Mainnet Models

OpenAI flagship tier — deepest reasoning for complex coding, agentic workflows, and long-horizon problems. 1M context

Balanced GPT-5.6 tier — everyday coding, reasoning, and agentic tasks at half the flagship price. 1M context

Cost-efficient GPT-5.6 tier for high-volume, latency-sensitive chat and lightweight agentic workflows. 1M context

Highest-capability GPT-5.6 — Sol with pro reasoning mode for the hardest problems and long-running agentic work. 1M context

GPT-5.6 Terra with pro reasoning mode — deeper responses on complex tasks at half the standard Terra rate. 1M context

GPT-5.6 Luna with pro reasoning mode — budget tier with deeper reasoning for high-volume workloads. 1M context

First fully retrained base since GPT-4.5. 1M context, 128K output, native agent + computer use

Premium GPT-5.5 with maximum compute for the hardest problems

ChatGPT's default model — the rolling `chat-latest` alias, currently GPT-5.5 Instant. Tuned for speed and concision, same price as GPT-5.5

Most capable and efficient frontier model with 1M context, native computer use, and thinking mode

Premium GPT-5.4 with maximum compute for the hardest problems

High intelligence with medium speed. Multimodal with vision, function calling, and structured outputs

Frontier model with 400K context and adaptive reasoning

Strongest mini model for coding, computer use, and subagents with GPT-5.4 capabilities

Cost-optimized reasoning and chat

Fastest and most affordable GPT-5.4 model for high-throughput tasks

Uses more compute for consistently better answers

Industry-leading agentic coding model. 400K context, reasoning, tool use, and complex execution

Latest GPT-4 generation model

Fast and affordable GPT-4.1 model

Ultra-fast and cost-effective GPT-4.1

Multimodal model with vision and audio

Fast and affordable GPT-4o model

Advanced reasoning model for complex tasks

Latest reasoning model with improved performance

Efficient reasoning model for STEM tasks

Latest generation efficient reasoning model

Fastest and most efficient Claude, near-frontier intelligence

Newest Sonnet — near-Opus coding/agentic quality at Sonnet cost. 1M context, 128k output, adaptive thinking, vision

Best balance of intelligence, speed, and cost

Sonnet 4.5 — strong coding and agentic performance, vision

Latest Anthropic flagship with enhanced reasoning and creativity

Powerful Claude Opus for complex reasoning and agentic coding. 1M context, 128k output, adaptive thinking

Anthropic's most capable model — Mythos-class tier above Opus, for the most demanding reasoning and long-horizon agentic work. 1M context, 128K output, always-on thinking

Most capable Claude 4-series Opus for complex reasoning and agentic coding. 1M context, 128k output, adaptive thinking

Newest Opus — step-change over Opus 4.8 for deep reasoning and agentic coding at the same price. 1M context, 128k output, adaptive thinking

Latest Gemini with improved thinking, token efficiency, and agentic capabilities. Optimized for software engineering (requires new SDK)

Frontier-class performance with Pro-level intelligence at Flash speed and pricing. Includes thinking mode (requires new SDK)

Newest-generation Flash with built-in thinking mode — frontier-class quality at Flash speed

Latest-generation Flash with built-in thinking mode — frontier-class quality at Flash speed

State-of-the-art for reasoning, coding, and mathematics

Fast and efficient Gemini model with vision support

Latest Flash Lite — ultra-fast, lightweight Gemini with thinking mode for high-throughput tasks

Ultra-fast and lightweight Gemini 3.1 model with thinking mode for high-throughput tasks

Most economical Gemini model - ultra-fast and lightweight (requires new SDK)

DeepSeek V4 flagship — 1.6T MoE / 49B active, 1M context. Strongest open-weight reasoner. Thinking mode default.

Paid V4 Flash in non-thinking mode (1.6T-class quality at $0.14 in / $0.28 out). Production-grade reliability and 5MB request bodies.

Paid V4 Flash in thinking mode for reasoning tasks. Same upstream as deepseek/deepseek-chat but with thinking enabled by default.

Moonshot's flagship — a 2.8-trillion-parameter open MoE with 1M context, image + text input, returning reasoning_content. Live-verified 2026-07-17 (chat, tools, vision).

Z.AI's flagship — 1M-token context with always-on reasoning, strong at long-horizon coding. Verified live on Z.AI.

Z.AI GLM-5.2 — 1M-token context, strong open-source long-horizon coding. Verified live on Z.AI.

Z.AI flagship — #1 open source on SWE-Bench Pro, 8-hour autonomous execution. 200K context

Z.AI's foundation model with 200K context. Strong reasoning and agentic capabilities

Optimized GLM-5 variant with faster inference

xAI's Grok 4.3 reasoning model. 1M context, vision-capable, tuned for agentic workflows and instruction-following.

xAI's fast agentic coding model, trained for interactive software-engineering workflows. 256K context, text + image input.

xAI's flagship Grok 4.5 — their most intelligent and fastest model. 500K context, vision-capable, chain-of-thought reasoning. Supports Live Search (+$0.025/source)

MiniMax's flagship reasoning model with recursive self-improvement. Great value for complex tasks (~60 tps)

MiniMax's M3 flagship — 1M context, strong reasoning + coding.

Alibaba's Qwen flagship — the Max tier. 1M context, strong reasoning, coding, and agentic tool use. Live-verified 2026-07-20.

Alibaba's balanced Qwen tier — 1M context with reasoning, coding, and agentic tool use at a fraction of the Max price

Alibaba's fastest Qwen tier — 1M context reasoning for high-volume, latency-sensitive workloads

Tencent's Hy3 — fast, inexpensive reasoning at 262K context. One of the most-used open models of 2026.

Xiaomi's MiMo-V2.5 Pro — 1M context reasoning model, priced well below the frontier tier.

NVIDIA's multimodal reasoning Nemotron Nano Omni hosted free by NVIDIA. 31B / 3.2B active MoE. Accepts text, images, video, audio. ChartQA 90.3, DocVQA 95.6, MMMU 70.8 — the only vision-capable free model in our catalog

Mistral × NVIDIA Nemotron instruction model hosted free by NVIDIA. Fast (~0.2s), strong instruction following.

StepFun Step 3.7 Flash hosted free by NVIDIA. Fast lightweight reasoning, 131K context.

NVIDIA Nemotron Nano 9B v2 hosted free by NVIDIA. Compact + fast (~0.7s), good for high-volume light tasks.

NVIDIA Nemotron Nano 12B v2 Vision-Language hosted free by NVIDIA. Accepts images; compact + fast.