Every way
to use the major models.

Meta: Muse Spark 1.3

multimodal

Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to k...

GLM-5.3-Flash is the first natively multimodal model in the GLM-5 series with 320B total parameters and 18B active parameters. It incorpo...

GLM-5.3 uses the same base model as GLM-5.2 — every gain comes from post-training. Compared with GLM-5.2, it is much better at complex co...

Qwen: Qwen3.8 Flash

multimodal

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, ...

Z.ai: GLM 5.3 Flash

multimodal

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse a...

granite-4.2-30b

30B

Granite-4.2-30B is the flagship reasoning model in the Granite 4.2 family. It delivers the strongest performance across reasoning-intensi...

granite-4.2-3b

3B

Granite-4.2-3B is the compact reasoning model in the Granite 4.2 family. Despite its small parameter count, it delivers strong performanc...

granite-4.2-8b

9B

Granite-4.2-8B is the mid-size reasoning model in the Granite 4.2 family. It delivers strong performance on reasoning-intensive tasks by ...

Tencent: Hy-MT2-7B

7B

Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language ...

Mistral: Ministral 8B

8B

Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient infere...

Tencent: Hy-MT2-1.8B

8B

Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minori...

Tencent: Hy-MT2-30B-A3B

30B

Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and m...

Qwen: Qwen3.8 27B

27B

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimoda...

Qwen3.8-2.4T-A95B

text

Qwen3.8-2.4T-A95B is Alibaba's most capable Qwen model to date, a 2.4T-parameter sparse MoE with ~95B active parameters. It is built for ...

Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end softwar...

DeepSeek: DeepSeek V4 Pro 0813

text

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Qwen3.8-2.4T-A95B

text

Qwen3.8-2.4T-A95B is Alibaba’s most capable Qwen model to date, a 2.4T-parameter sparse MoE with ~95B active parameters. It is built for ...

Qwen: Qwen3.8 2.4T A95B

text

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-...

NVIDIA-Nemotron-3.5-Lightning

text

NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substa...

NVIDIA: Nemotron 3.5 Lightning

text

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited f...

Nemotron Lightning 3.5 30B A3B

30B

Nemotron-Lightning-3.5-30B-A3B is a 30B-parameter Mixture-of-Experts language model (3B active) from NVIDIA's Nemotron-H family, built on...

Meta: Muse Glimmer 30B

30B

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for a...

Upstage: Solar Pro 4

text

Solar Pro 4 is a large language model from Upstage. It is suited for agentic workflows, office productivity, document-intensive work, and...

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The mode...

Meta: Muse Spark 1.2

multimodal

Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documen...

Qwen: Qwen3.8 Max

multimodal

Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a mul...

DeepSeek: DeepSeek V4 Flash 0731

text

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-tra...

Qwen: Qwen3.7 Flash

multimodal

Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer ...

Meta: Muse Spark 1.1

multimodal

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documen...

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and...

Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative g...

Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a colla...

Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text an...

Tencent: Hy3

text

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic w...

Ornith-1.0-35B is DeepReinforce's open (MIT-licensed) agentic-coding model: an RL post-train of Qwen3.5-35B-A3B, a 35B-total / ~3B-active...

Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 archit...

GLM-5.2 introduces a robust 1M-token context and advanced, multi-effort coding capabilities to significantly enhance performance on long-...

Z.ai: GLM 5.2

text

GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks. With a truly usable 1M-token context window, it can handle project-le...

Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding ta...

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reli...

NVIDIA-Nemotron-3-Ultra-550B-A55B

550B

Nemotron 3 Ultra is built for, frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It deli...

NVIDIA: Nemotron 3 Ultra

550B

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (...

Nemotron-Content-Safety-3.5

multimodal

Nemotron Content Safety 3.5 is a multimodal safety classifier developed by NVIDIA. A compact safety model that handles text, images, and...

Qwen: Qwen3.7 Plus

multimodal

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the se...

MiniMax: MiniMax M3

multimodal

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context ...

StepFun: Step 3.7 Flash

multimodal

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with ...

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

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

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

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

A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract using 4-bit QLoRA finetuning provided by...

AllenAI: Olmo 3 32B Think

32B

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

Arcee AI: Coder Large

text

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

Arcee AI: Maestro Reasoning

text

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

Arcee AI: Spotlight

1B

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

Arcee AI: Trinity Large Thinking

399B

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

Arcee AI: Trinity Mini

text

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

Arcee AI: Virtuoso Large

text

Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and e...

Baidu: ERNIE 4.5 21B A3B

21B

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

Baidu: ERNIE 4.5 21B A3B Thinking

21B

ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model, refined to boost reasoning depth and quality for top-tier performan...

Baidu: ERNIE 4.5 300B A47B

300B

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

Baidu: ERNIE 4.5 VL 28B A3B

28B

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

Baidu: ERNIE 4.5 VL 424B A47B

424B

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

Baidu: Qianfan-OCR-Fast

multimodal

Qianfan-OCR-Fast is a domain-specific multimodal large model purpose-built for OCR. By leveraging specialized OCR training data while pre...

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

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

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

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

UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobil...

Deep Cogito: Cogito v2.1 671B

671B

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

DeepSeek-V3-0324

671B

DeepSeek-V3-0324, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token, an impro...

DeepSeek-V3.1

text

DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase l...

DeepSeek: DeepSeek V3

689B

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

DeepSeek: DeepSeek V3 0324

689B

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

DeepSeek: DeepSeek V3.1

689B

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

DeepSeek: DeepSeek V3.1 Terminus

689B

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities whi...

DeepSeek: DeepSeek V3.2

689B

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

DeepSeek: DeepSeek V3.2 Speciale

text

DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on D...

DeepSeek: DeepSeek V4 Flash

292B

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

DeepSeek: DeepSeek V4 Pro

1602B

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

DeepSeek: R1 0528

671B

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced an...

EssentialAI: Rnj 1 Instruct

text

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

GLM-5.1 is Z.ai's next-generation flagship model built for agentic engineering, with stronger coding capabilities and sustained performan...

GLM-4.5-Flash

text

Lowest-latency, lowest-cost variant of GLM-4.5 on z.ai.

GLM-4.6

355B

Incremental upgrade on GLM-4.5 — improved reasoning, same context window.

GLM-4.7

9B

Mid-generation GLM 4.7 released between GLM-4.6 and GLM-5.

GLM-5

355B

Zhipu's GLM 5 generation — closed flagship between GLM-4.7 and GLM-5.1.

GLM-5 Turbo

text

Faster, cheaper sibling of GLM-5 on z.ai.

GLM-5.1

32B

Zhipu's GLM 5.1 series — successor to GLM-5 on z.ai's API.

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better rolepl...

IBM: Granite 4.0 Micro

3B

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 models released by ...

IBM: Granite 4.1 8B

8B

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-t...

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

Kimi K2.5 is Moonshot AI's flagship agentic model and a new SOTA open model. It unifies vision and text, thinking and non-thinking modes,...

Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven d...

Kwaipilot: KAT-Coder-Pro V2

text

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

Euryale 3.1 - 70B v2.2 is a model focused on creative roleplay from Sao10k

LiquidAI: LFM2-24B-A2B

24B

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

Llama Guard 3 8B

8B

Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be u...

Llama-3.2-11B-Vision-Instruct

11B

Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It exc...

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anth...

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

DeepSeek: DeepSeek V4.1 Flash

multimodal

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED)...

DeepSeek V4.1 Flash

multimodal

DeepSeek-V4.1-Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters that natively processes images and text at up ...

Ember-1 is a specialized model from Fireworks. Built on Kimi K3, it produces shorter reasoning traces, using approximately 40% fewer toke...

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, ...

Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters ou...

The multimodal version built on Ling-3.0-flash — 124B total / ~5.5B active per token, with native text, image, and video understanding. I...

NVIDIA: Nemotron 3.5 Content Safety

multimodal

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. I...

Qwen: Qwen3.8 Max (0902)

multimodal

Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model ...

Meta-Llama-3.1-70B-Instruct

70B

Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned g...

Meta-Llama-3.1-8B-Instruct

8B

Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned g...

Meta: Llama 3 70B Instruct

70B

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

Meta: Llama 3 8B Instruct

8B

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

Meta: Llama 4 Maverick

402B

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

Meta: Llama 4 Scout

109B

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

Meta: Llama Guard 4 12B

12B

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous v...

Microsoft: Phi 4 Mini Instruct

4B

Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high...

MiniMax M2.7

456B

Mixture-of-Experts language model. M2.7 is capable of building complex agent harnesses and completing highly elaborate productivity tasks...

MiniMax-M2.5

text

MiniMax M2.5 is built for state-of-the-art coding, agentic tool use, search, and office work, extensively trained with reinforcement lear...

MiniMax: MiniMax M1

456B

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

MiniMax: MiniMax M2

456B

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion acti...

MiniMax: MiniMax M2-her

text

MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn co...

MiniMax: MiniMax M2.1

230B

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

MiniMax: MiniMax M2.5

230B

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

MiniMax: MiniMax M2.7

230B

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

MiniMax: MiniMax-01

457B

MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, wi...

Mistral Large

text

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

Mistral Large 2407

text

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

Mistral-Nemo-Instruct-2407

text

12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.

Mistral-Small-3.2-24B-Instruct-2506

24B

Mistral-Small-3.2-24B-Instruct is a drop-in upgrade over the 3.1 release, with markedly better instruction following, roughly half the in...

Mistral: Codestral 2508

text

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

Mistral: Devstral 2 2512

128B

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...

Mistral: Devstral Medium

24B

Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Posit...

Mistral: Devstral Small 1.1

24B

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

Mistral: Ministral 3 14B 2512

14B

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

Mistral: Ministral 3 3B 2512

3B

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

Mistral: Ministral 3 8B 2512

8B

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

Mistral: Mistral 7B Instruct v0.1

7B

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

Mistral: Mistral Large 3 2512

multimodal

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

Mistral: Mistral Medium 3

multimodal

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

Mistral: Mistral Medium 3.1

multimodal

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to del...

Mistral: Mistral Medium 3.5

multimodal

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

Mistral: Mistral Small 3

24B

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

Mistral: Mistral Small 3.1 24B

24B

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

Mistral: Mistral Small 3.2 24B

24B

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

Mistral: Mistral Small 4

121B

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

Mistral: Pixtral Large 2411

multimodal

Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral Large 2](/mistralai/mistral-large-2411). The mo...

Mistral: Saba

text

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

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model d...

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

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

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

NVIDIA-Nemotron-3-Super-120B-A12B

120B

NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent ...

NVIDIA: Llama 3.3 Nemotron Super 49B V1.5

49B

Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct wit...

NVIDIA: Nemotron 3 Nano 30B A3B

30B

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

NVIDIA: Nemotron 3 Super

120B

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

NVIDIA: Nemotron Nano 9B V2

9B

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

Nemotron-3-Nano-Omni-30B-A3B-Reasoning

30B

Nemotron 3 Nano Omni is an open multimodal model built on a hybrid Mixture-of-Experts (MoE) architecture, engineered for high efficiency ...

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

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better rolepl...

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

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

Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Datas...

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

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

Qwen3-235B-A22B-Instruct-2507

235B

Qwen3-235B-A22B-Instruct-2507 is the updated version of the Qwen3-235B-A22B non-thinking mode, featuring Significant improvements in gene...

Qwen3.5-0.8B

8B

Qwen3.5-0.8B is Alibaba's smallest model in the Qwen3.5 series, featuring a hybrid Gated Delta Networks and sparse Mixture-of-Experts arc...

Qwen3.5-2B

2B

Qwen3.5-2B is a compact yet capable model from Alibaba's Qwen3.5 series. It features a 262K token context window, support for 201 languag...

Qwen3.5-4B

4B

Qwen3.5-4B is a mid-size model from Alibaba's Qwen3.5 series that delivers a strong balance of performance and efficiency. It features a ...

Qwen: Qwen Plus 0728

text

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, an...

Qwen: Qwen-Plus

text

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

Qwen: Qwen2.5 7B Instruct

7B

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

Qwen: Qwen2.5 VL 72B Instruct

72B

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

Qwen: Qwen3 14B

14B

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

Qwen: Qwen3 235B A22B

235B

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supp...

Qwen: Qwen3 235B A22B Instruct 2507

235B

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

Qwen: Qwen3 235B A22B Thinking 2507

235B

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

Qwen: Qwen3 30B A3B

30B

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

Qwen: Qwen3 30B A3B Instruct 2507

30B

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

Qwen: Qwen3 30B A3B Thinking 2507

30B

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

Qwen: Qwen3 32B

32B

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

Qwen: Qwen3 8B

8B

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

Qwen: Qwen3 Coder 30B A3B Instruct

30B

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

Qwen: Qwen3 Coder 480B A35B

480B

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

Qwen: Qwen3 Coder Flash

text

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

Qwen: Qwen3 Coder Next

480B

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

Qwen: Qwen3 Coder Plus

text

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

Qwen: Qwen3 Max

235B

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

Qwen: Qwen3 Max Thinking

text

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi...

Qwen: Qwen3 Next 80B A3B Instruct

80B

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thi...

Qwen: Qwen3 Next 80B A3B Thinking

80B

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

Qwen: Qwen3 VL 235B A22B Instruct

235B

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

Qwen: Qwen3 VL 235B A22B Thinking

235B

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

Qwen: Qwen3 VL 30B A3B Instruct

30B

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

Qwen: Qwen3 VL 30B A3B Thinking

30B

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

Qwen: Qwen3 VL 32B Instruct

32B

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

Qwen: Qwen3 VL 8B Instruct

8B

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

Qwen: Qwen3 VL 8B Thinking

8B

Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual rea...

Qwen: Qwen3.5 397B A17B

397B

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

Qwen: Qwen3.5 Plus 2026-02-15

multimodal

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

Qwen: Qwen3.5 Plus 2026-04-20

235B

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

Qwen: Qwen3.5-122B-A10B

122B

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

Qwen: Qwen3.5-27B

27B

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

Qwen: Qwen3.5-35B-A3B

35B

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

Qwen: Qwen3.5-9B

9B

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

Qwen: Qwen3.5-Flash

multimodal

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

Qwen: Qwen3.6 27B

27B

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

Qwen: Qwen3.6 35B A3B

35B

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

Qwen: Qwen3.6 Flash

multimodal

Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M toke...

Qwen: Qwen3.6 Plus

multimodal

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling s...

Qwen: Qwen3.7 Max

text

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric worklo...

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

Reka Edge

7B

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

Reka Flash 3

21B

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

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

The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user re...

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

This is [Sao10K](/sao10k)'s experiment over [Euryale v2.2](/sao10k/l3.1-euryale-70b).

Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3...

Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B ...

Euryale 70B v2.1 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). - Better prompt adherence. - Better ana...

Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and mo...

A coding model optimized for real-world development environments, with reliable tool use in common IDEs such as Claude Code. It delivers ...

Built for the Agent era, it delivers stable performance in complex reasoning and long-horizon tasks, including multi-step planning, visua...

StepFun: Step 3.5 Flash

199B

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

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

Tencent: Hunyuan A13B Instruct

80B

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B ...

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

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

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

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

Tongyi DeepResearch 30B A3B

30B

Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billio...

Upstage: Solar Pro 3

text

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

WizardLM-2 8x22B

22B

WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprie...

Writer: Palmyra X5

70B

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

Xiaomi: MiMo-V2-Flash

7B

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

Xiaomi: MiMo-V2-Omni

multimodal

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

Xiaomi: MiMo-V2-Pro

text

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

Xiaomi: MiMo-V2.5

315B

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

Xiaomi: MiMo-V2.5-Pro

65B

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

Z.ai: GLM 4 32B

32B

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

Z.ai: GLM 4.5V

9B

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 1...

Z.ai: GLM 4.6V

108B

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

Z.ai: GLM 4.7 Flash

31B

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

Z.ai: GLM 5V Turbo

multimodal

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

gemini-3.1-pro

multimodal

Bring any idea to life with state-of-the-art reasoning to help you learn, build, and plan anything. Best for complex tasks and bringing c...

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

Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-w...

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

Long-horizon coding + autonomous-execution upgrade over K2.5.

Multimodal agentic variant — adds a vision encoder to the K2 backbone.

Moonshot's open-weight reasoning variant — extended chain-of-thought training on top of Kimi K2.

GPT-OSS 120B

120B

OpenAI's first open-weight LLM in years — Apache-licensed MoE.

GPT-OSS 20B

20B

20B GPT-OSS — single-GPU local target.

GLM-4.5

355B

Zhipu's frontier open-weight MoE — 355B total, 32B active. Strong agentic + reasoning marks for an open model.

GLM-4.5-Air

106B

Smaller, cheaper sibling of GLM-4.5. 106B total, 12B active.

Moonshot's frontier open-weight MoE — 1T total, 32B active.

Qwen 3 235B

235B

Alibaba's frontier MoE — 235B total / 22B active.

Qwen 3 32B

33B

Dense 32B Qwen 3.

Gemma 3 12B

12B

12B Gemma 3 — multimodal, single-GPU target.

Gemma 3 1B

1B

1B Gemma 3 — edge / mobile.

Gemma 3 27B

27B

Google's open-weight multimodal LLM — efficient and license-permissive.

Gemma 3 4B

4B

4B Gemma 3 — laptop multimodal.

DeepSeek R1

671B

DeepSeek's reasoning model — RL-trained, frontier-class, MIT-licensed.

DeepSeek R1 Distill Llama 70B

70B

70B Llama distilled from DeepSeek R1's reasoning traces.

DeepSeek R1 Distill Qwen 1.5B

2B

Tiny distilled R1 — phone / browser deployable.

DeepSeek R1 Distill Qwen 14B

15B

14B distilled R1 — laptop-friendly reasoning.

DeepSeek R1 Distill Qwen 32B

33B

32B Qwen base distilled from DeepSeek R1.

DeepSeek R1 Distill Qwen 7B

8B

7B distilled R1 — runs on any modern GPU.

MiniMax-Text-01

456B

MiniMax's first open MoE — 456B total, 45.9B active. 1M+ context via Lightning Attention.

OLMo 3 7B

7B

Allen AI's latest fully-open OLMo — model + training data + checkpoints.

DeepSeek V3

671B

DeepSeek's flagship MoE — 671B total, 37B active, frontier-class.

IBM Granite 3.1 8B

8B

IBM's enterprise-focused open-weight LLM.

Phi-4

15B

Microsoft's 14B small-LM workhorse — punches above its weight.

Llama 3.3 70B

70B

Meta's best-in-class open-weight LLM — 70B class.

Qwen 2.5 Coder 32B

33B

Alibaba's open-weight coding model — best in class for 32B.

Hunyuan-Large

389B

Tencent's open-weight MoE — 389B total, 52B active. Largest open MoE at launch.

Stable Diffusion 3.5 Medium

3B

2.5B SD 3.5 — fits on 12 GB consumer GPUs.

Stable Diffusion 3.5 Large

8B

Stability AI's latest open-weight image-gen — 8.1B params, MMDiT architecture.

Yi-Lightning

text

01.AI's fastest production model. Tops the LMSYS Arena Chinese leaderboard.

Llama 3.2 11B Vision

11B

Meta's open-weight multimodal LLM — vision + text in 11B.

Llama 3.2 1B

1B

Meta's smallest Llama — mobile + on-device target.

Llama 3.2 3B

3B

3B Llama — laptop-class chat + RAG.

Llama 3.2 90B Vision

90B

Meta's largest vision-capable Llama.

Qwen 2.5 14B

15B

14B Qwen 2.5 — sweet spot for single-GPU local hosting.

Qwen 2.5 32B

33B

32B Qwen 2.5 — laptop-class workhorse.

Qwen 2.5 3B

3B

3B Qwen 2.5 — laptop / edge target.

Qwen 2.5 72B

73B

Alibaba's flagship open-weight LLM — 72B dense.

Qwen 2.5 7B

8B

7B Qwen 2.5 — most popular Qwen variant on Ollama.

Command R+

104B

Cohere's open-weight RAG-optimized LLM — multilingual + tool use.

Phi-3.5 Mini

4B

3.8B Phi — laptop / edge target.

Nous Research's flagship Llama fine-tune — agent-friendly.

FLUX.1 Dev

12B

Open-weight FLUX.1 — non-commercial license.

FLUX.1 Pro

12B

Black Forest Labs' flagship image-gen model — closed/API.

FLUX.1 Schnell

12B

Distilled fast FLUX.1 — Apache-2.0, commercial-friendly.

Gemma 2 2B

3B

Tiny 2B Gemma 2 — laptop / mobile.

Mistral Large 2

123B

Mistral's flagship open-weight model — 123B dense.

Llama 3.1 405B

405B

Meta's largest open-weight LLM — dense 405B, frontier-class at launch.

Llama 3.1 70B

70B

Llama 3.1 70B — production workhorse, superseded by 3.3 but still widely deployed.

Llama 3.1 8B

8B

Meta's most popular open-weight small LLM — fits anywhere.

Mistral Nemo 12B

12B

Mistral × Nvidia collab — 12B Apache-licensed, multilingual.

InternLM 2.5 20B

20B

Shanghai AI Lab's dense 20B open-weight. Strong long-context + tool use for its size.

Gemma 2 27B

27B

Google's pre-Gemma-3 open-weight workhorse.

Gemma 2 9B

9B

9B Gemma 2 — single-GPU local target.

DeepSeek Coder V2 236B

236B

DeepSeek's MoE coding model — 236B total, 21B active.

DeepSeek Coder V2 Lite

16B

16B MoE / 2.4B active — laptop-class coder.

Mistral 7B v0.3

7B

The current Mistral 7B — adds function calling + extended vocab.

Mixtral 8x22B

141B

Mistral's open MoE — 141B total, 39B active.

Mistral 7B v0.2

7B

Mistral 7B v0.2 — earlier 32K context revision.

mxbai-embed-large

0B

335M embedding model — top MTEB scores for its size.

Moondream 1.8B

2B

Tiny multimodal — laptop-class image understanding.

Nomic Embed Text

0B

Open embedding model — 69M Ollama pulls, the local default.

LLaVA 34B

34B

Largest open-weight LLaVA — vision encoder + Yi-34B backbone.

Multilingual + multifunctional embedding (100+ languages).

Code Llama 70B

70B

Meta's largest code-specialised Llama.

TinyLlama 1.1B

1B

1.1B Llama-arch model — 3T training tokens.

Whisper Large v3

2B

OpenAI's open-weight speech-to-text — the standard transcription model.

Yi-34B

34B

Earlier open-weight Yi release — bilingual EN/ZH, 32K-token context.

Mistral 7B v0.1

7B

Original Mistral 7B — historical reference.

Baichuan2-13B

13B

Bilingual EN/ZH open-weight. Strong for its size on Chinese-language benchmarks.

Stable Diffusion XL

4B

Workhorse open-weight image-gen — 3.5B params, runs anywhere.

Whisper Base

0B

74M Whisper — browser / Raspberry Pi-deployable.

Whisper Medium

1B

769M Whisper variant — half the size of Large, 80% of the accuracy.

Whisper Small

0B

244M Whisper — fits on edge GPUs and CPU.

Whisper Tiny

0B

39M Whisper — runs in-browser via WebGPU.

Stable Diffusion 1.5

1B

The original viral image-gen model — still searched heavily.

Meta: Muse Spark 1.3 Contributor

multimodal

Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and...

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, ...

Tencent: Hy4 preview

text

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding ...

DeepSeek: DeepSeek V4 Flash Vision Exp

multimodal

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepsee...

Meta: Muse Spark 1.2 Contributor

multimodal

Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. ...

gemma-4-31B-it-Ultra

31B

Ultra speed version of gemma-4-31B-it

gpt-oss-120b-Ultra

120B

Ultra fast version of gpt-oss-120b

Speed-optimized MiniMax-M2.7

NVIDIA Nemotron 3 Ultra NVFP4

text

Nemotron-3-Ultra-550B-A55B-NVFP4 is a frontier-scale large language model (LLM) trained by NVIDIA, designed to deliver strong agentic, re...

NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

550B

Nemotron 3 Ultra is built for, frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It deli...

DeepSeek: DeepSeek V3.2 Exp

671B

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

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

Qwen3-Coder-480B-A35B-Instruct-Turbo

480B

Qwen3-Coder-480B-A35B-Instruct is the Qwen3's most agentic code model, featuring Significant Performance on Agentic Coding, Agentic Brows...

Qwen: Qwen3.6 Max Preview

text

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

Tencent: Hy3 preview

299B

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

gemma-4-31B-it-turbo

31B

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input and generating te...