deepseek/deepseek-flash
1M context · $0.1800 / M input tokens · $0.7200 / M output tokens
DeepSeek V4.1 Flash is a DeepSeek model route on OurToken for developers who need native image understanding, very long context, and cost-efficient production traffic. It replaces the retired V4 Flash line and is called through the deepseek-flash model ID.
Historical uptime data is collected over time. Current status reflects the latest health check.
Pricing
Pay-per-use
No upfront costs, pay only for what you use
API Usage
API Access Guide
Code examples
Use the OurToken API endpoint for this model. The examples below use direct HTTP requests and the recommended endpoint for the model family.
curl https://api.ourtoken.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "deepseek-flash",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"max_tokens": 256
}'Chat Completions API Reference
Create a chat response with the OpenAI Chat Completions-compatible endpoint. Use https://api.ourtoken.ai/v1 as the SDK Base URL and POST /chat/completions as the endpoint.
Authorization
| Content-Type | application/json |
| Authorization | Bearer YOUR_API_KEY |
Request Body
| Field | Type | Required | Description |
|---|---|---|---|
| model | string | Required | Model ID to call. |
| messages | array<object> | Required | Conversation messages sent to the model. |
| max_tokens | integer | Optional | Maximum number of output tokens. |
| temperature | number | Optional | Sampling temperature. |
| top_p | number | Optional | Nucleus sampling parameter. |
| stream | boolean | Optional | Whether to return a streaming response. |
| stream_options | object | Optional | Additional options for streaming responses. |
| tools | array<object> | Optional | Tools available to the model. |
| tool_choice | string | object | Optional | Controls how the model selects tools. |
| response_format | object | Optional | Controls structured output, such as JSON object responses. |
Response Body
| Field | Type | Required | Description |
|---|---|---|---|
| id | string | Required | Unique chat completion identifier. |
| object | "chat.completion" | Required | Object type returned by the Chat Completions API. |
| created | integer | Required | Unix timestamp when the response was created. |
| model | string | Required | Model that produced the response. |
| choices | array<object> | Required | Candidate responses returned by the model. |
| choices[].message.role | string | Required | Role of the returned chat message. |
| choices[].message.content | string | Optional | Text content in the returned chat message. |
| choices[].finish_reason | string | Optional | Reason generation stopped. |
| usage | object | Optional | Token usage information for the chat completion. |
| usage.prompt_tokens | integer | Optional | Input token count. |
| usage.completion_tokens | integer | Optional | Output token count. |
| usage.total_tokens | integer | Optional | Total token count. |
| usage.prompt_tokens_details | object | Optional | Breakdown of input token usage. |
| usage.prompt_tokens_details.cached_tokens | integer | Optional | Tokens served from cache. |
Model Introduction
DeepSeek deepseek-flash
DeepSeek V4.1 Flash is a DeepSeek model route on OurToken for developers who need native image understanding, very long context, and cost-efficient production traffic. It replaces the retired V4 Flash line and is called through the deepseek-flash model ID.
DeepSeek V4.1 Flash gives teams a lower-cost DeepSeek route with a 1M-token context window, native image understanding, and up to 384K output tokens for application work that needs long prompts and predictable pricing. Use DeepSeek V4.1 Flash API when you want to test DeepSeek workflows through the OurToken unified API while keeping model IDs, usage logs, cache costs, and price review in one dashboard.
Why It Looks Great
- 60% of the official peak DeepSeek V4.1 Flash reference price for input and output tokens.
- OpenAI-compatible API setup through the same OurToken endpoint used by other supported models.
- A 1M-token context window with up to 384K output tokens for long documents, repositories, and multi-turn agents.
- Native image understanding, so vision and text prompts can travel in a single request.
- Dashboard logs and usage visibility help teams review request cost after launch.
Key Features
- Model ID: deepseek-flash
- Input price: $0.1800 per 1M tokens on OurToken
- Output price: $0.7200 per 1M tokens on OurToken
- Cache read price: $0.0036 per 1M tokens on OurToken
- Cache write price: $0 per 1M tokens on OurToken
- Provider: DeepSeek
Specifications
DeepSeek V4.1 Flash API Features
OurToken covers DeepSeek V4.1 Flash API access, pricing, model ID, context limits, and developer workflow. This route keeps a single key across chat, coding, and agent traffic while usage logs and cost stay visible.
Unified API Access
Call DeepSeek V4.1 Flash API through the same OpenAI-compatible endpoint OurToken uses for every supported model. One API key covers chat completions, responses, and Anthropic-style messages, so you can compare DeepSeek V4.1 Flash against other routes without maintaining a separate provider integration path.
Transparent Token Pricing
OurToken lists DeepSeek V4.1 Flash price per million tokens for input, output, cache read, and cache write, next to the official peak reference price. Because the model bills cache hits far below cache misses and off-peak traffic below peak, checking this table before you scale helps you forecast spend.
1M Context Window
DeepSeek V4.1 Flash supports a 1M-token context window with up to 384K output tokens, which suits long documents, large repositories, and multi-turn agents. On OurToken you can send long prompts and watch how cache read pricing changes the cost of repeated context.
Vision and Multimodal Input
V4.1 Flash is DeepSeek's first Flash build with native image understanding, so a single deepseek v4.1 flash api call can mix screenshots, scanned pages, or diagrams with text instructions. Combine that with a 1M context window for document review and visual QA workflows.
Thinking and Tool Calls
The model runs in thinking mode by default and also supports non-thinking mode, tool calls, JSON output, and structured responses. That combination fits assistants that must reason through a task and then return machine-readable payloads your application can validate.
Agent and Coding Workflows
Point coding agents such as Claude Code, Codex CLI, or OpenCode at the OurToken endpoint and select DeepSeek V4.1 Flash as the model. OurToken publishes setup guides for these tools, and the Responses API plus Anthropic-compatible endpoint keep existing agent integrations working.
How to Use DeepSeek V4.1 Flash on OurToken
Follow six steps to move from a new API key to production traffic: pick the model ID, send a first request, compare DeepSeek V4.1 Flash API pricing, then monitor usage and cost.
Create an API Key
Sign in to OurToken and create a key from the API Keys page. Copy it into your environment rather than into source control, then confirm the key is active before you build the rest of the integration around DeepSeek V4.1 Flash.
01Select the Model ID
Use deepseek-flash as the model value for new integrations. If you already ship deepseek-v4-flash or deepseek-v4-flash-vision-exp, those names still resolve and are served by V4.1 Flash, so migration can wait until your next release cycle.
02Send Your First Request
Point your client at the OurToken chat completions endpoint and send a short prompt before adding complexity. Streaming, system prompts, and multi-turn history all follow the OpenAI request shape, so existing SDK code usually needs only a base URL and model change.
03Compare Pricing and Cache Cost
Check the DeepSeek V4.1 Flash price table for input, output, and cache read, and note that off-peak traffic costs less than peak hours. Then estimate your own prompt mix, because cache hit rates decide most of the bill in agent workloads.
04Configure Thinking and Tools
Decide whether each workload should run in thinking mode or non-thinking mode, then define your tools and JSON schema if the response feeds another system. Test both settings against the same prompts before you commit to a default.
05Monitor Usage and Cost
Watch request logs, token counts, and cost per model in the OurToken dashboard after launch. Compare latency and quality against the routes you already run, and recheck DeepSeek V4.1 Flash API pricing whenever DeepSeek updates official rates.
06DeepSeek V4.1 Flash FAQ
Answers to the questions developers ask before adopting this route: what it is, what it costs, which model ID to use, what it supports, and how the V4 Pro change affects existing traffic.