EasyAPI

deepseek-v4-flash-0731-tem

Chat

高效轻量化MoE模型，总参284B，激活13B，原生支持百万超长上下文能力。推理速度快、延迟低、调用成本低廉，综合能力均衡，主打高并发、轻量化任务。

Input price

$0.104230% off

Market: $0.1489

/ M

Output price

$0.208330% off

Market: $0.2976

/ M

Cache read

$0.020830% off

Market: $0.0297

/ M

Input

Text

Output

Text

API

Quick Start

Drop-in code to call this model with EasyAPI's OpenAI-compatible API.

1

Get your API key

Create an API key from your dashboard and set it as an environment variable:

Replace sk-xxxxxxxx with your API token from the console (Bearer token).

Create API token
shell
export EASYAPI_API_KEY=sk-xxxxxxxx
2

Make your first request

Use deepseek/deepseek-v4-flash-0731-tem with the EasyAPI API:

cURL
curl https://token.easyapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $EASYAPI_API_KEY" \
  -d '{"model":"deepseek/deepseek-v4-flash-0731-tem","messages":[{"role":"user","content":"Hello!"}]}'
3

Enable streaming

Add "stream": true to your request body to receive responses as server-sent events:

curl
curl -N https://token.easyapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $EASYAPI_API_KEY" \
  -d '{"model":"deepseek/deepseek-v4-flash-0731-tem","messages":[{"role":"user","content":"Hello!"}],"stream":true}'

Endpoint

Sends a chat completion request. Supports streaming and non-streaming modes.

POSThttps://token.easyapi.com/v1/chat/completions
Authorization
Bearer $EASYAPI_API_KEY
Content-Type
application/json
Model
deepseek/deepseek-v4-flash-0731-tem

发送对话补全请求，支持流式与非流式。 Docs

GEThttps://token.easyapi.com/v1/models
Authorization
Bearer $EASYAPI_API_KEY

获取当前账户可用模型列表。 Docs

Parameters

NameTypeDefaultDescription
modelstring—模型 ID，如 openai/gpt-4o、anthropic/claude-3-5-sonnet
messagesarray—对话消息列表，每项含 role 与 content
streambooleanfalse设为 true 时以 SSE 流式返回
temperaturefloat1采样温度，越高越随机
max_tokensinteger—单次回复最大生成 Token 数
top_pfloat1核采样，限制候选词累积概率
frequency_penaltyfloat0频率惩罚，降低重复用词
presence_penaltyfloat0存在惩罚，鼓励新话题

Using third-party SDKs

Official OpenAI and other SDKs work by swapping the base URL. See integration guide

Related models

deepseek-v3

DeepSeek

Open-source general-purpose LLM with representative instruction-following and coding skills within the open-weights ecosystem, suited for chat, code assistance, and enterprise text workflows.

Text
15% off
Input price

$0.2439/ M

Output price

$0.975/ M

Cache read

$0.0484/ M

Cache write

$0/ M

deepseek-v3.1

DeepSeek

Hybrid model that switches between thinking and non-thinking modes on a single endpoint, post-trained for tool use and code agent workflows.

Text
15% off
Input price

$0.4879/ M

Output price

$1.4629/ M

Cache read

$0.1105/ M

Cache write

$0/ M

deepseek-v3.2

DeepSeek

Best value for code and math. Fraction of flagship cost.

Text
15% off
Input price

$0.2439/ M

Output price

$0.3663/ M

Cache read

$0.0493/ M

Cache write

$0.3051/ M

deepseek-v3.2-exp

DeepSeek

Experimental interim release focused on long-context efficiency, with optional reasoning mode and V3.1-level performance overall.

Text
15% off
Input price

$0.2439/ M

Output price

$0.3655/ M

Cache read

$0/ M

Cache write

$0/ M