Mistral Small 4 (Mistral AI) and Solar Pro 4 (Upstage) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.
Snapshot as of 9 September 2026
As of 9 September 2026, Solar Pro 4 holds the stronger ModelCap Index position (#93 vs #96); Solar Pro 4 is 5× cheaper per output token ($0.12/1M vs $0.60/1M); Solar Pro 4 offers the longer context window (524K vs 262K tokens); and Mistral Small 4 ships open weights.
Evidence: 1 public benchmark observation across 1 board · 3 public benchmark observations across 3 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.
Benchmark scores: Mistral Small 4 vs Solar Pro 4
Public benchmark boards where Mistral Small 4 or Solar Pro 4 has a published result
Solar Pro 4 ranks higher on the ModelCap Index as of 9 September 2026: #93 against #96. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
Is Mistral Small 4 cheaper than Solar Pro 4?
Solar Pro 4 is cheaper on output tokens: $0.12/1M against $0.60/1M. Input tokens are $0.15/1M for Mistral Small 4 and $0.03/1M for Solar Pro 4. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $0.60 for Mistral Small 4 versus $0.12 for Solar Pro 4. Solar Pro 4 costs 80.0% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.
Which has the bigger context window, Mistral Small 4 or Solar Pro 4?
Solar Pro 4 has the larger context window: 524K tokens against 262K.
Which is better for coding, Mistral Small 4 or Solar Pro 4?
AA Terminal-Bench 2.1: Mistral Small 4 21.0%, Solar Pro 4 57.3% — Solar Pro 4 leads.
Are Mistral Small 4 and Solar Pro 4 open-weight models?
Mistral Small 4: Open weights. Solar Pro 4: API only. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.
Where can I run Mistral Small 4 and Solar Pro 4?
ModelCap currently lists 2 API providers for Mistral Small 4 and 1 for Solar Pro 4, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.
How current is this Mistral Small 4 vs Solar Pro 4 comparison?
Every figure comes from the sealed ModelCap dataset published 9 September 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.