DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813
NewFlagshipFeatured
ToolsJSONReasoning
by DeepSeek · 2026-08-12

DeepSeek V4 Pro 0813 is the official release of DeepSeek's flagship V4 Pro model, superseding the April preview and rolled out simultaneously across the app, web, and API. It serves a 1M-token context window with up to 384K output tokens, supports thinking and non-thinking modes with selectable low / high / max reasoning effort, plus JSON output and tool calls, and natively speaks the Responses API with a targeted adaptation for Codex-style coding agents. The 0813 revision is a major step up in agent capability, with DeepSeek reporting especially strong gains in production environments on its published agent benchmarks — 87.9 on Terminal Bench 2.1, 83.3 on Cybergym, 74.1 on Toolathlon Verified, 62.7 on DeepSWE, 61.5 on NL2Repo, and 42.7 / 60.0 on HLE without / with tools. On the DeepSeek first-party API this revision is what the deepseek-v4-pro model id now serves; the dated identifier lists the same revision for callers that reference it by date. It is a strong pick for demanding coding agents, terminal and tool-use workloads, and complex agentic pipelines.

ctx1M tokens
Max output384K
Inputtext
Outputtext
p50 TTFT958 ms
INPUT$0.44/ 1M tokens
OUTPUT$0.88/ 1M tokens
p50 TTFT958 ms7d
p95 TTFT1.89 s7d
TRAFFIC87.9Mtokens / 7d

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
  • Anthropic SDKhttps://api.orcarouter.ai
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro-0813",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • reasoning
  • reasoning_effort
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Pricing

Input / 1M tokens$0.442
Output / 1M tokens$0.884
Cache read / 1M$0.060
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $5.75 · With prompt caching $4.41

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.000451

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
958 ms
Output speed
65.0 tok/s
p95 TTFT
1.89 s
Error rate
0%

Public benchmarks

Agent Last Exam
25.7
Automation Bench (Public)
31.8
Cybergym
83.3
DeepSWE
62.7
HLE (no tools)
42.7
HLE (with tools)
60.0
NL2Repo
61.5
Terminal Bench 2.1
87.9
Toolathlon Verified
74.1
Source: api-docs.deepseek.com

Community buzz

What developers are saying this week

Hacker News9 mentions · 7dup 9 vs the previous week

How it compares

DeepSeek V4 Pro 0813DeepSeek V4 ProDeepSeek V4 FlashDeepSeek V4 Flash 0731
Input $/M$0.44$0.44$0.15$0.15
Output $/M$0.88$0.88$0.29$0.29
Context1.0M1.0M1.0M1.0M
Quality7/108/107/106/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

How much does DeepSeek: DeepSeek V4 Pro 0813 cost on OrcaRouter?
DeepSeek: DeepSeek V4 Pro 0813 is priced at $0.44 per 1M input tokens and $0.88 per 1M output tokens via OrcaRouter. Pricing is pulled live from the routing layer.
What is DeepSeek: DeepSeek V4 Pro 0813's context window?
DeepSeek: DeepSeek V4 Pro 0813 supports a context window of 1M tokens. Use long-context features (RAG, summarisation) up to that limit.
How do I call DeepSeek: DeepSeek V4 Pro 0813 via the OpenAI SDK?
Set OpenAI base_url to https://api.orcarouter.ai/v1, supply your OrcaRouter API key, and pass model="deepseek/deepseek-v4-pro-0813" in the chat.completions.create call.
Does OrcaRouter rate-limit DeepSeek: DeepSeek V4 Pro 0813?
Per-model rate limits follow your OrcaRouter plan. Free tiers ship with conservative caps; paid tiers lift them. Check /pricing for current quotas.

Embed this badge

DeepSeek: DeepSeek V4 Pro 0813$0.44/M in958ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/deepseek/deepseek-v4-pro-0813" target="_blank"> <img src="https://www.orcarouter.ai/embed/deepseek/deepseek-v4-pro-0813.svg" alt="DeepSeek: DeepSeek V4 Pro 0813 on OrcaRouter" /> </a>
Markdown [![DeepSeek: DeepSeek V4 Pro 0813](https://www.orcarouter.ai/embed/deepseek/deepseek-v4-pro-0813.svg)](https://www.orcarouter.ai/models/deepseek/deepseek-v4-pro-0813)

Model card as data

GET /api/public/models/deepseek/deepseek-v4-pro-0813Open
Machine-readable:/llms.txt/llms-full.txt