Models

Fast and affordable Claude model for high-throughput tasks.

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

Previous Opus generation with strong reasoning and coding.

High-capability Claude model balancing intelligence and speed.

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

Latest Sonnet with Opus-tier capabilities at Sonnet pricing.

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

Scalable enterprise model optimized for RAG and multilingual tasks.

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

Updated R1 with improved reasoning accuracy and reduced hallucination.

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

Updated DeepSeek V3 with improved coding and reasoning performance.

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

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

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

Optimized for coding, reasoning, and tool use.

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

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).

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

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

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

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

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

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

GPT-5.1 code-optimized variant.

GPT-5.2 general-purpose model.

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.

Compact GPT-5.4 variant balancing capability and cost.

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

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

Fast and efficient Gemini model for high-throughput workloads.

Speed-optimized Gemini with strong reasoning and multimodal capabilities.

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

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

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

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

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

Largest Gemma 3 model with strong reasoning and instruction following.

Compact open-weight model for edge and mobile deployment.

Latest Gemma generation optimized for reasoning and agentic workflows.

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

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

Lightweight Grok optimized for cost-efficient reasoning.

Latest Grok with improved instruction following and reduced hallucination.

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

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

Widely deployed open-weight model with strong general capabilities.

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

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

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

Latest MiniMax general-purpose LLM with improved reasoning.

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

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

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

Amazon Nova Lite for fast, cost-efficient tasks.

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

Amazon Nova Pro for balanced capability and cost.

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

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

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

Alibaba's highest capability Qwen 3 model.

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

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

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

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

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

Compact Qwen 3.5 for single-GPU deployment.

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

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

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

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