DeepSeek-V3.1 Terminus API

deepseek/deepseek-non-reasoner-v3.1-terminus
DeepSeek-V3.
Context
128K tokens
Input
$0.371358 / 1M tokens
Output
$1.3754 / 1M tokens
Released
Aug 28, 2025

How to use DeepSeek-V3.1 Terminus API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to deepseek/deepseek-non-reasoner-v3.1-terminus.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "deepseek/deepseek-non-reasoner-v3.1-terminus",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "deepseek/deepseek-non-reasoner-v3.1-terminus",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-non-reasoner-v3.1-terminus","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

DeepSeek-V3.1 Terminus API Pricing

TypePrice
Input
$0.371358 / 1M tokens
Output
$1.3754 / 1M tokens
Cached input
$0.371358 / 1M tokens

DeepSeek-V3.1 Terminus Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
Intelligence
15.4
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Coding
43.5
Composite score across standardised coding evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Math
89.7
Composite score across standardised mathematics evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
MMLU-Pro
85.0
Multi-discipline knowledge + reasoning (harder MMLU)SourceSeptember 22, 2026
GPQA Diamond
80.7
Google-proof graduate science questions (hardest subset)SourceSeptember 22, 2026
Humanity's Last Exam
21.7
Expert-level questions across many domainsSourceSeptember 22, 2026
LiveCodeBench
74.9
Contamination-free competitive programming problemsSourceSeptember 22, 2026
SWE-bench Verified
68.4
Resolving verified real GitHub issuesSourceSeptember 22, 2026
Terminal-Bench
36.7
Autonomous shell/terminal task completionSourceSeptember 22, 2026

DeepSeek-V3.1 Terminus vs other models

ModelInputOutputContextBest for
$0.371358 / 1M tokens
$1.3754 / 1M tokens
128K tokens
Coding + agents
$6.5 / 1M tokens
$39 / 1M tokens
1M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$1.95 / 1M tokens
$11.7 / 1M tokens
1M tokens
Reasoning + agents

Frequently asked questions

DeepSeek-V3.1 Terminus has a 128,000 tokens context window and can return up to 8,000 tokens.

DeepSeek-V3.1 Terminus takes text as input and returns text.

Use deepseek/deepseek-non-reasoner-v3.1-terminus as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

DeepSeek-V3.1 Terminus is priced at input $0.371358 / 1M tokens, output $1.3754 / 1M tokens, cached input $0.371358 / 1M tokens.

Yes, DeepSeek-V3.1 Terminus can stream responses as they are generated.

DeepSeek-V3.1 Terminus was built by DeepSeek.

Start building with DeepSeek-V3.1 Terminus

Get API Key
1000+ models, one API.