Cloudflare

Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second Inkling generation. It was trained with reinforcement learning on long-horizon coding tasks across many agent harnesses, and is suited for agentic coding, autonomous research, agentic knowledge work and retrieval-augmented generation, with English and general multilingual support. It accepts text and image input (no audio), supports tool calling and variable reasoning effort, and has a 1M-token context window.

Clairic is Cloudflare's System One-style extraction model served on Workers AI. Given a text state and optional images plus a schema of typed fields, it extracts, computes, estimates, and forecasts strongly typed values (text spans, numbers, dates, times, durations, lists, estimates, forecasts) in a single pass, returning a confidence score and null probability for every field instead of generating tokens. Served through the Extractions API (/api/alpha/extractions); not available on /api/alpha/decisions.

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. 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. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp. It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.

Clef Omni is the mixture-of-experts member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3-Omni-30B-A3B (30B total, 3B active parameters) served on Workers AI. It turns a state plus a schema of typed questions into decisions, returning a calibrated probability for every allowed option of every question in a single forward pass instead of generating tokens. Use it for classification, routing, scoring, and guardrails over text, JSON, images, audio, and video through the Decisions API.

Clef-flash is the fast 9B member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3.5-9B served on Workers AI. It turns a state (text or structured JSON) plus a schema of typed questions into decisions, returning a calibrated probability for every allowed option of every question in a single forward pass instead of generating tokens. Use it for low-latency classification, routing, scoring, and guardrails through the Decisions API. Note: Workers AI currently truncates long text state to roughly the first 2K tokens, so content beyond that is not read; images are counted separately.

Clef is Cloudflare's open-source 27B multimodal decision model, a fine-tune of Qwen3.8-27B served on Workers AI. It turns a state (text or structured JSON) plus a schema of typed questions into decisions, returning a calibrated probability for every allowed option of every question in a single forward pass instead of generating tokens. Use it for classification, routing, scoring, guardrails, and agentic control flow through the Decisions API. Note: Workers AI currently truncates long text state to roughly the first 2K tokens, so content beyond that is not read; images are counted separately.

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency. Reasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.

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 that can be enabled or disabled.

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

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. This is the GA release of DeepSeek V4 Flash.

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.

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. It uses a native multimodal mixture-of-experts architecture that accepts text and image input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations. With a 256K-token context window, it targets long-horizon coding, agentic task decomposition, and multi-turn dialogue. The model activates 32B parameters out of roughly 1T total.

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. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments. The updated version is Mistral Small 3.2

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks. Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. Model Card

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in code generation, code reasoning and code fixing. - A more comprehensive foundation for real-world applications such as Code Agents. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies. To read more about its evaluation results, check out Qwen 2.5 Coder's blog.

Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate efficiently in low-resource environments while maintaining strong task performance. Supporting eight core languages and fine-tunable for more, Llama 1.3B is ideal for businesses or developers seeking lightweight yet powerful AI solutions that can operate in diverse multilingual settings without the high computational demand of larger models. Click here for the original model card. Usage of this model is subject to Meta's Acceptable Use Policy.

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it supports eight languages, including English, Spanish, and Hindi, and is adaptable for additional languages. Trained on 9 trillion tokens, the Llama 3.2 3B model excels in instruction-following, complex reasoning, and tool use. Its balanced performance makes it ideal for applications needing accuracy and efficiency in text generation across multilingual settings. Click here for the original model card. Usage of this model is subject to Meta's Acceptable Use Policy.

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, click here. Usage of this model is subject to Meta's Acceptable Use Policy.