Try every frontier AI model

Claude Opus 5

Chat & reasoning

Anthropic's everyday flagship for complex agentic coding and enterprise work. Ranks first overall on the AA Intelligence Index v4.1 at 63 with max effort.

Claude Fable 5

Chat & reasoning

Anthropic's highest-capability model for the hardest reasoning and long-horizon agentic work. Scores 62 on the AA Intelligence Index v4.1, just behind Opus 5 at max effort.

Grok 4.6

New

Chat & reasoning

xAI's frontier model for long-running agents, codebase work, and ambitious interactive or visual projects. Scores 61 on the AA Intelligence Index with 500K context and always-on reasoning.

GPT-5.6 Sol

Chat & reasoning

OpenAI's flagship. Scores 61 on the AA Intelligence Index v4.1 and sets the state of the art on the Coding Agent Index (80), with an `ultra` multi-agent mode for the hardest work.

Claude Opus 4.8

Chat & reasoning

Frontier all-rounder. Leads SWE-bench Pro (69%) at AA Intelligence Index v4.1 of 56 — the value pick just below Fable 5.

Grok 4.5

Chat & reasoning

xAI's previous-generation coding and agentic model, trained alongside Cursor. Scores 56 on the AA Intelligence Index with 500K context, always-on reasoning, and optional web search.

Gemini 3.7 Flash

New

Chat & reasoning

Google's most intelligent Flash workhorse for coding and agents. Scores 56 on the AA Intelligence Index with 1M context, multimodal input, and introductory half-price token rates through 2026.

GPT-5.6 Terra

Chat & reasoning

Balanced GPT-5.6 tier — matches GPT-5.5 quality (AA Intelligence Index 55) at roughly half the cost, tuned for everyday professional work.

GPT-5.5

Chat & reasoning

OpenAI's previous flagship. AA Intelligence Index v4.1 of 54.8 — a strong all-round frontier model, now succeeded by the GPT-5.6 family.

Claude Sonnet 5

Chat & reasoning

Anthropic's current fast workhorse — near-Opus quality at much lower latency and cost.

Gemini 3.6 Flash

Chat & reasoning

Google's previous Flash workhorse, scoring 52 on the AA Intelligence Index. Retained for its 1M context, multimodal input, and low-latency minimal reasoning mode.

GPT-5.6 Luna

Chat & reasoning

Fastest, most affordable GPT-5.6 tier — outperforms Claude Opus 4.8 on the Coding Agent Index at roughly a quarter of the cost.

GLM-5.2

Chat & reasoning

Zhipu's GLM-5.2 — the leading open-weights model on the AA Intelligence Index.

Muse Spark 1.1

Chat & reasoning

Meta Superintelligence Labs' multimodal reasoning model, built for agentic work. 1M-token context, image + video understanding, search grounding, and strong coding — served on the new OpenAI-compatible Meta Model API at value pricing.

Gemini 3.1 Pro

Chat & reasoning

Google DeepMind frontier. 2M context, fully multimodal, and an AA Intelligence Index v4.1 score of 46.

MiniMax M3

Chat & reasoning

MiniMax M3 — Apache-licensed, matches Gemini 3.1 Pro on coding at open-weights pricing.

DeepSeek V4 Pro

Chat & reasoning

Flagship open-source MoE (1.6T) — frontier reasoning + coding with a 1M-token context, at open-weights pricing.

Kimi K2.6

Chat & reasoning

Moonshot's K2.6 — open-weights, 80%+ SWE-bench Verified, top-tier agentic reasoning.

Qwen 3.7 Plus

Chat & reasoning

Alibaba's flagship closed model — strong reasoning + function calling, served exclusively on Fireworks outside Alibaba's own cloud.

Grok 4.3

Chat & reasoning

xAI flagship. Configurable reasoning, 1M context, and optional live web knowledge at low frontier pricing.

GPT-5

Chat & reasoning

OpenAI workhorse — strong general purpose at lower cost than 5.5.

GPT Image 2

Image generation

OpenAI's latest image model. Native edit support, photorealistic.

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

Image generation

Google's fastest and lowest-cost image model, optimized for 1K generation and editing with object references.

Nano Banana 2 (Gemini 3.1 Flash Image)

Image generation

Google's recommended all-around image model, balancing quality, speed, text rendering, and up to 14 references.

Nano Banana Pro (Gemini 3 Pro Image)

Image generation

Google's premium image model for complex design, precise text, and blending up to 14 reference images.

FLUX 2 Pro

Image generation

Black Forest Labs' flagship image model. Excellent prompt adherence.

Nano Banana (Gemini 2.5 Flash Image)

Image generation

Google's original Nano Banana for fast 1K generation and editing with up to 3 references; retires October 2, 2026.

Recraft v4 Pro

Image generation

Recraft v4's higher-fidelity tier — best for posters, logos, vector art.

Recraft v4

Image generation

Recraft's text + vector + raster image model.

Seedream 5 Lite

Image generation

ByteDance's Seedream 5 Lite via FAL — fast and cheap.

Ideogram v3 Quality

Image generation

Ideogram's text-rendering specialist — top tier (graphic design, posters).

Ideogram v3 Balanced

Image generation

Ideogram v3 mid tier — great text rendering at a lower price.

FLUX 2 Fill (Inpaint)

Image editing

Inpaint and outpaint with FLUX 2.

Seedance 2.0 Pro

Video generation

ByteDance's flagship — #1 on the Artificial Analysis text-to-video arena, best for multi-shot and brand consistency.

Kling 3.0 Pro

Video generation

Kuaishou's Kling 3.0 — 4K/60fps, precise shot control and character consistency for ads.

Veo 3.1

Video generation

Google's flagship video model with native audio.

Kling v2.1 Master

Video generation

Kuaishou's Kling v2.1 Master on Replicate — cinematic motion + character consistency.

Grok Imagine

Video generation

xAI's text-to-video with native audio — the value pick for fast, high-volume social clips.

Lyria 3

Music generation

Google DeepMind's latest music generation model — the best free-tier option for background tracks.

MiniMax Music 2.6

Music generation

MiniMax Music 2.6 — full tracks with vocals, backing music, and lyric structure tags from a style prompt.