DeepSeek

DeepSeek V4 Pro 0813 (Reasoning, Max Effort)

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

Pricing (per 1M tokens)

Input$1.32
Output$3.96
Blended (3:1)$1.98

Source: Artificial Analysis

Performance

Output Speed60 tok/s
Time to First Token1900ms

Median values from Artificial Analysis

Editorial Analysis

Profile. DeepSeek V4 Pro 0813 (Reasoning, Max Effort) is a budget-tier option from DeepSeek at $3.96/M output tokens. Despite the low price, it scores competitively on Coding Index (68.8) and Intelligence Index (53.2) — making it a candidate for high-volume production workloads where unit cost dominates.

Latency. On latency, DeepSeek V4 Pro 0813 (Reasoning, Max Effort) reports 60 tok/s output speed and 1900ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.

Cost model. For a workload of 1M input tokens + 100K output tokens, DeepSeek V4 Pro 0813 (Reasoning, Max Effort) costs $1.72 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 2026-09-06.

Compare with similar models

ModelInputOutputSpeed
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)Current
$1.32$3.9660 tok/s
Kimi K2.6
$0.95$4.0040 tok/s
Kimi K2.6 (Non-reasoning)
$0.95$4.0042 tok/s
Kimi K2.7 Code
$0.95$4.0039 tok/s
Qwen3 VL 235B A22B (Reasoning)
$0.40$4.0054 tok/s
Inkling (xhigh)
$1.00$4.0573 tok/s

Example Costs

Single Request
$0.0033
1.0K in / 500 out
1K Requests/day
$3.30
1.0M in / 500.0K out
10K Requests/day
$33.00
10.0M in / 5.0M out