Coding-focused GPT-5.3 variant with optimized routing.

Qwen3.5 122B A10B is Alibaba's high-end native vision-language model in the Qwen 3.5 family with strong text and multimodal performance.

Qwen3.5 122B A10B with extended reasoning enabled. Alibaba's high-end native vision-language model in the Qwen 3.5 family.

Qwen3.5 27B is a native vision-language dense model optimized for fast responses while balancing quality and inference speed.

Qwen3.5 27B with extended reasoning enabled. A native vision-language dense model optimized for fast responses.

Qwen3.5 35B A3B is a native vision-language MoE model with hybrid attention designed for efficient inference and strong general performance.

Qwen3.5 35B A3B with extended reasoning enabled. A native vision-language MoE model with hybrid attention.

Qwen3.5 Flash is the fastest and cheapest native Qwen 3.5 vision-language model with a 1M-token context window.

Qwen3.5 Flash with extended reasoning enabled. The fastest and cheapest native Qwen 3.5 vision-language model.

Gemini 3.1 Pro preview high-reasoning variant.

Gemini 3.1 Pro preview low-reasoning variant.

Gemini 3.1 Pro preview is built for tasks where simple answers are not enough. Stronger core reasoning for complex coding, math, and long-context workflows, with multimodal support and a reported 77.1% verified score on ARC-AGI-2. NOTE: Inputs > 200k tokens are charged at 2x input and 1.5x output rates.

Claude Sonnet 4.6 is Anthropic's most capable Sonnet yet — a full upgrade across coding, computer use, long‑context reasoning, agent planning, and design. Features a 1M token context window in beta. Approaches Opus‑level intelligence at Sonnet pricing.

Claude Sonnet 4.6 with extended thinking enabled for tougher coding, planning, and multi‑tool tasks. Ideal for long‑horizon agent workflows and complex problem solving.

Qwen 3.5's open-source 397B MoE model (17B active params) with hybrid linear attention. Runs via open-source providers. Supports text, image, and video input with a 256K context window.

Qwen 3.5's open-source 397B MoE model (17B active params) with hybrid linear attention and extended reasoning. Runs via open-source providers. Supports text, image, and video input with a 256K context window.

Qwen 3.5 Plus is a commercial model with hybrid linear attention and sparse MoE architecture. Supports text, image, and video input with a 1M context window.

Qwen 3.5 Plus with extended reasoning. A commercial model with hybrid linear attention and sparse MoE architecture. Supports text, image, and video input with a 1M context window.

Code-focused preview model in the Doubao Seed 2.0 family. Supports a 256k context window and up to 128k output tokens. ⚠️ Note: This model routes through ByteDance, a Chinese entity - privacy and logging guarantees may be limited.

Lower-cost variant in the Doubao Seed 2.0 family for fast general usage. Supports a 256k context window and up to 32k output tokens. ⚠️ Note: This model routes through ByteDance, a Chinese entity - privacy and logging guarantees may be limited.

Smallest and most affordable model in the Doubao Seed 2.0 family. Supports a 256k context window and up to 32k output tokens. ⚠️ Note: This model routes through ByteDance, a Chinese entity - privacy and logging guarantees may be limited.

Highest-capability general model in the Doubao Seed 2.0 family. Supports a 256k context window and up to 128k output tokens. ⚠️ Note: This model routes through ByteDance, a Chinese entity - privacy and logging guarantees may be limited.

Allen Institute's open-source Molmo 2 8B, a vision-language model built on Qwen3-8B with SigLIP 2 vision backbone. Supports image, video, and multi-image understanding with strong spatial grounding and object tracking. Included in the subscription.

MiniMax M2.5 is a productivity-focused flagship model that builds on M2.1 with stronger coding and real-world office workflow performance (Word, Excel, PowerPoint), plus better tool-use planning and token efficiency.

GLM-5 is Zhipu's latest flagship model with advanced reasoning and instruction following. This is the open-source hosted version and it is included in the subscription.

GLM-5 with extended thinking capabilities for complex reasoning. This is the open-source hosted version and it is included in the subscription.

GLM-5 is Zhipu's latest flagship model with advanced reasoning and instruction following. Routed directly via Z-AI (Zhipu).

GLM-5 original with extended thinking capabilities for complex reasoning.

GLM-5 is Z.AI's flagship model for complex systems engineering and long-horizon agent workflows. Running inside a TEE (Trusted Execution Environment), with verifiably no logging by the provider.

Claude Opus 4.6 is Anthropic's newest Opus model with stronger coding and agentic performance, plus a 1M-token context window in beta.