DeepSeek-V4-Pro-0813 vs Inkling: Specs & Benchmark Comparison

DeepSeek-V4-Pro-0813 is developed by DeepSeek, while Inkling comes from Thinking Machines Lab. Inkling was released in July 2026, and DeepSeek-V4-Pro-0813 followed a month later in August 2026. DeepSeek-V4-Pro-0813 is the larger model at roughly 1.6 trillion parameters, against 975 billion for Inkling.

The two models share 3 published benchmarks. DeepSeek-V4-Pro-0813 leads on 3 of them. The widest gaps are on Terminal-Bench 2.1, where DeepSeek-V4-Pro-0813 scores 88.0% against 63.8%; Humanity's Last Exam (with tools, text-only), where DeepSeek-V4-Pro-0813 scores 60.0% against 46.0%. Averaged across everything we track, DeepSeek-V4-Pro-0813 sits at 60.6% and Inkling at 61.8%.

Inkling is the cheaper API at $0.95 per million input tokens and $4.05 per million output tokens, about 39% below DeepSeek-V4-Pro-0813 at $1.32 and $3.96. DeepSeek-V4-Pro-0813 takes the larger context window at 1M tokens, compared with 524K for Inkling. DeepSeek-V4-Pro-0813 accepts text as input, while Inkling accepts text, images, and audio. On tooling, only DeepSeek-V4-Pro-0813 supports function calling and only DeepSeek-V4-Pro-0813 offers structured output.

CharacteristicDeepSeek-V4-Pro-0813Inkling
CompanyDeepSeekThinking Machines Lab
Release DateAugust 13, 2026July 21, 2026
Parameters1.6T975B
MultimodalNoYes
Context (input)1.0M524K
Context (output)393K524K
Input Price / 1M$1.32$0.95
Output Price / 1M$3.96$4.05
Average Score60.6%61.8%
Benchmarks
Terminal-Bench 2.188.0%63.8%
Humanity's Last Exam (with tools, text-only)60.0%46.0%
Humanity's Last Exam (no tools, text-only)42.7%29.7%

Visual Benchmark Comparison

DeepSeek-V4-Pro-0813
Inkling
Terminal-Bench 2.10.9 vs 0.6
0.9
0.6
Humanity's Last Exam (with tools, text-only)0.6 vs 0.5
0.6
0.5
Humanity's Last Exam (no tools, text-only)0.4 vs 0.3
0.4
0.3

Verdict

DeepSeek-V4-Pro-0813 leads in 2 out of 4 comparison categories.

Overall Performance

Both models show comparable average scores: DeepSeek-V4-Pro-0813 — 0.6, Inkling — 0.6.

API Cost

Inkling is 1.1x cheaper: input $0.95/1M vs $1.32/1M tokens.

Context Window

DeepSeek-V4-Pro-0813 supports a larger context: 1M vs 524K tokens.

Recency

DeepSeek-V4-Pro-0813 is newer: released 8/13/2026 vs 7/21/2026.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — DeepSeek-V4-Pro-0813 or Inkling?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — DeepSeek-V4-Pro-0813 or Inkling?
Inkling is cheaper for input: $0.95 per 1M tokens vs $1.32.
Which has a larger context window — DeepSeek-V4-Pro-0813 or Inkling?
DeepSeek-V4-Pro-0813 supports a larger context: 1,048,576 tokens vs 524,288.

The DeepSeek-V4-Pro-0813 and Inkling comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the DeepSeek-V4-Pro-0813 or Inkling page. See also the complete list of AI model comparisons.