Explore models.

DeepSeek-V4.1-Flash-1017

DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Alongside these gains, the model…

REReflection: Beam 1.0 501B A23B

Apache-2.0 text model with 501B total and 23B active parameters; ships BF16, FP8 and NVFP4 weights.

Meta: Muse Spark Open

OpenRouter lists a 1,048,576-token context and up to 943,718 output tokens for this open-weight model aimed at agentic coding.

Nemotron 3.5 Super VL

120B/12B-active Mamba-2 hybrid with a vision encoder; native speculative decoding and switchable thinking.

Google: Gemini 4 Argon

Long decode can use the unified 1M-token budget for output; reads video, audio and PDFs, with implicit-only caching.

OpenAI: GPT-6.1 Sol

Requires Responses API for tools; offers Ultrafast inference with US or EU data residency.

Anthropic: Claude Sonnet 5.5

Tuned for quick iteration on scoped fixes and documents; Anthropic favors Opus 5.5 for open-ended work needing sustained judgment.

Anthropic: Claude Opus 5.5

Always-on adaptive thinking defaults to medium effort; built for sustained work across large codebases and professional documents.

OpenAI: GPT-6 Luna

Can turn reasoning off for high-volume requests; Chat Completions tool calls require reasoning_effort=none.

XIXiaomi: MiMo-V2.6-Pro

MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...

SAStep-5-Preview

600B total and 27B active parameters; accepts images and video, with FP8 and BF16 weights for deployment.

DeepSeek: DeepSeek V4.1 Flash

Causal encoder-decoder activates 8B parameters for input and 16B for output, reducing the compute needed for long inputs.

OpenAI: GPT-6 Astra

Accepts mid-turn steering and async tool calls, so agents can take new instructions while other tools are still running.

Anthropic: Claude Fable 5.1

Beta controls change effort per message without invalidating the prompt cache and report progress between tool calls.

Qwen: Qwen3.8 Flash

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis,…

GLM-5.3-Flash

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context…

DeepSeek-V4-Flash-Vision-Exp

DeepSeek-V4-Flash-Vision-Exp is DeepSeek's experimental multimodal model in the V4-Flash family, adding visual understanding to the V4-Flash architecture. It serves a 1M-token (1,048,576) context window and…

GLM-5.3

Reuses the GLM-5.2 base with new post-training; exposes low, high and max reasoning effort, defaulting to max.

Qwen3.8-27B

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking…

Qwen: Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is...

NVIDIA: Nemotron 3.5 Lightning

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

Kimi-K3

2.8T total and 104B active parameters; combines Kimi Delta Attention with native image/video input under the Kimi K3 license.

Google: Gemma 4 31B

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native…

Claude Fable 5