~deepseek Pro Latest

~deepseek-pro-latest by DeepSeek Released August 13, 2026
Reasoning · Function calling · Structured output · Prompt caching · EU hosting · Up to 35% off
Input from
$0.429 / 1M
Output from
$1.287 / 1M
Cached input from
$0.022 / 1M
Context window
1.05M
Endpoints
7
from 7 providers
Regions
Global, Asia, Europe, United States

About ~deepseek Pro Latest

A flagship Mixture-of-Experts (MoE) large language model with 1.6 trillion total parameters and 49 billion activated parameters. It natively supports context windows of up to 1 million tokens. Trained on extensive high-quality data, the model delivers strong performance in mathematical and logical reasoning, complex reasoning, professional code generation, and in-depth long-document analysis, and is suitable for demanding scenarios such as advanced scientific research, complex enterprise workflows, and sophisticated agentic applications.

~deepseek Pro Latest is a chat model by DeepSeek, available on Eden AI through 7 endpoints from 7 providers, from $0.429 per million input tokens and $1.29 per million output tokens, with a context window of up to 1.05M tokens.

Providers and prices

7 endpoints from 7 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you.

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
Qwenqwen/deepseek-v4-pro-0813
Global
1M
$0.66$0.429
$1.287
$0.0429
−35% · Reasoning · Tools · JSON · Cache
Tencent Cloud (Asia)tencent/deepseek-v4-pro-0813
Asia
1M
$0.66
$1.98
$0.022
Reasoning · Tools · JSON · Cache
DeepInfra (United States)deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813
United States
1.05M
$1.3
$2.6
$0.1
Reasoning · Tools · JSON · Cache
Cloudflare (CF/DEEPSEEK-AI/DEEPSEEK-V4-PRO-0813)cloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813
CF/DEEPSEEK-AI/DEEPSEEK-V4-PRO-0813
1.05M
$1.32
$3.96
$0.044
Reasoning · Tools · JSON · Cache
Nebiusnebius/deepseek-ai/DeepSeek-V4-Pro-0813
Global
1.05M
$1.32
$3.96
$1.32
Reasoning · Tools · Cache
Together AItogether_ai/deepseek-ai/DeepSeek-V4-Pro-0813
Global
1.05M
$1.32
$3.96
$0.13
Reasoning · Tools · JSON · Cache
TensorX (Europe)tensorx/deepseek/deepseek-v4-pro-0813
Europe
1.05M
$2
$4
$0.5
Reasoning · Tools · Cache

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
1.01 s
TensorX (Europe)
Lowest latency
2.49 s
TensorX (Europe)
Highest throughput
103.59 tok/s
Together AI
Best availability
100%
Tencent Cloud (Asia)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Qwen
2.9 s
11.64 s
259.31 s
46.84 tok/s
99.53%
80.33%
0.52%
9.04%
Tencent Cloud (Asia)
3.6 s
7.23 s
45.77 s
46.33 tok/s
100%
97.96%
0%
0%
DeepInfra (United States)
2.64 s
4.8 s
24.49 s
42.42 tok/s
100%
82.24%
1.04%
0%
Together AI
1.3 s
3.12 s
25.67 s
103.59 tok/s
99.69%
94.22%
0.45%
0%
TensorX (Europe)
1.01 s
2.49 s
14.43 s
62.42 tok/s
100%
69.86%
0.79%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call ~deepseek Pro Latest with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "~deepseek-pro-latest",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about ~deepseek Pro Latest

On Eden AI, prices for this model start at $0.429 per million input tokens and $1.287 per million output tokens. Prices differ by endpoint; the providers table lists each one.

Up to 1.05M tokens, depending on the endpoint.

7 endpoints from 7 providers, available in: Global, Asia, Europe, United States. All of them are called with the same Eden AI API key.

Can I run ~deepseek Pro Latest in the EU? Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU. ‖ How fast is ~deepseek Pro Latest? Over the last 30 days, the fastest first token was 1.01 s (TensorX (Europe)) and the highest throughput was 103.59 tokens per second (Together AI).