Skip to content

Compare models

Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.

  1. Nemotron 3.5 Super VLNVIDIARemove
  2. Codestral 2508Mistral AIRemove
nemotron-3.5-super-vl vs codestral-2508
AttributeNemotron 3.5 Super VLnemotron-3.5-super-vlCodestral 2508codestral-2508
Pricing
Input$0.10 / 1M$0.45 / 1M
Output$0.40 / 1M$1.35 / 1M
Cache Write (5m)$0.10 / 1M$0.45 / 1M
Cache Write (1h)$0.10 / 1M$0.45 / 1M
Cache Read$0.10 / 1M$0.45 / 1M
Web Search$0 / 1M$0 / 1M
Context
Max context1M256K
Max outputN/AN/A
Capabilities
VisionYesNo
Function CallingYesYes
JSON ModeYesYes
StreamingYesYes
Catalogue
ProviderNVIDIAMistral AI
Categorychatchat
Charge typePay As You GoPay As You Go
Released——
Description
SummaryNVIDIA Nemotron 3.5 Super VL is an open multimodal Mixture-of-Experts (MoE) model featuring 120B total parameters with 12B activated per token. Built on a hybrid Mamba–Transformer architecture with multi-token prediction, it supports text, images, documents, GUI screenshots, and video inputs, along with a 1M-token context window for complex, long-horizon workflows. Optimized for multimodal reasoning, visual understanding, and agentic tool use, the model supports configurable reasoning modes and token budgets. It is well suited for document intelligence, web research, coding validation, customer service, GUI analysis, and video understanding, enabling efficient, long-running multimodal agent applications.Codestral is Mistral's cutting-edge language model for coding, released in late July 2025. It is purpose-built for low-latency, high-frequency developer workflows, excelling at tasks such as fill-in-the-middle (FIM) code completion, code correction, and test generation. Optimized for responsiveness and precision, Codestral is well suited for real-time coding assistance, IDE integration, and automated development pipelines where speed and accuracy are critical.