How much does DeepSeek V4 Pro 0813 cost?

On the Respan gateway, input starts at $0.50 per 1M tokens on Relace, and output starts at $1.98 per 1M tokens on OpenRouter, after gateway discounts. Averaged across its 14 routes from 13 providers, it costs $1.21 per 1M input tokens and $3.46 per 1M output tokens.

Which providers serve DeepSeek V4 Pro 0813 on Respan?

DeepSeek V4 Pro 0813 is available through 14 routes from 13 providers: Relace, OpenRouter, Nextbit256, DeepInfra, Baseten, EmpirioLabs, and 7 more.

What is DeepSeek V4 Pro 0813's context window?

DeepSeek V4 Pro 0813 accepts up to 1M tokens of context on its largest provider route.

How do I use DeepSeek V4 Pro 0813 with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "deepseek-v4-pro-0813". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

How fast is DeepSeek V4 Pro 0813?

Over the last 30 days of requests through the Respan gateway, the fastest provider was TogetherAI at 67 tokens per second, and the lowest response latency was 0.7 seconds on DeepInfra. Speed varies with request size and provider.

DeepSeek V4 Pro 0813

Q: What is DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 is a model from Deepseek, released on Aug 13, 2026. DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks. Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical.

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks. Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical.

Input / output, from: $0.50 / $1.98 per 1M
Weekly tokens / requests: 626.4K / 223
Context: 1M tokens
Released: Aug 13, 2026

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "deepseek-v4-pro-0813".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="deepseek-v4-pro-0813",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "deepseek-v4-pro-0813",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "deepseek-v4-pro-0813",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

14 routes from 13 providers, cheapest first, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read	Capabilities
Relace`relace/deepseek-ai/DeepSeek-V4-Pro-0813`	1M	$0.50/M	$2.00/M	$0.05/M	+2
OpenRouter`openrouter/deepseek/deepseek-v4-pro-0813`	1M	$0.66/M	$1.98/M	$0.02/M	+2
Nextbit256`nextbit256/deepseek:v4-pro-0813`	1M	$1.06/M	$3.17/M	$0.04/M
DeepInfra`deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813`	1M	$1.30/M	$2.60/M	$0.10/M	+2
Baseten`baseten/deepseek-ai/DeepSeek-V4-Pro-0813`	1M	$1.32/M	$3.96/M	$0.13/M	+2
EmpirioLabs`empiriolabs/deepseek-v4-pro-0813`	1M	$1.32/M	$3.96/M	$1.32/M	+2
Inference.net`inference_net/deepseek-v4-pro-0813`	1M	$1.32/M	$3.96/M	$0.04/M
Nebius`nebius/deepseek-ai/DeepSeek-V4-Pro-0813`	979K	$1.32/M	$3.96/M	$0.00/M	+2
Novita`novita/deepseek/deepseek-v4-pro-0813`	1M	$1.32/M	$3.96/M	$0.04/M	+2
Novita`novita/deepseek/deepseek-v4-pro-0813-p`	1M	$1.32/M	$3.96/M	$0.04/M	+2
Parasail`parasail/deepseek-ai/DeepSeek-V4-Pro-0813`	1M	$1.32/M	$3.96/M	$0.04/M	+2
Perplexity`perplexity/deepseek-v4-pro-0813`	1M	$1.32/M	$3.96/M	$0.04/M
TogetherAI`together_ai/deepseek-ai/DeepSeek-V4-Pro-0813`	1M	$1.32/M	$3.96/M	$0.13/M	+2
MangoBoost`mangoboost/deepseek-ai/DeepSeek-V4-Pro-0813`	1M	$1.50/M	$3.00/M	$0.13/M	+2

Is a provider down? OpenRouter status, Perplexity status, Together AI status

Pricing

Averaged across 14 routes from 13 providers, in USD per 1M tokens after gateway discounts.

Average input: $1.21 per 1M
Average output: $3.46 per 1M
Average cache read: $0.15 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$1.50/MMangoBoostLowest$0.50/MRelace

Throughput and latency

30-day averages from requests through the Respan gateway, 13 of 14 routes had traffic in that window. Under each figure, every model on the gateway by its average, this one in blue.