Model Library
MistralReleased November 18, 2024Pixtral Large
Mistral · Released November 18, 2024
Intelligence score
8
At a glance
- Intelligence
- 8
- Speed
- 52.0tokens/sec
- Latency
- 1.23stime to first token
- Input price
- $2.00per 1M tokens
- Output price
- $6.00per 1M tokens
- Context window
- 130Ktokens
- Parameters
- 124billions
Summary
Comparison summary
Pixtral Large scores 8 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 7). Pixtral Large generates output at 52.0 tokens per second (based on Mistral's API), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 81.5 t/s). Pixtral Large costs $2.00 per 1M input tokens (at the higher end, median: $0.53) and $6.00 per 1M output tokens (at the higher end, median: $1.05), based on Mistral's API.
Specifications
Technical specifications
| Model name | Pixtral Large |
|---|---|
| Provider | Mistral |
| Release date | November 18, 2024 |
| Intelligence score | 8 |
| Speed | 52.0 tokens/sec |
| Latency (TTFT) | 1.23s |
| Input price | $2.00 / 1M tokens |
| Output price | $6.00 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | 124B |
| Reasoning | No |
| Input modalities | image |
| Output modalities | — |
| Open weights | Yes |
| License | Mistral Research License |
| API availability | — |
| Source | Model Intelligence legacy profile: pixtral-large-2411 |
Pricing
Token prices
Price per 1M tokens
Pixtral Large, as listed in the catalog record
- Input$2.00
- Output$6.00
| Token type | Price per 1M |
|---|---|
| Input | $2.00 |
| Output | $6.00 |
Model Intelligence legacy profile: pixtral-large-2411
FAQ · 19
Frequently asked questions
Pixtral Large was released on November 18, 2024.
Pixtral Large was created by Mistral.
Pixtral Large scores 8 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 7).
Pixtral Large generates output at 52.0 tokens per second (based on Mistral's API), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 81.5 t/s).
Pixtral Large has a time to first token (TTFT) of 1.23s (based on Mistral's API), which is very competitive compared to other open weight non-reasoning models of similar size (median: 1.59s).
Pixtral Large costs $2.00 per 1M input tokens (at the higher end, median: $0.53) and $6.00 per 1M output tokens (at the higher end, median: $1.05), based on Mistral's API.
Pixtral Large costs $2.00 per 1M input tokens and $6.00 per 1M output tokens (based on Mistral's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $2.40 per 1M tokens. Pricing may vary by provider.
No, Pixtral Large is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Pixtral Large supports image input.
Pixtral Large supports text only output.
Yes, Pixtral Large supports image input and can analyze, describe, and answer questions about images.
No, Pixtral Large is not multimodal. It only supports image input.
Pixtral Large has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Pixtral Large is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Pixtral Large has 124 billion parameters.
Pixtral Large is released under the Mistral Research License license. Commercial use requires a separate license agreement.
Pixtral Large achieves a score of 8 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Pixtral Large is available via API through 1 provider.
Pixtral Large is available through 1 API provider.