Skip to content

Home Docs Model catalog

Overview Models Image, video & speech Coding tools Production API reference

Overview Models Image, video & speech Coding tools Production API reference

Sign in All models

Choose a model

Available models Image request builder

Chat models

Gemini chat GLM-5.3 GLM-5.3 Flash Qwen DeepSeek V4.1 / V4 Grok

deepseek-v4.1-flash

Models DeepSeek

deepseek-v4.1-flashChatExamples verified 2026-09-25

DeepSeek V4.1 Flash

Lightweight DeepSeek with max output 384,000 tokens; reads images and also supports Responses.

Official price: $0.2941 / $1.18/ 1M tokensInput / output
Context window: 1M tokens1,000,000

Notes

Model IDs carry a date suffix; bare IDs like deepseek-chat return 404.
Can't be used in Claude Code.
Priced by peak and off-peak hours; off-peak is half price.

Read the integration guideJSON Schema

Available groups

DeepSeek V4.1 Flash Official Direct

Integration guide

DeepSeek V4.1 / V4

Pricing

Official price in USD. Actual charge = official price × group multiplier.

Input: $0.2941 / 1M tokens
Cached input: $0.0059 / 1M tokens
Output: $1.18 / 1M tokens

Endpoints

POST/v1/chat/completions
POST/v1/responses

Same family

deepseek-v4-pro-202606 deepseek-v4-flash-202605

Prices come from the public catalog; limits come from specs exported from the gateway’s validation code. Actual charge = official price × group multiplier.