Large Language Models

OpenAI GPT-6.1 Sol: GPT-6.1 reasoning at a fifth of Astra's price, over a 1M-token context window.

OpenAI GPT-6.1 Terra: the mid-tier GPT-6.1 model at a tenth of Astra's price per token, over a 1M-token context window.

OpenAI GPT-6 Astra — frontier reasoning over a 1M-token context window.

OpenAI GPT-6 Sol: GPT-6 reasoning at a fifth of Astra's price, over a 1M-token context window.

OpenAI GPT-6 Luna: the fast, low-cost GPT-6 tier for high-volume chat and light agentic work, 1M-token context window.

Cost-efficient high-throughput model for budget-conscious applications

Google's latest GA Flash model for fast multimodal reasoning and agentic workloads.

Cost-efficient GA Flash model for high-throughput multimodal tasks.

Cost-efficient high-throughput model for budget-conscious applications.

Google's most capable agentic model with 1M token context, 77.1% ARC-AGI-2 reasoning, and native tool use.

Google's flagship reasoning model: a 1M-token context, text, image, video and audio in, text out, with native tool use and three thinking levels.

Mistral's open-weight flagship (public preview, 2026-10-06). 1.05T MoE (52B active) with a vision encoder; reasoning on demand, tools. 1M context.

Moonshot's open-weight 2.8T-parameter multimodal reasoning model with a 1M-token context window.

Moonshot's headline model: a 1M-token context window, native image understanding, tool use and reasoning.

Kimi K3.1 Pro at about 2–3× the speed, at a higher price: the same intelligence, with a 1M-token context window.

Premium model for complex, multi-step work. Augure sovereign Canadian AI.

Xiaomi's flagship MiMo model (V2.6, 2026-09). 1M context, accepts text and images, function calling and structured output, reasons before it answers.

Xiaomi's fast, low-cost MiMo model (V2.6, 2026-09). 1M context, accepts text and images, function calling and structured output, reasons before it answers.

MiMo V2.6 Pro on Xiaomi's high-speed tier, at a premium price. 1M context, accepts text and images, function calling and structured output.

OpenAI GPT-4.1 (chat completions endpoint).

OpenAI GPT-4.1 Mini (chat completions endpoint).

Fast multimodal Qwen (text & image in, text out) on the Singapore tenant. Thinking on by default. Context measured served: 1,006,592 tokens.

Ultra-fast model with 1M context. Best latency and cost efficiency for simple tasks.

Balanced flagship model with 1M context. Best performance/cost ratio for most tasks.

Alibaba's 2.4T-parameter multimodal MoE flagship. 1M context, accepts text and images.

Flagship 1T+ parameter model. State-of-the-art reasoning, coding, and agent capabilities.

Alibaba's newest Flash model. 1M context, accepts text and images, with tool use and thinking.

Low-cost Flash model with 1M context. Accepts text and images, with tool use and thinking.

Flagship 1T+ parameter model. State-of-the-art reasoning, coding, and agent capabilities.

Cost-effective coding model optimized for speed. Fast code generation and completion at lower cost.

Multimodal frontier (vision/video); cheaper than Max.

397B MoE model with 17B active parameters, 1M token context, multimodal (text/image/video)

Qwen3.6 Plus, next-gen frontier LLM (Agentic Coding, vision/OCR, fine-grained localization). Replaces Qwen3.5 Plus.

Sonnet 5.5 by Anthropic (2026-09-28): the best combination of speed and intelligence, for everyday coding, documents and agents. 1M context, 128K output, adaptive thinking.

Anthropic's most capable Sonnet — closes the gap with Opus for complex agents and coding (1M context)

Best Claude Sonnet for complex agents and coding (1M context)

Haiku 5.5 by Anthropic (2026-10-07): the fastest Claude, for high-volume, latency-sensitive work such as classification, extraction and routing. 1M context, 128K output, adaptive thinking.

Opus 5.5 by Anthropic (2026-09-21): the next Opus, for long-running agentic coding and knowledge work. 1M context, 128K output, adaptive thinking always on.

Anthropic's flagship Opus — deep reasoning, agentic coding and long-horizon work (1M context)

Anthropic's most capable model for complex reasoning and agentic coding (1M context)

Highly capable Claude Opus for complex reasoning and coding (1M context)

Most capable Claude model with enhanced reasoning and coding

Fable 5 by Anthropic.

Fable 5.1 by Anthropic: the Fable before 5.2, for demanding reasoning and long-horizon agentic work. 1M context, 128K output, adaptive thinking always on.

Fable 5.2 by Anthropic: the most capable generally available Claude, for demanding reasoning and long-horizon agentic work. 1M context, 128K output, adaptive thinking always on.

DeepSeek V4.1 Flash, the fast daily driver that replaced V4 Flash on 2026-09-10. 1M context, thinking (default) and non-thinking modes.

xAI's flagship general-purpose model. 1M context, balanced reasoning and chat.

Reasoning-mode variant of Grok 4.20. Slower but stronger on multi-step problems.

Non-reasoning variant of Grok 4.20. Fastest 4.20 path for chat and high-throughput tasks.

Z.ai's latest flagship for agentic and coding tasks.

Z.ai's newest flagship for agentic and coding tasks. Always reasons; text-only input.

Z.ai's fast, low-cost GLM-5.3 variant: 1M context, tools, always reasons; text and image input.

Inception Labs' most capable diffusion LLM: a 1M-token context, 131,072 max output, tool calling, reasoning_effort instant/low/medium/high (medium by default).

DeepSeek flagship V4. 512K context, advanced reasoning + tool use.

Upstage flagship agentic model. 512K context (API-confirmed family), tool calling, structured outputs and opt-in reasoning. English/Korean/Japanese.

Upstage compact agentic MoE (35B total, 3B active). 524,288-token context (API-confirmed), tool calling and opt-in reasoning, English/Korean/Japanese.

xAI's newest flagship, launched July 2026. 500K context, strongest reasoning + coding, trained alongside Cursor.

xAI's newest flagship. 500K context, accepts text and images, strongest reasoning + coding.

xAI's newest flagship (2026-09-21). 500K context, accepts text and images, function calling, structured outputs, reasoning.

Sakana's multi-agent conductor, orchestrates a pool of frontier models for complex reasoning. Billed per token, orchestration included.

OpenAI GPT-5.6 Sol — frontier logic + deep reasoning, the flagship 5.6 tier.

OpenAI GPT-5.6 Terra — balanced business logic, mid 5.6 tier.

OpenAI GPT-5.6 Luna — high-volume streaming tasks, fast + economical 5.6 tier.

OpenAI flagship chat model (April 2026 release).

OpenAI premium tier with deep reasoning. April 2026.

OpenAI mid-tier flagship (March 2026).

OpenAI fast/cheap chat model.

OpenAI cheapest tier, very fast.

OpenAI GPT-5.4 Pro (chat completions endpoint).

OpenAI GPT-5.3 Codex (chat completions endpoint).

OpenAI GPT-5.2 (chat completions endpoint).

OpenAI GPT-5.2 Pro (chat completions endpoint).

OpenAI GPT-5.1 (chat completions endpoint).

OpenAI GPT-5 (chat completions endpoint).

OpenAI GPT-5 Mini (chat completions endpoint).

OpenAI GPT-5 Nano (chat completions endpoint).

OpenAI GPT-5 Pro (chat completions endpoint).

OpenAI GPT-5 Search API (chat completions endpoint).

Advanced vision-language model with 262K context. Excels at visual coding, spatial perception, and multimodal reasoning.

Alibaba's Agent Frontier flagship.

Google's open-weight dense model with 262K context and strong multilingual reasoning

Google's open-weight mixture-of-experts model, 26B total, 4B active parameters for fast inference

Open-weight flagship. 675B MoE (41B active), multimodal with vision. Apache 2.0 licensed.

Fast and efficient model for simple tasks. Great balance of performance and cost.

Specialized model for code generation, completion, and understanding.

Latest Kimi K2 reasoning model. Replaces K2 thinking variants (k2-thinking and k2-thinking-turbo) being retired 2026-05-25.

Coding-specialized Kimi K2 model (k2.7). 256K context, agentic tool use and function calling, tuned for software engineering.

High-speed variant of Kimi K2.7 Code for low-latency agentic software engineering.

ByteDance Seed 2.0 Pro, flagship multimodal agent (text, image & video in → text), strong tool use + reasoning, 256K context. Native via BytePlus (Ark).

ByteDance Seed 2.1 Turbo, fast multimodal reasoning agent (text & image in → text), strong tool use + thinking, 256K context. Native via BytePlus (Ark).

ByteDance Seed 2.0 Lite, efficient multimodal agent (text, image & video in → text), tool use + reasoning, 256K context. Native via BytePlus (Ark).

ByteDance Seed 2.0 Code (preview), coding-specialized agent (text & image in → text), strong tool use + reasoning. Native via BytePlus (Ark).

Compact model tuned for code generation and structured output. 256K context.

StepFun's multimodal flagship reasoning model.

StepFun's latest reasoning model, 196B MoE (11B active), 256K context, open-source Apache 2.0. Fast agentic intelligence with strong code and math.

Newest reasoning model: the fastest of the Augure menu, strong at code, 256K context. Augure sovereign Canadian AI.

Premium multimodal model with vision and tool use, strong bilingual EN/FR. Augure sovereign Canadian AI.

Light tier: fast, thinking off, 256K context, served in Canada with no failover outside Canada. Replaces Tofino 2.5, retired by Augure on 2026-09-19.

Most capable Z.ai model. 744B params (40B active MoE), 28.5T training tokens. Built for complex systems engineering and agentic tasks.

Native multimodal coding model. 744B MoE (40B active), 203K context. Optimized for design-to-code, GUI automation, and vision-grounded agentic tasks.

Latest flagship. 358B params, 204K context, 131K output. #1 on LiveCodeBench.

Flagship model with reasoning, coding, and agentic capabilities. 200K context.

Z.ai's current flagship for agentic and coding tasks.

Lightweight, completely free GLM-4.7 variant with 200K context.

Lightweight, high-speed and affordable GLM-4.7 variant with 200K context.

Claude's best model for complex agents and coding

Claude's fastest and most intelligent Haiku model

Premium model combining maximum intelligence with practical performance

Perplexity's advanced search model, deeper web research, multi-step reasoning with citations, 200K context.

OpenAI o3 (chat completions endpoint).

Google's omni-modal Flash, GA — fast conversational generation with native video output. Served via the Interactions API like its preview parent, text-in today (multimodal input is a follow-on there); thinking control on that path is unprobed, so no ladder is declared yet (#544).

Google's omni-modal Flash 1.2, GA — fast conversational generation that answers in text and, when asked, in video with native audio. Served through the Interactions API like 1.1, text input today.

Efficient reasoning model for everyday logic tasks.

Premier frontier-class multimodal model. Great balance between Large and Small.

Ultra-lightweight edge model with vision. 3B params, runs on phones/laptops.

Compact edge model with vision. 8B params for local deployment.

High-performance edge model with vision. Best Ministral for complex tasks.

ByteDance Seed 2.0 Mini, fast lightweight multimodal agent (text, image & video in → text), tool use. Native via BytePlus (Ark).

Mistral's model optimized for command-line and terminal-based coding workflows.

Vision-capable model for image understanding and analysis.

Lightweight vision model. Fast and cost-effective for image tasks.

Previous flagship with thinking mode. MoE architecture, 128K context.

Lightweight model optimized for efficiency. 128K context.

Free tier model. Great for testing and light workloads.

Free vision model. Great for testing image understanding.

Perplexity's lightweight search-augmented model, real-time web search with citations, fast responses, 128K context.

Perplexity's reasoning model, extended thinking with real-time web search, ideal for complex research and analysis.

Perplexity's most thorough research model, multi-step deep web investigation with comprehensive citations and reasoning.

OpenAI GPT-4o (chat completions endpoint).

OpenAI GPT-4o Mini (chat completions endpoint).

Alibaba Qwen3.5 Omni, multimodal (text & image input, text output). Singapore deployment; native voice/audio coming.

Alibaba Qwen3.5 Omni Flash, fast multimodal (text & image input, text output). Singapore deployment; native voice/audio coming.

Vision-language model for image understanding and analysis.

Upstage nightly build of Solar Pro 2 with latest improvements.

Upstage advanced synthetic reasoning model with 64K context.

Fast variant of GLM-5 with optimized speed and competitive quality.

Sarvam's 24B multilingual LLM, fluent in all 22 official Indian languages + English. OpenAI-compatible API. Free tier with no per-token charges. Supports wiki grounding, reasoning effort control, and tool calls.