workhorse
Codestral Latest vs Deepseek V3.2
Side-by-side pricing, context window, features, and per-use-case verdict. Data sourced from LiteLLM, updated regularly.
Specifications
| Feature | Codestral Latest | Deepseek V3.2 |
|---|---|---|
| Provider | mistral | deepseek |
| Model ID | mistral/codestral-latest | deepseek/deepseek-v3.2 |
| Input / 1M tokens | $1.00 | $0.28 (72% cheaper) |
| Output / 1M tokens | $3.00 | $0.40 (87% cheaper) |
| Cached input / 1M | — | — |
| Context window | 32kk tokens | 164kk tokens |
| Max output | 8kk tokens | 164kk tokens |
| Vision | ⬜ | ⬜ |
| Function calling | ⬜ | ✅ |
| Prompt caching | ⬜ | ✅ |
| Web search | ⬜ | ⬜ |
| JSON schema | ✅ | ⬜ |
Monthly cost comparison
No cache discount applied — pure token costs at three usage scales.
| Scale | Codestral Latest | Deepseek V3.2 | Winner |
|---|---|---|---|
| Small 1M in / 0.2M out | $1.60 | $0.36 | Deepseek V3.2 saves 78% |
| Medium 10M in / 2M out | $16.00 | $3.60 | Deepseek V3.2 saves 78% |
| Large 100M in / 20M out | $160 | $36.00 | Deepseek V3.2 saves 78% |
Category winners
Cheapest input
Deepseek V3.2
$0.28/M
· 72% less than the other
Cheapest output
Deepseek V3.2
$0.40/M
· 87% less than the other
Larger context
Deepseek V3.2
164kk tokens · 412% larger window
More features
Deepseek V3.2
2 / 5 capabilities
Better for…
Short interactions & high-throughput APIs
$0.40/M output — 87% cheaper on output at scale
Deepseek V3.2
Long-document processing & large codebases
164k context window vs 32k — 412% larger context
Deepseek V3.2
Agentic workflows & tool use
Supports 2 of 5 tracked capabilities (vision, function calling, caching, web search, JSON schema)
Deepseek V3.2
Cost-sensitive production at scale
$36.00/month at 100M-token scale — 78% cheaper than the alternative
Deepseek V3.2
Deep-dive on each model
Pricing data sourced from LiteLLM and refreshed regularly. Always verify with each provider's official pricing page before making business decisions.