The AI arena is free today

Open Superagent

DeepSeek-V4-Pro-Max vs Inkling-Small

DeepSeek-V4-Pro-Max leads the LLM Stats Score 43.1 to 38.5. Inkling-Small is 3.1x cheaper per token.

DeepSeek · Thinking Machines Lab · Updated for 2026

Which is better?

DeepSeek-V4-Pro-Max leads the overall LLM Stats Score 43.1 to 38.5, ranking #43 overall.

In the 7 individual benchmarks reported for both models, DeepSeek-V4-Pro-Max wins 4; this is a narrower head-to-head signal than the composite indexes.

On price, Inkling-Small is roughly 3.1x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

DeepSeek-V4-Pro-Max also accepts a larger context window (1,048,576 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose DeepSeek-V4-Pro-Max

  • overall performance matters — it scores 43.1 and ranks #43 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 4 of 7 exact shared results
  • you process long inputs — it offers a 1,048,576 token context window

Choose Inkling-Small

  • cost matters — it's about 3.1x cheaper per token
  • you want the most recent training data — it shipped Jul 2026

At a glance

The differences that matter most.

Core performance indexes
43.1
#43
38.5
#65
43.3
#41
38.1
#63
32.1
#39
29.3
#54
23.9
#55
23.6
#56
Cost, coverage & limits
Benchmark wins
4 of 7
3 of 7
Input price
$1.30 / M
$0.30 / M
Output price
$2.60 / M
$1.20 / M
Context window
1,048,576
256,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
DeepSeek-V4-Pro-Max
Inkling-Small
40.1#15
33.9#51
22.8#45
21.1#55
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

22 reported for DeepSeek-V4-Pro-Max · 24 for Inkling-Small

7 shared

DeepSeek-V4-Pro-Max outperforms in 4 benchmarks (BrowseComp, GPQA, Humanity's Last Exam, SWE-Bench Verified), while Inkling-Small is better at 3 benchmarks (MCP Atlas, SWE-Bench Pro, Toolathlon).

DeepSeek-V4-Pro-Max has a slight edge in benchmark performance.

Mon Sep 21 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Inkling-Small costs less

For input processing, DeepSeek-V4-Pro-Max ($1.30/1M tokens) is 4.3x more expensive than Inkling-Small ($0.30/1M tokens).

For output processing, DeepSeek-V4-Pro-Max ($2.60/1M tokens) is 2.2x more expensive than Inkling-Small ($1.20/1M tokens).

In conclusion, DeepSeek-V4-Pro-Max is more expensive than Inkling-Small.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Mon Sep 21 2026 • llm-stats.com
DeepSeek
DeepSeek-V4-Pro-Max
Input tokens$1.30
Output tokens$2.60
Best providerDeepinfra
Thinking Machines Lab
Inkling-Small
Input tokens$0.30
Output tokens$1.20
Best providerUnknown Organization
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

1324.0B diff

DeepSeek-V4-Pro-Max has 1324.0B more parameters than Inkling-Small, making it 479.7% larger.

DeepSeek
DeepSeek-V4-Pro-Max
1.6Tparameters
Thinking Machines Lab
Inkling-Small
276.0Bparameters
1600.0B
DeepSeek-V4-Pro-Max
276.0B
Inkling-Small

Context Window

Maximum input and output token capacity

DeepSeek-V4-Pro-Max accepts 1,048,576 input tokens compared to Inkling-Small's 256,000 tokens. DeepSeek-V4-Pro-Max can generate longer responses up to 1,048,576 tokens, while Inkling-Small is limited to 256,000 tokens.

DeepSeek
DeepSeek-V4-Pro-Max
Input1,048,576 tokens
Output1,048,576 tokens
Thinking Machines Lab
Inkling-Small
Input256,000 tokens
Output256,000 tokens
Mon Sep 21 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Inkling-Small supports multimodal inputs, whereas DeepSeek-V4-Pro-Max does not.

Inkling-Small can handle both text and other forms of data like images, making it suitable for multimodal applications.

DeepSeek-V4-Pro-Max

Text
Images
Audio
Video

Inkling-Small

Text
Images
Audio
Video

License

Usage and distribution terms

DeepSeek-V4-Pro-Max is licensed under MIT, while Inkling-Small uses Apache 2.0.

License differences may affect how you can use these models in commercial or open-source projects.

DeepSeek-V4-Pro-Max

MIT

Open weights

Inkling-Small

Apache 2.0

Open weights

Release Timeline

When each model was launched

DeepSeek-V4-Pro-Max was released on 2026-04-23, while Inkling-Small was released on 2026-07-30.

Inkling-Small is 3 months newer than DeepSeek-V4-Pro-Max.

DeepSeek-V4-Pro-Max

Apr 23, 2026

5 months ago

Inkling-Small

Jul 30, 2026

1 months ago

3mo newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

DeepSeek-V4-Pro-Max is available from DeepInfra, Novita, DeepSeek, Fireworks, Together. Inkling-Small is available from Thinking Machines Lab, DeepInfra.

DeepSeek-V4-Pro-Max

deepinfra logo
Deepinfra
Input Price:Input: $1.30/1MOutput Price:Output: $2.60/1M
novita logo
Novita
Input Price:Input: $1.60/1MOutput Price:Output: $3.20/1M
deepseek logo
DeepSeek
Input Price:Input: $1.74/1MOutput Price:Output: $3.48/1M
fireworks logo
Fireworks
Input Price:Input: $1.74/1MOutput Price:Output: $3.48/1M
together logo
Together
Input Price:Input: $1.74/1MOutput Price:Output: $3.48/1M

Inkling-Small

thinking-machines logo
Unknown Organization
Input Price:Input: $0.30/1MOutput Price:Output: $1.20/1M
deepinfra logo
Deepinfra
Input Price:Input: $0.45/1MOutput Price:Output: $1.20/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against DeepSeek-V4-Pro-Max and Inkling-Small side-by-side, then vote on the output you prefer.

DeepSeek-V4-Pro-Max
✓ Preferred
Inkling-Small
Open in Playground

FAQ

Common questions about DeepSeek-V4-Pro-Max vs Inkling-Small.

Which is better, DeepSeek-V4-Pro-Max or Inkling-Small?

DeepSeek-V4-Pro-Max leads the LLM Stats Score 43.1 to 38.5. DeepSeek-V4-Pro-Max is made by DeepSeek and Inkling-Small is made by Thinking Machines Lab. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does DeepSeek-V4-Pro-Max compare to Inkling-Small in benchmarks?

DeepSeek-V4-Pro-Max scores CodeForces: 100.0%, HMMT Feb 26: 95.2%, LiveCodeBench: 93.5%, MathArena Apex: 90.2%, GPQA: 90.1%. Inkling-Small scores AIME 2026: 95.5%, VoiceBench Avg: 90.1%, GPQA: 89.5%, Global-MMLU-Lite: 86.7%, ARC-AGI: 84.0%.

Is DeepSeek-V4-Pro-Max cheaper than Inkling-Small?

Inkling-Small is 4.3x cheaper for input tokens. DeepSeek-V4-Pro-Max costs $1.30/M input and $2.60/M output via deepinfra. Inkling-Small costs $0.30/M input and $1.20/M output via thinking-machines.

What are the context window sizes for DeepSeek-V4-Pro-Max and Inkling-Small?

DeepSeek-V4-Pro-Max supports 1.0M tokens and Inkling-Small supports 256K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between DeepSeek-V4-Pro-Max and Inkling-Small?

Key differences include LLM Stats Score (43.1 vs 38.5), context window (1.0M vs 256K), input pricing ($1.30 vs $0.30/M), multimodal support (no vs yes), licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V4-Pro-Max and Inkling-Small?

DeepSeek-V4-Pro-Max is developed by DeepSeek and Inkling-Small is developed by Thinking Machines Lab.