Price Per TokenPrice Per Token
OpenAI
OpenAI
vs
Inception
Inception

GPT-5.3 Codex vs Mercury 2

A detailed comparison of pricing, benchmarks, and capabilities

OpenClaw

Deploy OpenClaw in Under 1 Minute We handle hosting, scaling, and maintenance

107 out of our 480 tracked models have had a price change in March.

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

Key Takeaways

GPT-5.3 Codex wins:

  • Larger context window
  • Higher intelligence benchmark
  • Better at coding
  • Supports vision

Mercury 2 wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Faster response time
Price Advantage
Mercury 2
Benchmark Advantage
GPT-5.3 Codex
Context Window
GPT-5.3 Codex
Speed
Mercury 2

Pricing Comparison

Price Comparison

MetricGPT-5.3 CodexMercury 2Winner
Input (per 1M tokens)$1.75$0.25 Mercury 2
Output (per 1M tokens)$14.00$0.75 Mercury 2
Cache Read (per 1M)$0.17$0.03 Mercury 2
Using a 3:1 input/output ratio, Mercury 2 is 92% cheaper overall.

GPT-5.3 Codex Providers

No provider data available

Mercury 2 Providers

No provider data available

Benchmark Comparison

3
Benchmarks Compared
3
GPT-5.3 Codex Wins
0
Mercury 2 Wins

Benchmark Scores

BenchmarkGPT-5.3 CodexMercury 2Winner
Intelligence Index
Overall intelligence score
54.032.8
Coding Index
Code generation & understanding
53.130.6
GPQA
Graduate-level science
91.577.0
GPT-5.3 Codex significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Other models

Context & Performance

Context Window

GPT-5.3 Codex
400,000
tokens
Mercury 2
128,000
tokens
GPT-5.3 Codex has a 68% larger context window.

Speed Performance

MetricGPT-5.3 CodexMercury 2Winner
Tokens/second68.3 tok/s794.9 tok/s
Time to First Token81.66s3.59s
Mercury 2 responds 1064% faster on average.

Capabilities

Feature Comparison

FeatureGPT-5.3 CodexMercury 2
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyGPT-5.3 CodexMercury 2
LicenseProprietaryProprietary
AuthorOpenAIInception
ReleasedFeb 2026Mar 2026

GPT-5.3 Codex Modalities

Input
textimage
Output
text

Mercury 2 Modalities

Input
text
Output
text

Related Comparisons

Compare GPT-5.3 Codex with:

Compare Mercury 2 with:

Frequently Asked Questions

Mercury 2 has cheaper input pricing at $0.25/M tokens. Mercury 2 has cheaper output pricing at $0.75/M tokens.
GPT-5.3 Codex scores higher on coding benchmarks with a score of 53.1, compared to Mercury 2's score of 30.6.
GPT-5.3 Codex has a 400,000 token context window, while Mercury 2 has a 128,000 token context window.
GPT-5.3 Codex supports vision. Mercury 2 does not support vision.
Advertise with us