DeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus is DeepSeek's September 22, 2025 refined iteration of V3.1. It delivers more stable outputs with improvements to multilingual consistency, Code Agent performance, and Search Agent capability.
View API reference- Input and output price
- Input $0.27, Output $1, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'deepseek/deepseek-v3.1-terminus', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out DeepSeek V3.1 Terminus by DeepSeek. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
DeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call DeepSeek V3.1 Terminus through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'deepseek/deepseek-v3.1-terminus', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same DeepSeek V3.1 Terminus request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'deepseek/deepseek-v3.1-terminus', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. deepseek/deepseek-v3.1-terminus. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. DeepSeek V3.1 Terminus supports up to 65,536 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 131K-token context window |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK deepseek provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'deepseek/deepseek-v3.1-terminus', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['novita'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'deepseek/deepseek-v3.1-terminus', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'deepseek/deepseek-v3.1-terminus', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by DeepSeek
| Model |
|---|
| 1M | 1.3 s | 331 tps | $0.22/M | $0.66/M | Read$0.007/M | — | +1 | | 09/08/2026 | |||||
| 1M | 0.4 s | 172 tps | $0.22/M | $0.65/M | Read$0.007/M | — | +1 |   +1 | 08/21/2026 | |||||
| 1M | 0.3 s | 107 tps | $0.60/M | $1.90/M | Read$0.02/M | — |   +8 | 08/12/2026 | ||||||
| 1M | 0.5 s | 244 tps | $0.07/M | $0.15/M | Read$0.007/M | — |  +16 | 07/31/2026 | ||||||
| 1M | 0.5 s | 223 tps | $0.08/M | $0.18/M | Read$0.007/M | — |  +7 | 04/23/2026 | ||||||
| 1M | 0.6 s | 139 tps | $0.66/M | $1.98/M | Read$0.02/M | — | +4 | 04/23/2026 |
Copy link to headingAbout DeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus was released September 22, 2025 as a refined iteration of DeepSeek-V3.1, responding directly to user feedback from V3.1's August release. Rather than introducing new architectural features, Terminus focuses on reliability. It eliminates Chinese-English language-mixing errors, removes spurious random character insertions, and delivers more consistent outputs across benchmarks.
The "Terminus" designation signals a mature, production-hardened checkpoint rather than an intermediate development release. Benchmark comparisons show DeepSeek V3.1 Terminus delivers more stable results than V3.1, with particular strength in Code Agent and Search Agent performance. Output consistency in these areas directly affects task success rates in automated pipelines. Weights are available on Hugging Face at the official DeepSeek repository.
The model launched simultaneously across DeepSeek's App, Web, and API surfaces, making it the production-recommended version of the V3.1 generation. If you're running V3.1 and experienced inconsistent multilingual outputs or agent reliability issues, Terminus is the designated upgrade path within the same generation before moving to V3.2.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: If your application processes mixed Chinese-English content or relies on agentic tool use, DeepSeek V3.1 Terminus's targeted improvements make it the preferred choice over earlier V3.1 for production.
- Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use DeepSeek V3.1 Terminus
Best for
- Mixed Chinese-English production: V3.1's language mixing issues are resolved, making Terminus suitable for multilingual production deployments
- Reliable code agent pipelines: Output consistency and stable function-call behavior are critical to high task completion rates
- Search agent integrations: Reliable multi-step retrieval and synthesis with fewer random output artifacts
- Drop-in V3.1 upgrade: Teams on V3.1 get stability improvements without migrating to a new API surface or model generation
Consider alternatives when
- Beyond V3.1 generation: Use DeepSeek-V3.2 for the next major iteration when new capabilities are required
- Simple general-purpose model: DeepSeek-V3 may serve your workload at lower cost when hybrid thinking modes aren't required
- Greenfield integrations: V3.2 may be a better fit when you want the broader V3.2 generation feature set over Terminus's stability focus
Copy link to headingConclusion
DeepSeek V3.1 Terminus is the production-recommended checkpoint for the DeepSeek V3.1 generation. It delivers V3.1's hybrid inference and agentic capabilities with targeted fixes for the multilingual and reliability issues users reported. If you're experiencing inconsistent V3.1 outputs, Terminus is the direct upgrade path.
Copy link to headingFrequently Asked Questions
What does "Terminus" mean in the context of DeepSeek V3.1 Terminus?
Terminus indicates a mature, production-hardened iteration within the V3.1 generation. It's a refined checkpoint that addresses real-world feedback before the model family advances to the next major version.
What specific output quality problems does DeepSeek V3.1 Terminus fix over V3.1?
It fixes Chinese-English language-mixing errors and random character insertions reported after V3.1's initial deployment. Outputs are more predictable and consistent.
How does DeepSeek V3.1 Terminus compare to V3.1 on benchmarks?
DeepSeek V3.1 Terminus delivers more stable outputs across benchmarks, with particular improvements in Code Agent and Search Agent task performance.
Are the model weights publicly available?
Yes. Weights are published on Hugging Face at the official DeepSeek repository, alongside API access through AI Gateway.
Is DeepSeek V3.1 Terminus backward compatible with existing V3.1 integrations?
Yes. Terminus shares the same API surface as V3.1, including the
deepseek-chatanddeepseek-reasonerendpoints for non-thinking and thinking modes respectively.Was DeepSeek V3.1 Terminus launched across all DeepSeek surfaces simultaneously?
Yes. It launched across the DeepSeek App, Web interface, and API on September 22, 2025.
Should I upgrade from V3.1 to Terminus or wait for V3.2?
If multilingual consistency or Code/Search Agent reliability are pain points, upgrade to Terminus now. It's the designated fix for those issues. If you're planning a broader migration, V3.2 is the next major generation step.