DeepSeek V4 Pro

DeepSeek's Pro model, called with the name deepseek-v4-pro. It has a 1M-token context and up to 384K tokens of output. It takes text only, not images.

Model namedeepseek-v4-pro
Served byDeepSeek-V4-Pro-0813
Context1M
Max output384K
Image inputNo
Concurrent requests500
US dollars per 1M tokens
ModelInput, cache hitInput, cache missOutput
DeepSeek V4 ProDeepSeek, peak hours$0.044$1.32$3.96
DeepSeek, off-peak$0.022$0.66$1.98
HaryAI$0.022$0.594$1.782

Get started

Ask an AI to do it

Send this to Codex or Claude Code (or whatever AI assistant you use). Put your key in place of <your HaryAI key> first.

Codex
Set up Codex on this computer to use HaryAI.

1. Back up ~/.codex/config.toml (copy it to ~/.codex/config.toml.bak). If it doesn't exist, create it.
2. Add these settings. If a setting with the same name is already there, change its value. Leave everything else as it is.

```toml
model = "deepseek-v4-pro"
model_provider = "haryai"
forced_login_method = "api"
model_reasoning_effort = "high"

[model_providers.haryai]
name = "HaryAI"
base_url = "https://api.haryai.com/v1"
wire_api = "responses"
experimental_bearer_token = "<your HaryAI key>"
```

3. Then tell me to quit Codex completely, reopen it, and send a short message to check that it answers.
4. Also tell me how to undo this: put the backup back and reopen Codex.
Claude Code
Set up Claude Code on this computer to use HaryAI.

1. Back up ~/.claude/settings.json (copy it to ~/.claude/settings.json.bak). If it doesn't exist, create it containing {}.
2. Add the entries below to the "env" object in that file. If an entry with the same name is already there, change its value. Keep every other setting, and keep the file valid JSON.

```json
{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.haryai.com",
    "ANTHROPIC_AUTH_TOKEN": "<your HaryAI key>",
    "ANTHROPIC_MODEL": "deepseek-flash[1m]",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "deepseek-flash[1m]",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "deepseek-flash[1m]",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "deepseek-flash",
    "CLAUDE_CODE_SUBAGENT_MODEL": "deepseek-flash",
    "CLAUDE_CODE_EFFORT_LEVEL": "max",
    "CLAUDE_CODE_AUTO_COMPACT_WINDOW": "786432",
    "CLAUDE_CODE_DISABLE_ARTIFACT": "1"
  }
}
```

3. Then tell me to start a new Claude Code session and send a short message to check that it answers.
4. Also tell me how to undo this: put the backup back and start a new session.

One click with CC Switch

CC Switch is a free app that switches your tools between providers. Install it from its GitHub releases page. Account page

Write code

OpenAI format
https://api.haryai.com/v1
Anthropic format
https://api.haryai.com
Model
deepseek-v4-pro

Questions

What model name do I use?

deepseek-v4-pro.

How does its price compare with Flash?

Input costs 4.4 times as much as on V4.1 Flash. See the comparison for every price.

Can it read screenshots?

No. For images, use V4.1 Flash.

Sources

DeepSeek's figures are from its own docs, checked on 2026-11-15.

DeepSeek at 55% off the official price

Cheaper than DeepSeek's own off-peak price, around the clock.