Model directory

Extract

Scaledown

0

Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want

Summarize

Scaledown

0

Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifti

Muse Wonder

Meta

0

Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, aud

Step 5 Preview

StepFun

0

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). I

Claude Haiku 5.5

Anthropic

0

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds

Mistral Large 4

Mistral AI

0

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a

Nano Banana 2.1

Google

0

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pr

Ling 3.1 Flash

Inclusionai

0

Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.

Apodex 1.1 Mini (free)

Apodex

0

Apodex 1.1 Mini is a reasoning-first model from Apodex, built for complex, long-horizon research and forecasting tasks. It works directly with files,

Pareto 26.10 Preview

Unbiased

0

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad r

GPT-6.1 Sol

OpenAI

0

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, co

GPT-6.1 Sol Pro

OpenAI

0

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost

Claude Sonnet 5.5

Anthropic

0

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially st

Jev Router

Typesafe

0

Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on Jev, TypeSafe's first System One

Perceptron Mk1.5

Perceptron

0

Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text p

Ember-1

Fireworks

0

Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter

Aion 3.5

AionLabs

0

Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation pro

Aion 3.5 Mini

AionLabs

0

Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sib

GLM 5.3 Prime

Z.AI

0

GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through infe

Qwen3.8 Max Prime

Qwen

0

Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts

Solar Mini 4

Upstage

0

Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context wind

Space Bunny Alpha

Stealth

0

Space Bunny Alpha is an anonymous large model with blazing-fast inference, strong coding capabilities and native multimodal input support. It delivers

Claude Opus 5.5

Anthropic

1

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particul

Command A+

Cohere

0

Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native t

GPT-6 Luna

OpenAI

0

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive

GPT-6 Luna Pro

OpenAI

0

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost n

GPT-6 Sol

OpenAI

0

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier.

GPT-6 Sol Pro

OpenAI

0

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost not

Grok 4.7

xAI

0

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running so

MiMo-V2.6-Flash

Xiaomi

0

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B

MiMo-V2.6-Pro

Xiaomi

0

MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capa

MiMo-V2.6-Pro-UltraSpeed

Xiaomi

0

MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoi

Qwen3.8 Omni Flash

Qwen

0

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video under

Switchyard

NVIDIA

0

Switchyard is an open-source model router that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter ma

GLM 5.3 FlashX

Z.AI

0

GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built o

Ternary Bonsai 2 27B

Prism Ml

0

Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image unders

Pareto

Unbiased

0

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad r

Union Alpha

Stealth

0

Union Alpha is a multimodal model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range

Schematron V2 Small

Inference Net

0

Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long

Schematron V2 Turbo

Inference Net

0

Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads

Fugu Max

Sakana

0

Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration

Fugu Ultra v2

Sakana

0

Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchest

DeepSeek V4.1 Flash

DeepSeek

0

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) architecture

Ling 3.0 Flash VL

Inclusionai

0

Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while addi

Mercury 2.5

Inception

0

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

Nex-N2.5-Mini

Nex Agi

0

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: i

Nex-N2.5-Mini (free)

Nex Agi

0

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: i

Nex-N2.5-Pro

Nex Agi

0

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: i