Every model.One place.

An experimental vision-enabled DeepSeek V4 Flash model that adds image understanding while retaining the text, reasoning, coding, tool-calling, and agent capabilities of the base model.

Model ID

deepseek/deepseek-v4-flash-vision-exp

Discovery tier

Efficient

Context window

1,048,576 tokens

The October 17, 2026 snapshot of DeepSeek V4.1 Flash supports text and image input, tool calling, and optional reasoning with low, high, and max effort. It has a shared 1,048,576-token context window and supports up to 393,216 output tokens within the remaining context. Released under the MIT license.

Model ID

deepseek/deepseek-v4.1-flash-1017

Discovery tier

Open weights

Context window

1,048,576 tokens

The October 17, 2026 snapshot of DeepSeek V4.1 Flash supports text and image input, tool calling, and optional reasoning with low, high, and max effort. It has a shared 1,048,576-token context window and supports up to 393,216 output tokens within the remaining context. Released under the MIT license.

Model ID

deepseek/deepseek-v4.1-flash-1017:thinking

Discovery tier

Open weights

Context window

1,048,576 tokens

The original 0423 checkpoint of DeepSeek V4 Flash, with a 1M-token context window, text input, tool calling, structured output, and optional reasoning.

Model ID

deepseek/deepseek-v4-flash-0423

Discovery tier

Open weights

Context window

1,048,576 tokens

The original 0423 checkpoint of DeepSeek V4 Flash, with a 1M-token context window, text input, tool calling, structured output, and optional reasoning.

Model ID

deepseek/deepseek-v4-flash-0423:thinking

Discovery tier

Open weights

Context window

1,048,576 tokens

A lower-refusal finetune of DeepSeek V4.1 Flash with text input, optional reasoning, and tool calling. Supports a context window of up to 1M tokens.

Model ID

deepseek/deepseek-v4.1-flash-uncensored

Discovery tier

Open weights

Context window

1,048,576 tokens

A lower-refusal finetune of DeepSeek V4.1 Flash with text input, optional reasoning, and tool calling. Supports a context window of up to 1M tokens.

Model ID

deepseek/deepseek-v4.1-flash-uncensored:thinking

Discovery tier

Open weights

Context window

1,048,576 tokens

DeepSeek V4.1 Flash's October 17, 2026 checkpoint (1017) supports text and image input, reasoning, tool calling, and structured output with a 1M-token context window. This route runs through Tinfoil attested inference inside a Trusted Execution Environment. Tinfoil lists this model as experimental, with availability subject to change.

Model ID

TEE/deepseek-v4.1-flash

Discovery tier

Open weights

Context window

1,048,576 tokens

DeepSeek V4.1 Flash supports text and image input, reasoning, tool calling, and structured output with a 1M-token context window. This is a rate-limited beta with limited capacity, intended for testing rather than production use.

Model ID

deepseek/deepseek-v4.1-flash

Discovery tier

Open weights

Context window

1,000,000 tokens

DeepSeek V4.1 Flash supports text and image input, reasoning, tool calling, and structured output with a 1M-token context window. This is a rate-limited beta with limited capacity, intended for testing rather than production use.

Model ID

deepseek/deepseek-v4.1-flash:thinking

Discovery tier

Open weights

Context window

1,000,000 tokens

DeepSeek V4 Pro 0813 is the general-availability release of DeepSeek V4 Pro, built for coding, tool use, cybersecurity, automation, and long-horizon agent workflows. DeepSeek reports strong gains over the preview and scores above Opus 4.8 on Terminal Bench 2.1, Cybergym, DeepSWE, and AutomationBench. It supports a 1M-token context window.

Model ID

deepseek/deepseek-v4-pro-0813

Discovery tier

Open weights

Context window

1,048,576 tokens

DeepSeek V4 Pro 0813 Thinking enables reasoning by default on the general-availability release of DeepSeek V4 Pro, built for coding, tool use, cybersecurity, automation, and long-horizon agent workflows. DeepSeek reports strong gains over the preview and scores above Opus 4.8 on Terminal Bench 2.1, Cybergym, DeepSWE, and AutomationBench. It supports a 1M-token context window.

Model ID

deepseek/deepseek-v4-pro-0813:thinking

Discovery tier

Open weights

Context window

1,048,576 tokens

Moving alias for DeepSeek V4.1 Flash 1017, with text and image input, tool calling, structured output, and optional reasoning. Zero data retention and JSON Schema output are available on eligible routes; output limits and reasoning levels depend on the selected route.

Model ID

deepseek/deepseek-v4-flash-latest

Discovery tier

Open weights

Context window

1,048,576 tokens

DeepSeek V4 Flash 0731 Thinking enables reasoning by default on the re-post-trained Mixture-of-Experts model with a 1M-token context window, built for coding, reasoning, and agent workflows.

Model ID

deepseek/deepseek-v4-flash-0731:thinking

Discovery tier

Open weights

Context window

1,048,576 tokens

DeepSeek V4 Flash 0731 is a re-post-trained Mixture-of-Experts model with a 1M-token context window, built for coding, reasoning, and agent workflows.

Model ID

deepseek/deepseek-v4-flash-0731

Discovery tier

Open weights

Context window

1,048,576 tokens

Compatibility alias that routes to the newest thinking DeepSeek model. Currently routes to DeepSeek V4 Pro 0813 Thinking, the general-availability release built for coding, tool use, cybersecurity, automation, and long-horizon agent workflows. Requests are routed through privacy-friendly third-party providers and are not sent directly to DeepSeek.

Model ID

deepseek/deepseek-latest

Discovery tier

Open weights

Context window

1,048,576 tokens

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with a 1M-token context window, built for fast inference, high-throughput workloads, reasoning, coding, and agent workflows.

Model ID

deepseek/deepseek-v4-flash

Discovery tier

Open weights

Context window

1,048,576 tokens

DeepSeek V4 Flash Thinking enables DeepSeek's reasoning mode on the efficiency-optimized Mixture-of-Experts model with a 1M-token context window, built for fast inference, high-throughput workloads, reasoning, coding, and agent workflows.

Model ID

deepseek/deepseek-v4-flash:thinking

Discovery tier

Open weights

Context window

1,048,576 tokens

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with a 1M-token context window, built for advanced reasoning, coding, long-horizon agent workflows, knowledge, math, and software engineering tasks.

Model ID

deepseek/deepseek-v4-pro

Discovery tier

Open weights

Context window

1,048,576 tokens

DeepSeek V4 Pro Thinking enables DeepSeek's chain-of-thought mode on the large-scale Mixture-of-Experts model with a 1M-token context window, built for advanced reasoning, coding, long-horizon agent workflows, knowledge, math, and software engineering tasks.

Model ID

deepseek/deepseek-v4-pro:thinking

Discovery tier

Open weights

Context window

1,048,576 tokens