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.
| Attribute | Nemotron 3.5 Lightning (Free)nemotron-3.5-lightning:free | GPT-6.1 Terragpt-6.1-terra | DeepSeek V4.1 Flash 1017deepseek-v4.1-flash-1017 |
|---|---|---|---|
| Pricing | |||
| Input | $0 / 1M | $1.00 / 1M | $0.20 / 1M |
| Output | $0 / 1M | $5.00 / 1M | $0.80 / 1M |
| Cache Write | $0 / 1M | — | — |
| Cache Read | $0 / 1M | $1.00 / 1M | $0.20 / 1M |
| Cache Write (5m) | — | $1.00 / 1M | $0.20 / 1M |
| Cache Write (1h) | — | $1.00 / 1M | $0.20 / 1M |
| Web Search | — | $0 / 1M | $0 / 1M |
| Context | |||
| Max context | 1M | 1M | 1M |
| Max output | N/A | N/A | N/A |
| Capabilities | |||
| Vision | Yes | Yes | Yes |
| Function Calling | Yes | Yes | Yes |
| JSON Mode | Yes | Yes | Yes |
| Streaming | Yes | No | Yes |
| Catalogue | |||
| Provider | NVIDIA | OpenAI | DeepSeek |
| Category | chat | chat | chat |
| Charge type | Free | Pay As You Go | Pay As You Go |
| Released | — | — | — |
| Description | |||
| Summary | NVIDIA Nemotron 3.5 Lightning is an open Mixture-of-Experts (MoE) model with 30B total parameters and 3B active per token, optimized for high-throughput agentic workloads and efficient inference. Its lightweight active compute and open design make it well suited for specialized agents, domain-specific customization, and scalable production deployments where speed, cost efficiency, and adaptability are key. | GPT-6.1 Terra is OpenAI’s mid-tier model in the GPT-6.1 series, designed to balance capability, speed, and cost efficiency. Positioned below GPT-6.1 Sol, it delivers strong performance across everyday agentic workflows, coding, and professional writing, with particular strengths in screenshot understanding and on-screen content analysis. Optimized for high-volume production workloads, GPT-6.1 Terra is well suited for coding assistants, visual interface analysis, workflow automation, and scalable agentic applications that require reliable performance at an accessible cost. | DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek’s cost-efficient Mixture-of-Experts (MoE) model, built on its innovative Causal Encoder-Decoder (CED) architecture. Featuring 552B total parameters with 8B activated for input and 16B for output, it combines efficient inference with native multimodal understanding through jointly trained text and visual representations. Optimized for coding, terminal and computer-use agents, and long-horizon workflows, the model introduces compressed KV caching that reduces cache memory usage to approximately one-quarter of the previous Flash generation. DeepSeek reports that it surpasses V4 Pro in performance, inference speed, and task completion time, making it well suited for cost-efficient autonomous agents, complex software engineering, and long-context analysis. |