modellen

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for c

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for c

This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text

This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Traini

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with gre

GPT-4-0314 is the first version of GPT-4 released, with a context length of 8,192 tokens, and was supported until June 1

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Train

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Train

The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling,

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exc

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintai

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintai

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON sc

The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored

The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nua

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their

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

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

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It i

GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications

GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed fo

GPT-5 Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improveme

GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by GPT-5 Mini, with GPT Image 1 Mini for effi

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instru

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, a

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved in

GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retain

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designe

GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development

GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance co

GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retai

GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is des

GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance

GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ toke

GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput wor

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabili

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reason

GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workload

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for

A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices an

GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-rea

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mi

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1

The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasonin

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual rea

o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. No

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science,

OpenAI o3-mini-high is the same model as o3-mini with reasoning_effort set to high. o3-mini is a cost-efficient language

The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retain

o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step res

OpenAI o4-mini-high is the same model as o4-mini with reasoning_effort set to high. OpenAI o4-mini is a compact reasonin

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: -

Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - S

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Cod

Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost c

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced perfo

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced perfo

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capa

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning an

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forw

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for c

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) a

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameter

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning a

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is opt

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful c

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It

Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agen

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction followi

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that re

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable respo

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” tr

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understan

Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across i

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images

Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images

Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and re

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understandi

Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visua

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention

The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response t

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear att

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and v

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention me

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attentio

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video inp

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It fea

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion act

Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video inp

Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts ro

Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to Gemini Flash 1.5, while maintainin

Gemini 2.0 Flash Lite offers a significantly faster time to first token (TTFT) compared to Gemini Flash 1.5, while maint

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mat

Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation mode

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cos

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cos

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientifi

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientifi

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientifi

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and c

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the orig

Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemi

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, impro

Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing o

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tie

Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models. Gem

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 12

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 12

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 12

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and ta

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total para

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.

30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available

Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through

Gemini 3.1 Pro Preview routed directly to Google AI Studio with no rate limits.

Gemini 3.5 Flash routed directly to Google AI Studio with no rate limits.

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-f

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter

Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and Al

Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral A

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to

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

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

A 7.3B parameter model that outperforms Llama 2 13B on all benchmarks, with optimizations for speed and context length

This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-availabl

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available

Mistral Large 2 2411 is an update of Mistral Large 2 released together with Pixtral Large 2411 It provides a significant

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities a

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with t

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language mode

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multi

Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accu

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mis

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with ad

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following,

Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unp

Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of Mistral Large 2. The model is able to u

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retain

Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targete

Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in r

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of

Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on com

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning,

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, a

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that oper

Fast-mode variant of Opus 4.6 - identical capabilities with higher output speed at premium 6x pricing. Learn more in Ant

Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the

Fast-mode variant of Opus 4.7 - identical capabilities with higher output speed at premium 6x pricing. Learn more in Ant

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and f

Fast-mode variant of Opus 4.8 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and rea

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflow

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and prof

Claude 5 Sonnet is Anthropic's next-generation model featuring top-tier performance for coding and complex tasks.

Claude 5 Fable is Anthropic's ultra-advanced frontier model optimized for deep thinking and reasoning.

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of

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

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinki

DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B

May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reas

DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from De

DeepSeek R1 Distill Qwen 32B is a distilled large language model based on Qwen 2.5 32B, using outputs from DeepSeek R1.

DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing i

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and ag

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and

DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performanc

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B a

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated par

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was o

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was op

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is f

Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and tex

Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as s

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language process

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-exper

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion p

Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous vers

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Simi

GLM 4 32B is a cost-effective foundation language model. It can efficiently perform complex tasks and has significantly

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-E

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applica

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) ar

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has be

GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across i

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further opt

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workf

GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments suc

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks.

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven ta

Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed Gi

Maestro Reasoning is Arcee's flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32 B tuned with DPO and ch

Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight i

Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixtur

Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance

Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active

Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creat

MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billi

MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. Wit

MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and express

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous i

A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, de

ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model, refined to boost reasoning depth and quality for t

ERNIE-4.5-300B-A47B is a 300B parameter Mixture-of-Experts (MoE) language model developed by Baidu as part of the ERNIE

A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, deliveri

ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B tota

Qianfan-OCR-Fast is a domain-specific multimodal large model purpose-built for OCR. By leveraging specialized OCR traini

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos t

Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, an

Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of model

Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the bes

Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion

Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model develo

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-dire

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX gener

Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the Ope

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, m

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, m

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hy

Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across compl

Note: Sonar Pro pricing includes Perplexity search pricing. See details here For enterprises seeking more advanced capab

Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning

Note: Sonar Pro pricing includes Perplexity search pricing. See details here Sonar Reasoning Pro is a premier reasoning

Euryale 70B v2.1 is a model focused on creative roleplay from Sao10k. - Better prompt adherence. - Better anatomy / spat

Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models,

This is Sao10K's experiment over Euryale v2.2

Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.1

Euryale L3.3 70B is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.2

MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309

MiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified arch

MiMo-V2-Pro is Xiaomi's flagship foundation model, featuring over 1T total parameters and a 1M context length, deeply op

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex softwar

Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It

Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in re

Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong a

Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-

Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and ada

Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual unders

Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities

Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and f

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance acr

command-r-08-2024 is an update of the Command R with improved performance for multilingual retrieval-augmented generatio

command-r-plus-08-2024 is an update of the Command R+ with roughly 50% higher throughput and 25% lower latencies as comp

Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, too

Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute ef

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified mod

Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligenc

Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary w

Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced

UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scena

This model always redirects to the latest model in the Anthropic Claude Haiku family

This model always redirects to the latest model in the Claude Opus family

This model always redirects to the latest model in the Anthropic Claude Sonnet family

Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for

Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, de

Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that

Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situation

Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - wit

WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared t

Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines t

Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents

Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic wor

This model always redirects to the latest model in the Google Gemini Flash family

This model always redirects to the latest model in the Google Gemini Pro family

This model always redirects to the latest model in the OpenAI GPT family

This model always redirects to the latest model in the OpenAI GPT Mini family

Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of mo

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It

Inflection 3 Pi powers Inflection's Pi chatbot, including backstory, emotional intelligence, productivity, and safety. I

Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or preci

Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The mod

Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transform

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generat

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka.

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can

The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant fil

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parame

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use

This model always redirects to the latest model in the MoonshotAI Kimi family

Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and

Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following,

A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract using 4-bit QLoRA finet

Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activat

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet( and Opus

FLUX.2 Flex image generation (Black Forest Labs). Used by the arbi subproduct for ad creatives.

UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, we

Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and o

Rnj-1 is an 8B-parameter, dense, open-weight model family developed by Essential AI and trained from scratch with a focu

One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens

KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-gra

LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment

An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in

DeepSeek V3.1 Nex-N1 is the flagship release of the Nex-N1 series — a post-trained model designed to highlight agent aut

Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It a

INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervise

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) archit

Switchpoint AI's router instantly analyzes your request and directs it to the optimal AI from an ever-evolving library.

A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge

Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active par

Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It d