Qwen 3 Coder 480B A35B Instruct FP8

GLM 5

GLM-5 is an open-source model for architect-level, long-horizon systems engineering and programming.

xAI

Grok 4

An enhanced Grok 4 model with extended context capacity, supporting programming and technology domains with reasoning capabilities.

xAI

Grok 3

A Grok 3 model optimized for conversational AI tasks, emphasizing responsive dialogue and tool support.

Qwen 3 Next 80B A3B Thinking

Thinking-optimized 80B variant with stronger multi-step reasoning.

Qwen 3 Coder 480B A35B Instruct FP8

Ultra-large coding-focused model built for advanced software and debugging tasks.

Qwen 3 235B A22B Thinking 2507

Reasoning-optimized 235B model with high analytical strength.

Qwen 3 Next 80B A3B Instruct

Next-gen 80B model offering strong reasoning and versatile knowledge at lower cost.

Qwen 2.5 72B Instruct Turbo

High-capability Turbo model delivering strong general-purpose performance.

Qwen 2.5 7B Instruct Turbo

Fast and cost-efficient 7B Turbo model for lightweight language tasks.

GPT OSS 120B

Open-source large-scale language model for high-quality reasoning and generation.

Qwen 3 235B A22B Instruct 2507 TPUT

Cost-optimized variant of the 235B model for high-throughput general instruction tasks.

Qwen 3 235B A22B FP8 TPUT

Throughput-optimized 235B model delivering high-volume performance at reduced cost.

Qwen 3 32B

A third-generation, 32B-parameter Qwen model optimized for tasks in the health category, supporting complex reasoning and workflows.

GPT-5 Nano

The fastest, cheapest version of GPT-5. It's great for summarization and classification tasks.

GPT-5 Mini

The faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.

GPT-5.2

OpenAI's flagship model for coding and agentic tasks across industries.

GPT OSS 20B

GPT-OSS-20B is a 21B Apache 2.0 model delivering strong reasoning with efficient single-GPU performance.

GPT-4 Turbo

A turbocharged GPT-4 variant focused on high-speed text generation with enhanced tool integration and large context handling.

GPT-5

An intelligent reasoning model for coding and agentic tasks with configurable reasoning effort.

GPT-4o

A multimodal GPT model with strong finance domain focus, capable of handling text and image inputs for complex information processing.

Moonshot

Kimi K2.5

Kimi K2.5 is Moonshot AI’s top open-source reasoning model with SOTA performance and 2× faster INT4 inference.

Moonshot

Kimi K2 Thinking

Reasoning-oriented variant optimized for multi-step problem solving.

GPT-4o Mini

A smaller, versatile GPT model optimized for multimodal finance, marketing, academic, SEO, and translation tasks with efficient outputs.

GPT-4.1

A GPT-4.1 model with extensive multi-domain support, optimized for programming, science, technology, legal, health, and academic tasks.

Mistral

Mistral Small 3

A 24B model matching top compact models, with larger versions up to 70B—ideal for chat, support, translation, and summarization.

Moonshot

Kimi K2 Instruct

General-purpose instruction-tuned model for practical task execution.

MiniMax

Minimax M2.5

MiniMax M2.5 is a state-of-the-art coding and agentic AI model with 80.2% SWE-Bench and 37% faster performance than M2.1.

Llama 3 8B Instruct Lite

Lower-cost 8B model tuned for lightweight chat and content tasks.

Meta Llama 3.1 8B Instruct Turbo

A high-context Llama 3.1 turbo variant supporting tool integrations and optimized for fast, responsive trivia and general text generation.

Mistral

Mixtral 8x7B Instruct v0.1

Pretrained generative Sparse Mixture of Experts model designed for efficient, high-performance instruction following.

Llama 3.1 405B Instruct Turbo

Large-scale 405B model optimized for high-quality reasoning and professional tasks.

Llama 4 Maverick 17B 128E Instruct FP8

Balanced 17B model tuned for broad capability and usefulness.

Llama 3.3 70B Instruct Turbo

A Llama 3.3 instruct turbo model tailored for concise marketing applications, offering efficient generation and prompt responses.

Meta Llama 3.3 70B Instruct

A powerful Llama 3.3 large-scale instruct model designed to generate marketing-focused content with high coherence and clarity.

Llama 4 Scout 17B 16E Instruct

Efficiency-focused 17B model optimized for fast inference.

Meta Llama 3.1 8B Instruct

An instruction-tuned Llama 3.1 model optimized for guided text generation with focused performance in trivia and knowledge retrieval tasks.

Llama 3.2 3B Instruct Turbo

Lightweight 3B model with good speed and cost-efficiency for simpler tasks.

Llama 3.1 8B

A high-throughput Llama 3.1 8B model by Cerebras, designed for trivia, rapid answer generation, and real-time question resolving.

Marin

Marin 8B Instruct

Compact general-purpose instruction-tuned model with balanced capabilities.

Gemini 2.5 Flash

A Gemini model supporting large context inputs with strong multimodal reasoning and broad category applications.

Gemini 2.5 Pro

An advanced Gemini 2.5 Pro model designed for comprehensive multimodal reasoning and extensive category coverage including finance and legal.

Gemma 3N E4B IT

Efficient 4-bit quantized Gemma 3 variant with strong reasoning and tool-use.

DeepSeek R1 0528 TPUT

Optimized variant of R1 for faster, high-volume inference.

Gemini 3 Flash

Gemini 3 Flash Preview is a low-latency, cost-efficient multimodal reasoning model for agentic workflows and coding.

DeepSeek V3

Updated Deepseek model balancing capability with improved efficiency.

DeepSeek R1

Advanced reasoning model focused on complex, chain-of-thought tasks.

Deep Cogito

Cogito V2 Preview Llama 405B

Large-scale Cogito model focused on deep reasoning and complex knowledge tasks.

DeepSeek V3.2

A DeepSeek model that combines exceptional computational efficiency with advanced reasoning and strong agent capabilities.

Deep Cogito

Cogito V2 Preview Llama 109B MoE

Sparse MoE architecture offering cost-efficient intelligence at scale.

Deep Cogito

Cogito V2 Preview Llama 70B

70B Cogito V2 variant emphasizing factuality and applied reasoning.

Claude Opus 4.0

A high-capacity Claude Opus 4.0 model optimized for programming tasks, complex reasoning, and extended dialogue handling.

Arcee

Trinity Mini

26B-parameter (3B active) sparse MoE model optimized for long-context inference, function calling, and multi-step agents.

Claude Opus 4.5

Anthropic's fastest model with near-frontier intelligence.

Claude Sonnet 4.0

A versatile Claude Sonnet 4.0 model designed for broad application across programming, finance, marketing, science, and roleplay domains.

Claude Sonnet 4.5

Anthropic's smart model for complex agents and coding.