Model Library
MistralReleased December 11, 2023Mixtral 8x7B
Mistral · Released December 11, 2023
Intelligence score
2
At a glance
- Intelligence
- 2
- Speed
- —
- Latency
- —
- Input price
- $0.45per 1M tokens
- Output price
- $0.70per 1M tokens
- Context window
- 33Ktokens
- Parameters
- 46.7billions
Summary
Comparison summary
Mixtral 8x7B Instruct scores 2 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 7). Mixtral 8x7B Instruct costs $0.45 per 1M input tokens (better than average, median: $0.53) and $0.70 per 1M output tokens (better than average, median: $1.05), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Mixtral 8x7B |
|---|---|
| Provider | Mistral |
| Release date | December 11, 2023 |
| Intelligence score | 2 |
| Speed | — |
| Latency (TTFT) | — |
| Input price | $0.45 / 1M tokens |
| Output price | $0.70 / 1M tokens |
| Context window | 33,000 tokens |
| Parameters | 46.7B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: mixtral-8x7b-instruct |
Pricing
Token prices
Price per 1M tokens
Mixtral 8x7B, as listed in the catalog record
- Input$0.45
- Output$0.70
| Token type | Price per 1M |
|---|---|
| Input | $0.45 |
| Output | $0.70 |
Model Intelligence legacy profile: mixtral-8x7b-instruct
FAQ · 18
Frequently asked questions
Mixtral 8x7B Instruct was released on December 11, 2023.
Mixtral 8x7B Instruct was created by Mistral.
Mixtral 8x7B Instruct scores 2 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 7).
Mixtral 8x7B Instruct costs $0.45 per 1M input tokens (better than average, median: $0.53) and $0.70 per 1M output tokens (better than average, median: $1.05), 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.
No, Mixtral 8x7B Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Mixtral 8x7B Instruct supports text only input.
Mixtral 8x7B Instruct supports text only 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 only 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 46.7 billion parameters (12.9 billion active).
Mixtral 8x7B Instruct is a Mixture of Experts (MoE) model with 46.7 billion total parameters, but only 12.9 billion active parameters are used during inference.
Mixtral 8x7B Instruct is released under the Apache 2.0 license. This license allows commercial use.
Mixtral 8x7B Instruct achieves a score of 2 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Mixtral 8x7B Instruct is available via API through 1 provider.
Mixtral 8x7B Instruct is available through 1 API provider.