Price Per TokenPrice Per Token
Deepseek
Deepseek
vs
Nousresearch
Nousresearch

DeepSeek V3.1 vs Hermes 4 70B

A detailed comparison of pricing, benchmarks, and capabilities

OpenClaw

Best LLMs for OpenClaw Vote for which model works best with OpenClaw

100 out of our 304 tracked models have had a price change in February.

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

DeepSeek V3.1 wins:

  • Higher intelligence benchmark
  • Better at coding
  • Better at math

Hermes 4 70B wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Larger context window
  • Faster response time
Price Advantage
Hermes 4 70B
Benchmark Advantage
DeepSeek V3.1
Context Window
Hermes 4 70B
Speed
Hermes 4 70B

Pricing Comparison

Price Comparison

MetricDeepSeek V3.1Hermes 4 70BWinner
Input (per 1M tokens)$0.15$0.11 Hermes 4 70B
Output (per 1M tokens)$0.75$0.38 Hermes 4 70B
Using a 3:1 input/output ratio, Hermes 4 70B is 41% cheaper overall.

DeepSeek V3.1 Providers

SambaNova $0.15 (Cheapest)
Chutes $0.20
DeepInfra $0.21
SiliconFlow $0.27
Novita $0.27

Hermes 4 70B Providers

Chutes $0.11 (Cheapest)
Nebius $0.13

Benchmark Comparison

6
Benchmarks Compared
6
DeepSeek V3.1 Wins
0
Hermes 4 70B Wins

Benchmark Scores

BenchmarkDeepSeek V3.1Hermes 4 70BWinner
Intelligence Index
Overall intelligence score
28.013.6
Coding Index
Code generation & understanding
28.49.2
Math Index
Mathematical reasoning
49.711.3
MMLU Pro
Academic knowledge
83.366.4
GPQA
Graduate-level science
73.549.1
LiveCodeBench
Competitive programming
57.726.9
DeepSeek V3.1 significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
DeepSeek V3.1
Other models

Context & Performance

Context Window

DeepSeek V3.1
32,768
tokens
Max output: 7,168 tokens
Hermes 4 70B
131,072
tokens
Max output: 131,072 tokens
Hermes 4 70B has a 75% larger context window.

Speed Performance

MetricDeepSeek V3.1Hermes 4 70BWinner
Tokens/second0.0 tok/s73.3 tok/s
Time to First Token0.00s0.62s
Hermes 4 70B responds Infinity% faster on average.

Capabilities

Feature Comparison

FeatureDeepSeek V3.1Hermes 4 70B
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyDeepSeek V3.1Hermes 4 70B
LicenseOpen SourceOpen Source
AuthorDeepseekNousresearch
ReleasedAug 2025Aug 2025

DeepSeek V3.1 Modalities

Input
text
Output
text

Hermes 4 70B Modalities

Input
text
Output
text

Related Comparisons

Compare DeepSeek V3.1 with:

Compare Hermes 4 70B with:

Frequently Asked Questions

Hermes 4 70B has cheaper input pricing at $0.11/M tokens. Hermes 4 70B has cheaper output pricing at $0.38/M tokens.
DeepSeek V3.1 scores higher on coding benchmarks with a score of 28.4, compared to Hermes 4 70B's score of 9.2.
DeepSeek V3.1 has a 32,768 token context window, while Hermes 4 70B has a 131,072 token context window.
DeepSeek V3.1 does not support vision. Hermes 4 70B does not support vision.