Model Marketplace

Qwen: Qwen3 Coder 480B A35B (free)

qwen3-coder-free

Text Generation

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-con

Doubao Seed 2.0 Lite

doubao-seed-2.0-lite

Text Generation

256K, balanced performance+cost

Doubao Seed 2.0 Pro

doubao-seed-2.0-pro

Text Generation

256K, vision+tools+reasoning, flagship

OpenAI: GPT Audio

gpt-audio

Text Generation

The gpt-audio model is OpenAIs first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is p

OpenAI: GPT Audio Mini

gpt-audio-mini

Text Generation

A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...

DeepSeek R1

deepseek-r1

Text Generation

Reasoning, chain-of-thought, math/code/science

DeepSeek V4 Pro

deepseek-v4-pro

Text Generation

Latest MoE flagship, 1M context

Google: Lyria 3 Pro Preview

lyria-3-pro-preview

Text Generation

Full-length songs are priced at $0.08 per song. Lyria 3 is Googles family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...

Lyria 3 Pro

lyria-3-pro

Speechaudio

AI music generation, composition+arrangement

Kimi K2.5

kimi-k2.5

Text Generation

200K context, 100-agent cluster, previous flagship

Mistral: Voxtral Small 24B 2507

voxtral-small-24b-2507

Text Generation

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translati

Grok 4.20

grok-4.20

Text Generation

Latest, multi-agent capable

xAI: Grok 4.20 Multi-Agent

grok-4.20-multi-agent

Text Generation

Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesi

Command R

command-r

Text Generation

Efficient RAG LLM

Command R+

command-r-plus

Text Generation

Enterprise RAG LLM, tool use, multilingual

ERNIE Speed

ernie-speed

Text Generation

Fast, cost-effective

Pangu 5.5

pangu-5.5

Image Generationimage

Domestic chip sovereign, industrial verticals

SenseNova V6

sensenova-v6

Text Generation

CV leader, embodied AI, 30+ industrial scenes

Spark X2

spark-x2

Text Generation

Voice interaction leader, education/medical/office

Yi Vision

yi-vision

Image Generationimage

Chinese+English bilingual multimodal

Baichuan M3

baichuan-m3

Text Generation

Chinese LLM, medical/legal vertical focus

StepFun: Step 3.5 Flash

step-3.5-flash

Text Generation

Step 3.5 Flash is StepFuns most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

Step 3.7 Flash

step-3.7-flash

Text Generation

Fast, multimodal terminal agent

Vidu Q1

vidu-q1

Video Generationvideo

VFX+AI sound, 5s 1080p

Tencent: Hunyuan A13B Instruct

hunyuan-a13b-instruct

Text Generation

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers compe

Nova Pro

nova-pro

Text Generation

Balanced performance

WizardLM-2 8x22B

wizardlm-2-8x22b

Text Generation

WizardLM-2 8x22B is Microsoft AIs most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state

Stable Audio Open

stable-audio-open

Speechaudio

44.1kHz stereo, 3-min music gen

SD 3.5 Large

sd3.5-large

Image Generationimage

8B flagship, open weights

FLUX 2 Pro

flux-2-pro

Image Generationimage

Professional

FLUX Schnell

flux-schnell

Image Generationimage

Fastest, Apache 2.0 open

AI21: Jamba Large 1.7

jamba-large-1.7

Text Generation

Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 2

Jamba 1.5

jamba-1.5

Embedding

Mamba-Transformer hybrid, 262K

Sonar Pro

sonar-pro

Text Generation

Search-augmented, 200K, vision

Sonar Reasoning Pro

sonar-reasoning-pro

Text Generation

Multi-step CoT + search

Reka Edge

reka-edge

Text Generation

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leadin

Reka Flash 3

reka-flash-3

Text Generation

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function ca

Inflection: Inflection 3 Pi

inflection-3-pi

Text Generation

Inflection 3 Pi powers Inflections [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like custo

Inflection: Inflection 3 Productivity

inflection-3-productivity

Text Generation

Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines. It has access to recent news. For emotional

LiquidAI: LFM2.5-1.2B-Instruct (free)

lfm-2.5-1.2b-instruct-free

Text Generation

LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference an

LiquidAI: LFM2.5-1.2B-Thinking (free)

lfm-2.5-1.2b-thinking-free

Text Generation

LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K

DBRX Instruct

dbrx-instruct

Text Generation

132B MoE open-source

Snowflake Arctic

snowflake-arctic

Text Generation

Dense-MoE hybrid

InternLM 3

internlm-3

Text Generation

Chinese multimodal open-source flagship

InternVL 2.5

internvl-2.5

Text Generation

Vision-language, image/video/document

MiniCPM 4.0

miniCPM-4.0

Text Generation

On-device, extreme compression, Sparse

Granite 4.1 8B

granite-4.1-8b

Text Generation

IBM Apache 2.0, 12 languages, FIM

Poolside: Laguna M.1 (free)

laguna-m.1-free

Text Generation

Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling an

Poolside: Laguna XS.2 (free)

laguna-xs.2-free

Text Generation

Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai), their efficient coding agent series. It combines tool calling and reasoning capabilities with a co