Mixtral 8x22B Instruct
Mixtral 8x22B Instruct is Mistral AI's language model with a 66K context window and up to 52K output tokens, available from 5 providers, starting at $0.6 / 1M input and $0.6 / 1M output. The instruction-tuned version of Mistral AI's Mixtral 8x22B MoE model, optimized for following complex instructions and multi-turn dialogue.
| Specifications | |
|---|---|
mistral-mixtral-8x22b-instruct | |
| Language | |
| Active | |
| Mistral AI | |
| 66K tokens | |
| 52K tokens | |
| PDFText | |
| Text | |
| 22B | |
| 748 | |
| 28,279 | |
| 6,052,030 | |
| · 2 years ago | |
| · 3 years ago | |
| Benchmarks | |
|---|---|
| Intelligence Index | #494 |
| MMLU-Pro | #284 |
| GPQA | #477 |
| HLE | #486 |
| LiveCodeBench | #284 |
| AIME | #183 |
| Time to First Token | #232 |
| SciCode | #445 |
| MATH-500 | #160 |
| Output TPS | #471 |
Capabilities
Input2/5
Text✓
Image·
Audio·
Video·
PDF✓
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
| $0.9 | $0.9 | N/A | |
| $1.20 | $1.20 | N/A | |
| $0.6 | $0.6 | N/A | |
| $2.00 | $6.00 | $0.2 | |
| $1.20 | $1.20 | N/A | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Mixtral 8x22B Instruct, ranked by cheapest on-demand price. The model needs about 53 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_NP10s |  Azure | AMD Alveo U250 FPGA (64GB) | 64 GB | $1.65/hr | ||
| Standard_NV32as_v4 | Azure | AMD Radeon Instinct MI25 | 64 GB | $1.86/hr | ||
| Standard_NP20s | Azure | 2× AMD Alveo U250 FPGA (64GB) | 128 GB | $3.30/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Dolphin 2.5 Mixtral 8x7B | — | — | — | — | Available |
| Dolphin 2.6 Mixtral 8x7B | — | 33K | $0.500 | $0.500 | Available |
| Dolphin 2.7 Mixtral 8x7B | — | — | — | — | Available |
| MiniMax M2 | 1.0M | $0.255 | $1.02 | Deprecating | |
| Mixtral 8x22B Instruct | 66K | $0.600 | $0.600 | Current | |
| Mixtral 8x7B Instruct | 33K | $0.070 | $0.150 | Deprecated | |
| Hermes 2 Mixtral 8x7B DPO | — | 33K | $0.500 | $0.500 | Deprecated |
| KARAKURI LM 8x7B Instruct | — | — | — | — | Available |
| Mixtral | — | — | — | — | Available |
| Mixtral 8x22B | — | 66K | $1.20 | $1.20 | Deprecated |
| Mixtral 8x7B | — | 33K | $0.500 | $0.500 | Deprecated |