DeepSeek

DeepSeek V3.1 Terminus (Reasoning)

AI model by DeepSeek. Real-time pricing and benchmark data.

Pricing (per 1M tokens)

Input$1.64
Output$2.75
Blended (3:1)$1.92

Source: Artificial Analysis

Performance

Output Speed
Time to First Token

Median values from Artificial Analysis

Editorial Analysis

Profile. DeepSeek V3.1 Terminus (Reasoning) is a budget-tier option from DeepSeek at $2.75/M output tokens. Despite the low price, it scores competitively on Coding Index (43.5) and Intelligence Index (31.4) — making it a candidate for high-volume production workloads where unit cost dominates.

Cost model. For a workload of 1M input tokens + 100K output tokens, DeepSeek V3.1 Terminus (Reasoning) costs $1.92 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.

Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.

Compare with similar models

ModelInputOutputSpeed
DeepSeek V3.1 Terminus (Reasoning)Current
$1.64$2.75
Nemotron 3 Ultra 550B A55B (Reasoning)
$0.60$2.75146 tok/s
Llama 3 Instruct 70B
$0.65$2.75
Qwen3 235B A22B (Non-reasoning)
$0.70$2.8059 tok/s
Apertus 70B Instruct
$0.82$2.92
LongCat 2.0
$0.75$2.9544 tok/s

Example Costs

Single Request
$0.0030
1.0K in / 500 out
1K Requests/day
$3.02
1.0M in / 500.0K out
10K Requests/day
$30.15
10.0M in / 5.0M out