Back to Discovery
Pixtral 12B
byunitalk
The Pixtral model demonstrates strong capabilities in tasks such as chart and image understanding, document question answering, multimodal reasoning, and instruction following. It can ingest images at natural resolutions and aspect ratios and handle an arbitrary number of images within a long context window of up to 128K tokens.
Providers Supporting This Model
Unitalkpixtral-12b-2409
Maximum Context Length
--
Maximum Output Length
--
Input Price
$0.15
Output Price
$0.15
Mistral
pixtral-12b-2409
Maximum Context Length
128K
Maximum Output Length
--
Input Price
$0.15
Output Price
$0.15
Higress
pixtral-12b-2409
Maximum Context Length
128K
Maximum Output Length
--
Input Price
$0.15
Output Price
$0.15
Related Recommendations
unitalk
Claude 3.7 Sonnet
0.description
200K
unitalk
Grok 3 Thinking
Grok 3 Mini Beta model, supports reasoning trace via reasoning_content field.
128K
unitalk
Grok 3
Grok 3 is xAI’s latest advanced reasoning model, featuring enhanced multimodal capabilities, real-time web access, and specialized modes for step-by-step thinking and complex task solving. It is designed for high-performance applications and large-scale deployment across diverse domains.
128K
unitalk
OpenAI o4 Mini
o4-mini is OpenAI’s new reasoning model that supports image and text inputs and generates text outputs. It is suitable for complex tasks requiring broad general knowledge. The model has a 200K token context window and a knowledge cutoff of May 31, 2024.
200K
unitalk
OpenAI o3
o3 is OpenAI’s new reasoning model that supports image and text inputs and generates text outputs. It is suitable for complex tasks requiring broad general knowledge. The model has a 200K token context window and a knowledge cutoff of May 31, 2024.
200K
unitalk
GPT-4.1 mini
gpt-4.1-mini.description
1M
unitalk
GPT-4.1 nano
gpt-4.1-nano.description
1M
unitalk
GPT-4.1
gpt-4.1.description
1M