All models
Mistral AI
Mistral Small 3 fastruns locally
mistral/mistral-small-24b-instruct-2501
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...
Input / 1M
$0.050
USD per million tokens
Output / 1M
$0.080
USD per million tokens
Est. cost / token
$0.000000057
$0.058 per 1M, 3:1 mix
Context window
33K
max output 16K
Major features
Open weightsJSON schema
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context2
- agentic1
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 12.7 GB |
| Q3_K_M | fair | 14.4 GB |
| Q4_K_Mrecommended | good | 17.4 GB |
| Q5_K_M | very good | 19.9 GB |
| Q6_K | excellent | 22.6 GB |
| Q8_0 | near-lossless | 28.6 GB |
| F16 | lossless | 51.9 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.050 | $0.080 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.050
- Output
- $0.080
- Blended (3:1)
- $0.058
Details
- Company
- Mistral AI
- Version
- —
- Family
- Mistral
- Released
- 2025-01-30
- Parameters
- 23.6B
- Max output
- 16K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 31 min ago