Mistral Small 3.2 24B pricing across providers
Across tracked provider offerings, input runs $0.075–$0.100 per million tokens and output $0.200–$0.300 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Mistral at $0.014 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 2 of 4 offerings publish a cache-read rate; 4 of 4 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to Mistral Small 3.2 24B
Is this the right model for your workload? Compare open-weight picks and providers for your use case →
Daily price history
Loading price history…
Daily snapshots are retained for up to 90 days; history begins with the first recorded snapshot.
Provider offerings for Mistral Small 3.2 24B
Ranked by effective cost at a typical agentic mix. Quantized and tier variants stay separate rows.
| Provider | Quant | Input $/M | Output $/M | Cache $/M | Blended $/M | Uptime (30m) |
|---|---|---|---|---|---|---|
| Mistral | unknown | $0.100 | $0.300 | $0.010 | $0.014 | 100.00% |
| Parasail | bf16 | $0.090 | $0.300 | $0.050 | $0.052 | 100.00% |
| DeepInfra | fp8 | $0.075 | $0.200 | — | $0.076 | 100.00% |
| Venice | fp8 | $0.094 | $0.250 | — | $0.095 | 100.00% |
Provider-offering pricing refreshed 2026-10-29. Uptime is the 30-minute endpoint metric where a provider publishes it. Verify rates on the provider's official pricing page before committing spend.