier — higher-fidelity text-to-image, $0.05/image at 1K.

Grok Imagine image-to-video. $0.07/sec at 720p.

Grok Imagine reference-image-guided video generation.

xAI Grok Imagine video model. $0.07/sec at 720p (480p is $0.05/sec).

Kling o3 Pro image-to-video — newer Kling line, premium quality.

Kling 3.0 Pro image-to-video. Animate a still at pro quality.

Kling 3.0 Pro text-to-video. High-fidelity motion and detail at the pro tier.

Kling 3.0 Standard image-to-video — same v3 model, cheaper standard tier.

ElevenLabs Eleven v3 expressive TTS

ElevenLabs Multilingual v2 narration

ElevenLabs Turbo v2.5 low-latency TTS

GLM 4.7 is a balanced, cost-effective Z.AI model for general chat, coding, and tools.

GLM 4.7 Flash is Z.AI's fast, low-cost tier for high-volume chat and lightweight agents.

GLM 5 is Z.AI's flagship model with strong reasoning, coding, and agentic tool use.

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

MiniMax M2.5 is a capable, cost-efficient general-purpose model with a 196K context window.

Kimi K2 Thinking is Moonshot AI's reasoning model that thinks step-by-step before answering.

Kimi K2.5 is Moonshot AI's strong agentic model with a 256K context window and tool use.