codestral-latest
Input $0.01 USD · Output $0.01 USD / 1M tokens
chat comparison
codestral-latestvsgpt-5.3-codex-spark
Compare the things that matter before you build: current price, capabilities, and observed LLM7 usage.
Current pricing
See the cost difference clearly
gpt-5.3-codex-spark
Input $0.36 USD · Output $2.81 USD / 1M tokens
What's different
Only capabilities that differ between these models are listed. Green highlights the broader supported option or larger context window.
Context window
codestral-latest
32,000 tokens
gpt-5.3-codex-sparkBetter fit
400,000 tokens
Reasoning
codestral-latest
Not supported
gpt-5.3-codex-sparkBetter fit
Supported
Observed usage comparison
A 30-day LLM7 snapshot, not a global model benchmark.
Requests handled
codestral-latest
1,748
gpt-5.3-codex-spark
52
Observed success rate
codestral-latest
99.6%
gpt-5.3-codex-spark
100%
Average API latency
codestral-latest
2,124.08 ms
gpt-5.3-codex-spark
1,363.69 ms
P95 API latency
codestral-latest
10,000 ms
gpt-5.3-codex-spark
5,000 ms
Estimate your workload
Try the same request volume against both public price lists.
Cost calculator
Adjust the volume to see an instant estimate at the current public price.
01M
Input estimate
$0.0001
Output estimate
$0.000025
Estimated total
$0.000125
Cost calculator
Adjust the volume to see an instant estimate at the current public price.
01M
Input estimate
$0.0036
Output estimate
$0.007025
Estimated total
$0.010625
Quick take
- gpt-5.3-codex-spark has a larger context window.
- gpt-5.3-codex-spark recorded a lower observed p95 API latency on LLM7 during this period.