Released 85 days after DeepSeek R1 (0528) · All DeepSeek releases
DeepSeek-V3.1, released in August 2025, was one of the first production-ready hybrid inference models, combining thinking and non-thinking modes within a single 671-billion-parameter MoE. Both modes activate 37 billion parameters per token and support a 128K-token context, letting developers switch between multi-step reasoning and direct answers via the chat template. Thinking mode performs chain-of-thought reasoning at quality comparable to the earlier R1 model while reaching answers faster, and non-thinking mode delivers quick, tool-compatible responses with function calling support. Post-training notably strengthened agent and tool-use skills, with widely reported improvements in multi-step reasoning over its predecessor. Open weights are available on Hugging Face. V3.1 suits agentic systems that need to move dynamically between rapid inference and deeper reasoning depending on the task.
Call DeepSeek V3.1 on Opper with the OpenAI SDK. Sign up without a credit card. Get started
DeepSeek V3.1 runs on 4 different routes through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.
DeepSeek V3.1 runs on 2 independently monitored routes through the Opper gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 2 further routes for this model are not on the board yet and are not counted above. See uptime for every provider Opper monitors.
Each route hosting DeepSeek V3.1 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; unknown; DPA available.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; DPA available.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; DPA available.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; unknown; DPA available.
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call DeepSeek V3.1 through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.
DeepSeek V3.1 is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "deepinfra/deepseek-ai/DeepSeek-V3.1",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
