Mistral: Codestral 2508 (batch) vs ScaleDown: Summarize
On input price, ScaleDown: Summarize is ~3.8× cheaper. Verified 2026-10-21.
Mistral: Codestral 2508 (batch) $0.150/$0.450vsScaleDown: Summarize $0.040/Free
Verdict
On blended price (3:1 input:output), ScaleDown: Summarize is ~7.5× cheaper ($0.040/Free vs $0.150/$0.450 per 1M tokens).
Pricing
Per-million-token list prices, verified 2026-10-21. Green marks the better value.
| Metric | Mistral: Codestral 2508 (batch) | ScaleDown: Summarize |
|---|---|---|
| Input / 1M | $0.150 | $0.040 |
| Output / 1M | $0.450 | Free |
| Cache read / 1M | $0.015 | — |
| Blended (3:1) | $0.225/1M | $0.030/1M |
| Estimated monthly cost | Mistral: Codestral 2508 (batch) | ScaleDown: Summarize |
|---|---|---|
| Chatbot10,000 reqs · 800/400 tok | $3.00 | $0.32 |
| Coding agent5,000 reqs · 8000/2000 tok | $10.50 | $1.60 |
| RAG pipeline30,000 reqs · 4000/500 tok | $24.75 | $4.80 |
Plug in your own numbers in the calculator, or paste a real bill into the Bill Shredder.
Specifications & capabilities
| Metric | Mistral: Codestral 2508 (batch) | ScaleDown: Summarize |
|---|---|---|
| Context window | 256K | 1M |
| Max output | 205K | 4K |
| Vision input | – | ✓ |
| Tool calling | ✓ | – |
| Reasoning | – | – |
Provider
Infrastructure metrics for the organizations behind these models.
| Metric | Mistral AI | scaledown |
|---|---|---|
| Listed endpoints | 10 | — |
| Reliability | 99.5% | — |
| Avg latency | 400 ms | — |
| Pricing tiers | standard, free | — |
Full details: Mistral: Codestral 2508 (batch) pricing · ScaleDown: Summarize pricing