DeepSeek V4 Pro 0813

Tool calling
Streaming
1.05M context
Open weights

Model id

deepseek/deepseek-v4-pro-0813

Context window: 1.05M; tokens
Input price: $1.3; per 1M tokens
Output price: $2.6; per 1M tokens
Max output: Provider; no narrower limit

Provider list price

Pricing

USD / 1M tokens

Input	$1.3 / M tokens
Output	$2.6 / M tokens
Cache read	$0.1 / M tokens
Context window	1.05M tokens
Routing	Free

Provider list price. BYOK bills your provider; managed credits draw down at these rates. No markup or request fee. Every request is metered per engineer and joined to shipped work.

Registry 2026-09-29.1 · effective 9/17/2026 · Private rate card. Source withheld.

Registry contract

Capabilities

deepseek/deepseek-v4-pro-0813

Protocols: 3; Chat · Responses · Messages · streaming
Tools: 2; Chat · Messages
JSON Schema: None; Not supported
Vision: No; Not supported
Reasoning: None; No public control
Output limit: Provider; No narrower TokenSpend limit

canonical deepseek/deepseek-v4-pro-0813 · revision deepseek/deepseek-v4-pro-0813 · aliases deepseek-ai/DeepSeek-V4-Pro-0813, deepseek-v4-pro-0813

First request

Run it

Python · TokenSpend SDK

from tokenspend import TokenSpend

client = TokenSpend()
resp = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro-0813",
    messages=[{"role": "user", "content": "hello"}],
)

TypeScript · TokenSpend SDK

import { TokenSpend } from "@tokenspend/sdk";

const client = new TokenSpend();
const resp = await client.chat.completions.create({
  model: "deepseek/deepseek-v4-pro-0813",
  messages: [{ role: "user", content: "hello" }]
});

curl

curl https://api.tokenspend.dev/v1/chat/completions \
  -H "content-type: application/json" \
  -H "Authorization: Bearer $TOKENSPEND_API_KEY" \
  -d '{"model":"deepseek/deepseek-v4-pro-0813","messages":[{"role":"user","content":"hello"}]}'

Claude Code integration

export ANTHROPIC_BASE_URL=https://api.tokenspend.dev
export ANTHROPIC_API_KEY=$TOKENSPEND_API_KEY
export ANTHROPIC_MODEL=deepseek/deepseek-v4-pro-0813

One request shape reaches every model. Claude Code connects as an integration with two environment variables. TokenSpend never stores prompts or responses.

Questions

How much does DeepSeek V4 Pro 0813 cost?

$1.3 per 1M input tokens and $2.6 per 1M output tokens, at provider list price. TokenSpend adds no markup or request fee. Managed credits carry a 5% fee when you buy them.

What is the context window of DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 has a 1.05M token context window.

Does DeepSeek V4 Pro 0813 support tool calling?

Yes. Tool calling is supported on Chat, Messages.

Does DeepSeek V4 Pro 0813 support images?

No. Image input is not supported on DeepSeek V4 Pro 0813 through TokenSpend.

Does DeepSeek V4 Pro 0813 support reasoning?

No. Reasoning control is not supported on DeepSeek V4 Pro 0813 through TokenSpend.

Does DeepSeek V4 Pro 0813 have prompt caching?

Yes. Cache reads cost $0.1 per 1M tokens.

When were these prices last checked?

Prices follow rate card 2026-09-29.1, effective 9/17/2026. Source: Private rate card.