codestral-latest
Input $0.01 USD · Output $0.02 USD / 1M tokens
chat comparison
Compare the things that matter before you build: current price, capabilities, and latest aggregated LLM7 statistics.
Current pricing
codestral-latest
Input $0.01 USD · Output $0.02 USD / 1M tokens
L3-8B-Lunaris-v1-Turbo
Input $0.04 USD · Output $0.05 USD / 1M tokens
Only capabilities that differ between these models are listed. Green highlights the broader supported option or larger context window.
Context window
codestral-latestBetter fit
32,000 tokens
L3-8B-Lunaris-v1-Turbo
8,000 tokens
Tool calling
codestral-latestBetter fit
Supported
L3-8B-Lunaris-v1-Turbo
Not supported
JSON mode
codestral-latestBetter fit
Supported
L3-8B-Lunaris-v1-Turbo
Not supported
Recent aggregated percentages and response-time metrics from LLM7, not a global model benchmark or traffic disclosure.
Recent stability
codestral-latest
98.45%
L3-8B-Lunaris-v1-Turbo
100%
Average response time
codestral-latest
3,236.46 ms
L3-8B-Lunaris-v1-Turbo
1,168.67 ms
P95 API latency
codestral-latest
30,000 ms
L3-8B-Lunaris-v1-Turbo
2,000 ms
Shared charts make the observed differences easier to read. Metrics without enough history stay hidden.
Both models on the same scale
Both models on the same scale
Both models on the same scale
Fixed-price models can be estimated directly; dynamic models use recent references and are billed from actual provider usage.
Adjust the volume to see an instant estimate at the current public price.
Input estimate
$0.0001
Output estimate
$0.00005
Estimated total
$0.00015
Adjust the volume to see an instant estimate at the current public price.
Input estimate
$0.0004
Output estimate
$0.000125
Estimated total
$0.000525