Skip to main content

DeepSeek V3.1 Terminus

DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. $0.27 per million input tokens, $0.95 per million output tokens. 163,840 token context window, maximum output of 32,768 tokens. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.

Input / output price
$0.27 / $1.00 per 1M
Context
164K tokens
Released
Sep 22, 2025
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "deepseek-v3.1-terminus".

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

ProviderInputOutput
OpenRouteropenrouter/deepseek-v3.1-terminus
$0.27/M$1.00/M

Is a provider down? OpenRouter status

Pricing

USD per 1M tokens on OpenRouter, after gateway discounts.

Input
$0.27 per 1M
Output
$1.00 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.27/MOpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

2.2tokens/sacross providers

Faster than 6% of the other 588 models on the gateway

Response latency

Lower is better

1.5sacross providers

Faster than 51% of the other 747 models on the gateway

Benchmarks

The Respan Index plus 12 published scores from 2 sources, each linked to where it was published.

20.5/ 100

Respan Index#125 of 175

175 ranked models. The shaded band is this model's 95% interval, 14.0 to 39.2. Qwen3.5 9B and Qwen3 235B-A22B Instruct 2507 fall inside it, so the gap is within the margin of error.
DeepSeek V3.1 Terminus by category: Coding 4.7, Agents 14.8, Reasoning 25.8, Knowledge & language 19.7, Human preference 47.8
  1. 125DeepSeek V3.1-Terminus20.5
  2. 124Qwen3.5 9B20.6
  3. 126Qwen3 235B-A22B Instruct 250720.2

Published scores

BenchmarkScore
Aider-Polyglothuggingface.co76.1%
LiveCodeBenchhuggingface.co74.9%
SWE Verifiedhuggingface.co68.4%
SWE-bench Multilingualhuggingface.co57.8%
Terminal-benchhuggingface.co36.7%

Compare DeepSeek V3.1 Terminus: DeepSeek V3.1-Terminus vs DeepSeek-V4.1-Flash-1017, DeepSeek V3.1-Terminus vs DeepSeek V4.1 Flash, DeepSeek V3.1-Terminus vs DeepSeek V4 Pro, DeepSeek V3.1-Terminus vs DeepSeek V4 Flash, DeepSeek V3.1-Terminus vs DeepSeek-V4-Flash (Preview), DeepSeek V3.1-Terminus vs DeepSeek V3.2

Apps

Use DeepSeek V3.1 Terminus in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

DeepSeek V3.1 Terminus FAQ

Short answers, built from the data on this page.

DeepSeek V3.1 Terminus is a model from Deepseek, released on Sep 22, 2025. DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. $0.27 per million input tokens, $0.95 per million output tokens. 163,840 token context window, maximum output of 32,768 tokens. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.

On the Respan gateway, DeepSeek V3.1 Terminus costs $0.27 per 1M input tokens and $1.00 per 1M output tokens on OpenRouter, after gateway discounts.

DeepSeek V3.1 Terminus is served by OpenRouter.

DeepSeek V3.1 Terminus accepts up to 164K tokens of context.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "deepseek-v3.1-terminus". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

DeepSeek V3.1 Terminus scores 20.5 out of 100 on the Respan Index v1.1, ranking #125 of 175 models. By category: Coding 4.7, Agents 14.8, Reasoning 25.8, Knowledge & language 19.7, and Human preference 47.8. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

DeepSeek V3.1 Terminus has 12 published benchmark scores, including Aider-Polyglot 76.1%, SimpleQA (agentic tool use) 96.8%, and GPQA-Diamond 80.7%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.