Mixtral 8x22B Instruct
Mistral · Open weights · Released Apr 17, 2024 · mistralai/mixtral-8x22b-instruct
Best $2.00 in / $6.00 out via Mistral
66K contextToolsStructured outputPrompt cachingOpen weights
Available from 2 providersUSD / MTOK · PRICES 16 MINUTES AGO · SPEED 16 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $2.00 | $6.00 | $0.20 | 66K | — | 0.7s | 177 tok/s | 100.0% | |
| $2.20 | $6.60 | $0.22 | 66K | — | — | — | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 16 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$2.00 / $6.00
per MTok in / out
CACHE READ $0.20
About
Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
Specifications
Context window65,536
Max output52,428
Modalities intext, file
Modalities outtext
LicenseOpen weights
ReleasedApr 17, 2024
Knowledge cutoff2024-01-31
TokenizerMistral
WeightsHugging Face ↗
Open weights
safetensors
Related
Embed badge
[](https://modelindex.ai/models/mistralai/mixtral-8x22b-instruct)Sources
OpenRouter API16 minutes ago
AGGREGATORHugging Face16 minutes ago
COMMUNITYModelIndex benchmarks16 days ago
MEASUREDVerified 16 minutes ago · list prices, not negotiated rates.