Mistral Small 3
- Input / output
- $0.04 / $0.064
- Providers
- 1
- Spread
- 1.25×
- 7 days
- −20.0%
- 30 days
- −20.0%
- Context
- 32K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
| fp8 | $0.04 | $0.064 | $0.046 | ref | |||
| fp8 | $0.05 | $0.08 | $0.0575 | +25% |
- DeepInfraCheapestfp8/flex$0.046$0.04 in · $0.064 outref vs ref32K ctxfp8
- $0.0575$0.05 in · $0.08 out+25% vs ref32K ctx100% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.046 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
No provider has changed its price since tracking began on Oct 3, 2026.
Changes
- ListedNow served,Listed
About
The cheapest provider for Mistral Small 3 is DeepInfra at $0.046 per 1M tokens (blended), charging $0.04 per 1M input and $0.064 per 1M output tokens. It is served by a single provider. Its best price fell 20.0% over the last 30 days. Context window: 32K tokens. Prices tracked since Oct 3, 2026.
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...
- Released
- Jan 30, 2025
- First tracked
- Oct 3, 2026
- Canonical slug
- mistralai/mistral-small-24b-instruct-2501
- Weights
- mistralai/Mistral-Small-24B-Instruct-2501