Chat / Instruct

Fast and efficient Gemini 3 model for high-throughput workloads.

Compact open-weight model for edge and mobile deployment.

Mid-size open-weight Gemma model with vision support.

Compact Qwen 3.5 for single-GPU deployment.

Ultra-lightweight GPT-5 for high-speed, low-cost text generation.

Compact Qwen 3 for edge and single-GPU deployment. Open weight.

Optimized for coding, reasoning, and tool use.

Amazon Nova Lite for fast, cost-efficient tasks.

Open-weight 117B MoE model (5.1B active) achieving near o4-mini reasoning. Apache 2.0 licensed, runs on a single 80GB GPU.

Largest Gemma 3 model with strong reasoning and instruction following.

Natively multimodal MoE model with 10M context. 109B total, 17B active. Fits single H100.

Mid-size Qwen 3 with strong coding and math capabilities. Open weight.

Speed-optimized Gemini with strong reasoning and multimodal capabilities.

Unified model combining fast instruct, deep reasoning, and multimodal chat. 119B params.

Fast and efficient Gemini model for high-throughput workloads.

Widely deployed open-weight model with strong general capabilities.

Edge-optimized model with vision support. Apache 2.0 licensed.

Largest Qwen 3 model with hybrid thinking modes for flexible reasoning control.

Mid-size Qwen 3.5 MoE model with 35B total, 3B active parameters.

MiniMax general-purpose LLM with competitive reasoning and coding capabilities.

Most capable open Gemma model with best intelligence-per-parameter.

Strong reasoning and coding with 106B total, 12B active MoE architecture.

Updated DeepSeek V3 with improved coding and reasoning performance.

Cost-efficient smaller GPT-4o variant for lightweight tasks.

Largest open Llama 4 with 128 experts. 400B total, 17B active. Beats GPT-4o on benchmarks.

State-of-the-art 1T MoE model with 32B active parameters. Strong coding and agentic capabilities.

Open-weight 671B MoE model with strong coding and reasoning at low cost.

Ultra-lightweight GPT-5.4 for high-speed, low-cost tasks.

Lightweight Grok optimized for cost-efficient reasoning.

Native multimodal Qwen with text, image, and video processing.

Open-weight multimodal model with agent swarm mode supporting up to 100 parallel sub-agents.

Compact GPT-5 variant for lightweight tasks and rapid prototyping.

Latest DeepSeek V3 with improved reasoning and coding. 671B MoE (37B active), MIT licensed, 164K context.

Reasoning-focused model with chain-of-thought capabilities rivaling o1.

Large Qwen 3.5 MoE model with 122B total, 10B active parameters.

Latest MiniMax general-purpose LLM with improved reasoning.

Latest Haiku tier with improved capabilities at fast speed and low cost.

High-capability Gemini model for complex reasoning and coding tasks.

Open-source frontier model with 355B parameters. MIT licensed.

Compact GPT-5.4 variant balancing capability and cost.

Alibaba's latest flagship with 1M context and advanced agentic coding.

GPT-5.2 general-purpose model.

Updated R1 with improved reasoning accuracy and reduced hallucination.

High-capability Gemini 3 model. Deprecated in favor of 3.1 Pro.

GPT-5 variant optimized for code generation and software engineering.

GPT-5.1 code-optimized variant.

Largest Qwen 3.5 MoE model with 397B total, 17B active parameters.

GPT-5.2 code-optimized variant.

GPT-5.3 code-optimized variant.

OpenAI's latest frontier model combining reasoning, coding, and agentic workflows.

Latest GPT-5.4 code-optimized variant with industry-leading coding capabilities.

Frontier 744B model trained on Huawei Ascend chips. Open source with strong agentic capabilities.

Fast and affordable Claude model for high-throughput tasks.

Amazon Nova Pro for balanced capability and cost.

Lightweight reasoning model balancing chain-of-thought rigor with speed and cost efficiency.

High-capability Claude model balancing intelligence and speed.

Latest Sonnet with Opus-tier capabilities at Sonnet pricing.

Mistral's most capable model. 675B MoE with 41B active parameters.

Alibaba's highest capability Qwen 3 model.

Qwen 3 Max with extended reasoning and chain-of-thought capabilities.

Google's current flagship model with top benchmark scores and 1M context.

Coding-focused frontier model scoring 94% of Claude Opus 4.6. 744B MoE trained on Huawei Ascend 910B. #1 on SWE-Bench Pro (open source).

Previous Opus generation with strong reasoning and coding.

Anthropic's most capable model with 1M token context and advanced reasoning.

Latest Grok with improved instruction following and reduced hallucination.

Reasoning-focused model with step-by-step deliberation for complex math, coding, and science tasks.

Cohere's latest flagship model for enterprise RAG, tool use, and agents.

Scalable enterprise model optimized for RAG and multilingual tasks.

OpenAI's flagship multimodal model with strong reasoning, coding, and vision capabilities.

Amazon's most capable LLM for complex reasoning and enterprise tasks.

xAI's flagship LLM trained on 200K+ GPUs with real-time web and X integration.

Most capable reasoning model in OpenAI's lineup with extended thinking for maximum reliability.

Highest capability GPT-5.4 tier with maximum reasoning depth. Premium pricing.

Latest Gemma generation optimized for reasoning and agentic workflows.