Mistral has launched a newer model, Mistral Medium 3.1, we suggest considering this model instead.
For more information, see Comparison of Mistral Medium 3.1 to other models and API provider benchmarks for Mistral Medium 3.1.
Pixtral Large Intelligence, Performance & Price Analysis
Model summary
Intelligence
Artificial Analysis Intelligence Index
Speed
Output tokens per second
Input Price
USD per 1M tokens
Output Price
USD per 1M tokens
Verbosity
Output tokens from Intelligence Index
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
| Reasoning | No This page shows the non-reasoning version of this model. A reasoning variant may also exist. |
|---|---|
| Input modality | Supports: image This information is still being updated |
| Output modality | This information is still being updated |
| Context window | 128k ~192 A4 pages of size 12 Arial font |
| Total parameters | 124B |
| License | Mistral Research License |
| Model weights | Hugging Face |
Pixtral Large is above average in intelligence, but particularly expensive when comparing to other open weight non-reasoning models of similar size. It's also slower than average, however fairly concise. The model supports image input, and has a 128k tokens context window.
Pixtral Large scores 14 on the Artificial Analysis Intelligence Index, placing it above average among comparable models (averaging 13). When evaluating the Intelligence Index, it generated 1.8M tokens, which is fairly concise in comparison to the average of 3.8M.
Pricing for Pixtral Large is $2.00 per 1M input tokens (expensive, average: $0.20) and $6.00 per 1M output tokens (expensive, average: $0.57). In total, it cost $71.65 to evaluate Pixtral Large on the Intelligence Index.
At 49 tokens per second, Pixtral Large is slower than average (60).
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Evaluations
Openness
Artificial Analysis Openness Index: Results
Intelligence Index Comparisons
Intelligence vs. Price
Intelligence Index Token Use & Cost
Output Tokens Used to Run Artificial Analysis Intelligence Index
Cost to Run Artificial Analysis Intelligence Index
Context Window
Context Window
Pricing
Pricing: Input and Output Prices
Intelligence vs. Price (Log Scale)
Pricing Comparison of Pixtral Large API Providers
Speed
Measured by Output Speed (tokens per second)
Output Speed
Output Speed vs. Price
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 Tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Frequently Asked Questions
Common questions about Pixtral Large
Pixtral Large was released on November 18, 2024.
Pixtral Large was created by Mistral.
Pixtral Large scores 14 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 13).
Pixtral Large generates output at 48.6 tokens per second (based on Mistral's API), which is below average compared to other open weight non-reasoning models of similar size (median: 59.9 t/s).
Pixtral Large has a time to first token (TTFT) of 1.44s (based on Mistral's API), which is better than average compared to other open weight non-reasoning models of similar size (median: 1.66s).
Pixtral Large costs $2.00 per 1M input tokens (at the higher end, median: $0.52) and $6.00 per 1M output tokens (at the higher end, median: $0.81), 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 (3:1 input to output ratio), this is $3.00 per 1M tokens. Pricing may vary by provider. Compare provider pricing
When evaluated on the Intelligence Index, Pixtral Large generated 1.8M output tokens, which is better than average compared to other open weight non-reasoning models of similar size (median: 3.8M).
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. View license
Pixtral Large achieves a score of 14 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. Compare API providers
Pixtral Large is available through 1 API provider. Compare providers