This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
Mistral has launched a newer release, Mistral Small 3.2. We suggest considering it instead.
Mixtral 8x7B Instruct: Intelligence, Performance & Price Analysis
Available providers
Model summary
Verbosity
Mixtral 8x7B Instruct supports text input, outputs text, and has a 33k tokens context window.
Pricing for Mixtral 8x7B Instruct is $0.45 per 1M input tokens (moderately priced, median: $0.45) and $0.70 per 1M output tokens (moderately priced, median: $0.71).
| Reasoning | No |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Context window | 33k ~49 A4 pages of size 12 Arial font |
| Total parameters | 46.7B |
| Active parameters | 12.9B Number of parameters active per token during inference |
| License | Apache 2.0 |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Openness Index
Artificial Analysis Openness Index: Score
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Performance
Measured by time per task (minutes), output speed (tokens per second), time to first answer token and time to first token (seconds)
Time per Intelligence Index Task
Output Speed
Time to First Answer Token
Context Window
Context Window
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Further details
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Mixtral 8x7B Instruct | - | 46.7B 12.9B active at inference time | 33k | $0.47 | - | 55 |
Frequently Asked Questions
Common questions about Mixtral 8x7B Instruct
Mixtral 8x7B Instruct was released on December 11, 2023.
Mixtral 8x7B Instruct was created by Mistral.
Mixtral 8x7B Instruct has a time to first answer token of 0.76s (based on the median across providers serving the model), which is very competitive compared to other open weight non-reasoning models of similar size (median: 1.78s).
Mixtral 8x7B Instruct costs $0.45 per 1M input tokens (better than average, median: $0.45) and $0.70 per 1M output tokens (better than average, median: $0.71), based on the median across providers serving the model.
Mixtral 8x7B Instruct costs $0.45 per 1M input tokens and $0.70 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.47 per 1M tokens. Pricing may vary by provider. Compare provider pricing
No, Mixtral 8x7B Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Mixtral 8x7B Instruct supports text input.
Mixtral 8x7B Instruct supports text output.
No, Mixtral 8x7B Instruct does not support image input. It can only process text.
No, Mixtral 8x7B Instruct is not multimodal. It only supports text input.
Mixtral 8x7B Instruct has a context window of 33k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Mixtral 8x7B Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Mixtral 8x7B Instruct has 46.7B parameters (12.9B active).
Mixtral 8x7B Instruct is a Mixture of Experts (MoE) model with 46.7B total parameters, but only 12.9B active parameters are used during inference.
Mixtral 8x7B Instruct is released under the Apache 2.0 license. This license allows commercial use. View license
Yes, Mixtral 8x7B Instruct is available via API through 1 provider. Compare API providers
Mixtral 8x7B Instruct is available through 1 API provider. Compare providers