Balanced multimodal model pairing a 1M-token context window with deeper reasoning for analysis, content creation, and tool use across text, image, audio, video, and PDF inputs.
1 provider
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Fast, low-cost multimodal model for understanding text, images, audio, video, and PDFs, with tool calling and a 1M-token context window.
1 provider
Qwen instruction model for multilingual chat, reasoning, and tool use
11 providers
Web-grounded Sonar for multi-step research questions that need cited reasoning
9 providers
Open sparse mixture-of-experts Mistral instruction model
1 provider
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Vision Mediumvispark/vision-medium | 1M | $4.21 | $12.63 | 2024-05-15 | |||
| Vision Smallvispark/vision-small | 1M | $1.05 | $3.16 | 2024-05-15 | |||
| Qwen Plusalibaba/qwen-plus | Alibaba Qwen |
1M | $0.4 | $1.2 | 2024-01-25 | ||
| Sonar Reasoning Properplexity/sonar-reasoning-pro | Perplexity |
128K | $2 | $8 | 2024-01-01 | ||
| Mixtral 8x7B Instruct v0.1mistral/mixtral-8x7b-instruct-v0.1 | Mistral AI |
32.768K | $0.488 | $0.758 | 2023-12-11 |