Open weight MoE
Mixture-of-experts under the MIT license. V4-Pro has about 1.6T total parameters with 49B active, V4-Flash has 284B total with 13B active.
DeepSeek V4 is the open-weight mixture-of-experts family that made DeepSeek the single largest source of tokens on OpenRouter. It comes in two sizes, V4-Pro for the hardest reasoning and coding, and V4-Flash for fast, high volume work, both with a 1 million token context. On avots.ai you run them pay per use, no subscription, and the same balance also covers Claude Opus 5, GPT-5.6, Gemini and 40+ image, video and music models.
Mixture-of-experts under the MIT license. V4-Pro has about 1.6T total parameters with 49B active, V4-Flash has 284B total with 13B active.
Both variants default to a 1 million token context window with up to 384k output, enough for whole repositories and long documents in one pass.
DeepSeek Sparse Attention with token-wise compression. At 1M context V4-Pro uses about 27 percent of the inference compute and 10 percent of the KV cache of V3.2.
V4-Pro at max reasoning hits a LiveCodeBench Pass@1 of 93.5 and about 80.6 percent on SWE-bench Verified.
V4-Pro runs at about 0.44 USD input and 0.87 USD output per million tokens, V4-Flash at about 0.14 and 0.28.
V4 focuses on text and code reasoning. For image input pair it with Gemini or GPT-5.6 on the same avots balance.
| Coding benchmark | DeepSeek V4-Pro | Gemini 3.1 Pro | Claude Opus 4.6 Max |
|---|---|---|---|
| LiveCodeBench Pass@1 (max effort) | 93.5 | 91.7 | 88.8 |
| SWE-bench Verified | about 80.6% | strong | high |
| Context window | 1M tokens | 1M tokens | 200K tokens |
| Weights | open, MIT | closed | closed |
| Price per 1M in / out | $0.44 / $0.87 | $2 / $12 | higher |
On DeepSeek's own coding evaluation V4-Pro at max reasoning tops LiveCodeBench, ahead of Gemini 3.1 Pro and Claude Opus 4.6 Max, at a fraction of the price and with open weights. Numbers are from DeepSeek's release notes and independent write-ups.
Sign up on app.avots.ai with email, Google or Telegram. Takes a minute.
1,000 tokens cost 0.99 EUR. No plan to choose, no renewal, the balance sits there until you use it.
Choose a DeepSeek V4 model in the picker, or let Agent Avots route for you. Every reply shows its token cost.
app.avots.ai on desktop and mobile, no install needed.
DeepSeek V4 in @AvotsAIbot, same balance, from any phone.
Use it inside Claude Desktop, Cursor or Cline via the MCP server.
The OpenAI compatible API takes your existing client, one key for every model.
1,000 tokens cost 0.99 EUR and DeepSeek V4 replies cost a fraction of a cent. The same balance unlocks Claude Opus 5, GPT-5.6, Gemini, Kimi K3, Veo video and Nano Banana images.
Sign up and chat ✦Every LLM on avots.ai and which one to pick per task.
Z.ai's open-weight coding model, 1M context, MIT license. Live now.
Moonshot's frontier open model, number one at coding, 1M context.
OpenAI's newest Sol, Terra and Luna tiers, 1M context. Live now.
What to use instead of ChatGPT Plus and how one balance replaces it.
Google against OpenAI, task by task, tested on one balance.
avots.ai runs 40+ AI models for chat, image, video and audio on one balance. See the full list on the Tools page or open the app and start creating.