This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.

DeepSeek has launched a newer release, DeepSeek V3.2. We suggest considering it instead.

•DeepSeek V3.1 Terminus•

Open weights model

•

Released September 2025

DeepSeek V3.1 Terminus (Reasoning) API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of DeepSeek V3.1 Terminus (Reasoning) for your use-case.

Lowest Time per Task

Time per Intelligence Index task (minutes)

Total 2 providers

Lowest Cost per Task

Cost per Intelligence Index task

Total 2 providers

DeepSeek V3.1 Terminus is available through 2 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

    Benchmarks of providers are not available for this model.

    Please see the models page for DeepSeek V3.1 Terminus (Reasoning) for details of the model and its intelligence compared to other models.

    Inference time (minutes) per Intelligence Index task · Lower is better
    No data available
    Weighted average cost (USD) per Intelligence Index task · Lower is better
    No data available

    Pricing

    Cost per Intelligence Index Task: DeepSeek V3.1 Terminus (Reasoning)

    Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better
    No data available

    Pricing: Cache Hit, Input, and Output: DeepSeek V3.1 Terminus (Reasoning)

    Price (USD per M Tokens) · Lower is better

    Output Speed vs. Cost per Task: DeepSeek V3.1 Terminus (Reasoning)

    Output speed: output tokens divided by total request time, including time to first token · Weighted average cost (USD) per Intelligence Index task
    Most attractive quadrant
    No data available

    Speed

    Average of the single-request and multi-turn agentic workloads measured

    Output Speed: DeepSeek V3.1 Terminus (Reasoning)

    Output tokens divided by total request time · Includes time to first token · Average of the single-request and multi-turn agentic workloads measured · Higher is better
    No data available

    Latency

    Average of the single-request and multi-turn agentic workloads measured

    Time to First Answer Token: DeepSeek V3.1 Terminus (Reasoning)

    Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better
    No data available

    Reliability

    Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured

    Endpoint Error Rate: DeepSeek V3.1 Terminus (Reasoning)

    Share of requests the endpoint failed with an error, a rate limit or a timeout · Across all the single-request and multi-turn agentic workloads measured · Lower is better
    No data available

    Caching

    Cache Hit Rate: DeepSeek V3.1 Terminus (Reasoning)

    Median across multi-turn agentic session runs in the last four weeks, updated Oct 26, 2026 · Higher is better

    Cost per Task vs. Cache Hit Rate: DeepSeek V3.1 Terminus (Reasoning)

    Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Oct 26, 2026
    Most attractive quadrant
    No data available

    Key Comparison Metrics & API Features

    Novita logoNovita
    --
    --
    --
    --
    131k
    Open
    SambaNova logoSambaNova
    --
    --
    --
    --
    131k
    Open

    Frequently Asked Questions

    Common questions about DeepSeek V3.1 Terminus (Reasoning) providers