All models
Mistral AI
Mixtral 8x22B Instruct balancedruns locally
mistral/mixtral-8x22b
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
Input / 1M
$2.00
USD per million tokens
Output / 1M
$6.00
USD per million tokens
Est. cost / token
$0.000003
$3.00 per 1M, 3:1 mix
Context window
66K
max output 52K
Major features
Open weightsCachingJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding4
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat4
- creative4
- translation4
- vision1
- long context2
- agentic4
Run it locally
Will it run on my machine? →ollama run mixtral:8x22b| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 66.2 GB |
| Q3_K_M | fair | 76.5 GB |
| Q4_K_Mrecommended | good | 94.7 GB |
| Q5_K_M | very good | 109 GB |
| Q6_K | excellent | 126 GB |
| Q8_0 | near-lossless | 161 GB |
| F16 | lossless | 300 GB |
Estimates. Mixture-of-experts: memory covers all parameters; only the active ones are used per token, so it runs faster than its size suggests.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $2.00 | $6.00 | $0.20 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $2.00
- Output
- $6.00
- Cached input
- $0.20
- Blended (3:1)
- $3.00
Details
- Company
- Mistral AI
- Version
- —
- Family
- Mixtral
- Released
- 2024-04-17
- Parameters
- 141B (39B active)
- Max output
- 52K
- Open weights
- Yes
- Inputs
- file, text
- Last synced
- 31 min ago