# DeepSeek Models via Hanzo AI — 18 models > Access 18 DeepSeek models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing. [Models](https://hanzo.ai/models)/DeepSeek # DeepSeek Models via Hanzo AI 18 models available Access all 18 DeepSeek models through Hanzo's OpenAI-compatible API. One key, one bill, no rate limit juggling. [Get API Access](https://hanzo.ai/signup)[API Docs](https://docs.hanzo.ai) Instant Guest API Keyguest_temp_key No account or sign up required Test right now from your terminal. No credentials needed: cURL · instant guest request Copy ``` curl https://api.hanzo.ai/v1/chat/completions \ -H "Authorization: Bearer guest_temp_key" \ -d '{"model": "zen-free", "messages": [{"role": "user", "content": "hello"}]}' ``` [DeepSeek V3164KDeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...text](https://hanzo.ai/models/deepseek/deepseek-chat) [DeepSeek V3 0324164KDeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...text](https://hanzo.ai/models/deepseek/deepseek-chat-v3-0324) [DeepSeek V3.1164KDeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...text](https://hanzo.ai/models/deepseek/deepseek-chat-v3.1) [R1 0528164KMay 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...text](https://hanzo.ai/models/deepseek/deepseek-r1-0528) [DeepSeek V3.1 Terminus164KDeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...text](https://hanzo.ai/models/deepseek/deepseek-v3.1-terminus) [DeepSeek V3.2164KDeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...text](https://hanzo.ai/models/deepseek/deepseek-v3.2) [DeepSeek V3.2 Exp164KDeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...text](https://hanzo.ai/models/deepseek/deepseek-v3.2-exp) [DeepSeek V4 Flash 04231MDeepSeek 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. It is designed for fast inference and...text](https://hanzo.ai/models/deepseek/deepseek-v4-flash) [DeepSeek V4 Flash 07311MDeepSeek 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....text](https://hanzo.ai/models/deepseek/deepseek-v4-flash-0731) [DeepSeek V4 Flash Vision Exp1MDeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...text](https://hanzo.ai/models/deepseek/deepseek-v4-flash-vision-exp) [DeepSeek V4 Pro 04231MDeepSeek 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. It is designed for advanced reasoning, coding,...text](https://hanzo.ai/models/deepseek/deepseek-v4-pro) [DeepSeek V4 Pro 08131MDeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.text](https://hanzo.ai/models/deepseek/deepseek-v4-pro-0813) [DeepSeek V4.1 Flash1MDeepSeek 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...text](https://hanzo.ai/models/deepseek/deepseek-v4.1-flash) [DeepSeek V4.1 Flash 10171MDeepSeek 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...text](https://hanzo.ai/models/deepseek/deepseek-v4.1-flash-1017) [DeepSeek V4.1 Flash (batch)1MDeepSeek 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...text](https://hanzo.ai/models/deepseek/deepseek-v4.1-flash:batch) [DeepSeek Flash Latest1MThis model always redirects to the latest model in the DeepSeek Flash family.text](https://hanzo.ai/models/deepseek/deepseek-flash-latest) [DeepSeek Pro Latest1MThis model always redirects to the latest model in the DeepSeek Pro family.text](https://hanzo.ai/models/deepseek/deepseek-pro-latest) [DeepSeek V4 Flash Latest1MThis model always redirects to the latest model in the DeepSeek V4 Flash family.text](https://hanzo.ai/models/deepseek/deepseek-v4-flash-latest) ## Use DeepSeek models via Hanzo One key. One bill. Works with every SDK you already have. [Start Free](https://platform.hanzo.ai/api-keys)[Browse All Models](https://hanzo.ai/models)