codestral-latest
Checking current pricing…
Chat comparison
codestral-latestvsdeepseek-v4-pro
Compare the things that matter before you build: current price, capabilities, and latest aggregated LLM7 statistics.
Current pricing
See the cost difference clearly
deepseek-v4-pro
Checking current pricing…
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
deepseek-v4-proBetter fit
1,000,000 tokens
Capability scores
AI-estimated ratings on 30 criteria from head-to-head comparisons against 86 other text models in the LLM7 catalog, judged by TypeSafe Jev from public information (2026-10-20). Each score is the win rate against the field, relative to the strongest model for that criterion (100%). Not a benchmark.
Below 50%50–79%80–94%95%+
codestral-latest · leads in 6
28%
Weak
deepseek-v4-pro · leads in 23
46%
Weak
Knowledge & reasoning
General knowledge
codestral-latest9%deepseek-v4-proLeads48%Logical reasoning
codestral-latest10%deepseek-v4-proLeads26%Mathematics
codestral-latest25%deepseek-v4-proLeads63%Scientific and technical depth
codestral-latest15%deepseek-v4-proLeads57%Planning and task decomposition
codestral-latest11%deepseek-v4-proLeads26%
Coding & tools
Code generation
codestral-latestLeads85%deepseek-v4-pro60%Debugging and code review
codestral-latestLeads60%deepseek-v4-pro49%Agentic coding
codestral-latestLeads44%deepseek-v4-pro42%Tool and function calling
codestral-latest33%deepseek-v4-proLeads42%SQL and query writing
codestral-latestLeads60%deepseek-v4-pro58%
Writing & language
Creative writing
codestral-latest7%deepseek-v4-proLeads34%Professional writing
codestral-latest8%deepseek-v4-proLeads42%Conversational quality
codestral-latest7%deepseek-v4-proLeads34%Multilingual ability
codestral-latest32%deepseek-v4-proLeads59%Translation
codestral-latest11%deepseek-v4-proLeads48%Summarization
codestral-latest7%deepseek-v4-proLeads53%
Data & professional work
Data analysis
codestral-latest13%deepseek-v4-proLeads51%Professional domains
codestral-latest5%deepseek-v4-proLeads44%Information extraction
codestral-latest16%deepseek-v4-proLeads51%Classification and labeling
codestral-latest15%deepseek-v4-proLeads49%Long-context handling
codestral-latest15%deepseek-v4-proLeads75%
Reliability & control
Instruction following
codestral-latest21%deepseek-v4-proLeads40%Structured output
codestral-latest44%deepseek-v4-proLeads59%Factual accuracy
codestral-latest17%deepseek-v4-proLeads44%Safety and alignment
codestral-latest14%deepseek-v4-proLeads34%Steerability
codestral-latest14%deepseek-v4-proLeads36%Output consistency
codestral-latest52%deepseek-v4-proLeads59%
Speed, cost & vision
Response speed
codestral-latestLeads85%deepseek-v4-pro32%Cost efficiency
codestral-latestLeads82%deepseek-v4-pro30%Image understanding
codestral-latestNo image inputdeepseek-v4-proNo image input
Latest LLM7 statistics
Recent aggregated percentages and response-time metrics from LLM7, not a global model benchmark or traffic disclosure.
Recent stability
codestral-latest
98.36%
deepseek-v4-pro
99.37%
Average response time
codestral-latest
3,439.06 ms
deepseek-v4-pro
21,349.57 ms
P95 API latency
codestral-latest
10,000 ms
deepseek-v4-pro
60,000 ms
Side-by-side trends
Shared charts make the observed differences easier to read. Metrics without enough history stay hidden.
Request success rate
Both models on the same scale
codestral-latest: 99.3%deepseek-v4-pro: 100%
Average API latency
Both models on the same scale
codestral-latest: 4,108 msdeepseek-v4-pro: 21,275 ms
P95 API latency
Both models on the same scale
codestral-latest: 10,000 msdeepseek-v4-pro: 60,000 ms
Estimate your workload
Published rates are loaded from the pricing API; per-request quotes are billed from actual provider usage.
Checking current pricing…
Checking current pricing…
Quick take
- deepseek-v4-pro has a larger context window.
- deepseek-v4-pro recorded higher recent LLM7 stability during this period.
- codestral-latest recorded a lower observed p95 API latency on LLM7 during this period.