workhorse
Mistral Large 3 vs Mistral Small Latest
Side-by-side pricing, context window, features, and per-use-case verdict. Data sourced from LiteLLM, updated regularly.
Specifications
| Feature | Mistral Large 3 | Mistral Small Latest |
|---|---|---|
| Provider | mistral | mistral |
| Model ID | mistral/mistral-large-3 | mistral/mistral-small-latest |
| Input / 1M tokens | $0.50 | $0.06 (88% cheaper) |
| Output / 1M tokens | $1.50 | $0.18 (88% cheaper) |
| Cached input / 1M | — | — |
| Context window | 262kk tokens | 131kk tokens |
| Max output | 262kk tokens | 131kk 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 | Mistral Large 3 | Mistral Small Latest | Winner |
|---|---|---|---|
| Small 1M in / 0.2M out | $0.80 | $0.10 | Mistral Small Latest saves 88% |
| Medium 10M in / 2M out | $8.00 | $0.96 | Mistral Small Latest saves 88% |
| Large 100M in / 20M out | $80.00 | $9.60 | Mistral Small Latest saves 88% |
Category winners
Cheapest input
Mistral Small Latest
$0.06/M
· 88% less than the other
Cheapest output
Mistral Small Latest
$0.18/M
· 88% less than the other
Larger context
Mistral Large 3
262kk tokens · 100% larger window
More features
Mistral Large 3
3 / 5 capabilities
(tied)
Better for…
Short interactions & high-throughput APIs
$0.18/M output — 88% cheaper on output at scale
Mistral Small Latest
Long-document processing & large codebases
262k context window vs 131k — 100% larger context
Mistral Large 3
Cost-sensitive production at scale
$9.60/month at 100M-token scale — 88% cheaper than the alternative
Mistral Small Latest
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.