Models

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash: a fast sparse mixture-of-experts model with a 1M-token context window and text and image input. Pin it when you need behaviour that will not change.

Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows.

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.

Qwen3.8 27B is an open-weight dense vision-language model from Qwen.

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Qwen3.8 Max is Alibaba Qwen's open-weight flagship: a sparse mixture-of-experts model with 2.4T total and 95B active parameters, built for reasoning, coding and agentic work.

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.

GLM 5.2 is a large-scale reasoning model from Z.ai.

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro.

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.

NVIDIA Nemotron 3 Nano Omni is a 30B-A3B open multimodal reasoning model designed to work as a perception and context sub-agent in enterprise agent systems.

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks.

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart.

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.

NVIDIA Nemotron Nano 12B v2 VL is a 12.6B vision-language model for document intelligence: multi-image reasoning, video understanding, visual Q&A and summarization of invoices, receipts and manuals.

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. Built with Llama.

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference.

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass.

Llama 4 Maverick 17B Instruct (128E) is Meta's high-capacity multimodal mixture-of-experts model, with 128 experts and 17 billion active parameters per forward pass. Built with Llama.

Gemma 3 introduces multimodality, supporting vision-language input and text outputs.