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.
- Nova-3DeepgramRemove
- GPT-6 Luna ProOpenAIRemove
- DeepSeek V4.1 FlashDeepSeekRemove
- Perceptron Mk1.5PerceptronRemove
4 is the maximum. Remove one to add another.
| Attribute | Nova-3nova-3 | GPT-6 Luna Progpt-6-luna-pro | DeepSeek V4.1 Flashdeepseek-v4.1-flash | Perceptron Mk1.5perceptron-mk1.5 |
|---|---|---|---|---|
| Pricing | ||||
| Input | $0 / 1M | $0.10 / 1M | $0.30 / 1M | $0.15 / 1M |
| Output | $0 / 1M | $0.50 / 1M | $1.20 / 1M | $1.50 / 1M |
| Cache Write (5m) | Not applicable | $0.10 / 1M | $0.30 / 1M | $0.15 / 1M |
| Cache Write (1h) | Not applicable | $0.10 / 1M | $0.30 / 1M | $0.15 / 1M |
| Cache Read | Not applicable | $0.10 / 1M | $0.30 / 1M | $0.15 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | ||||
| Max context | N/A | 1.1M | 1M | 36.9K |
| Max output | N/A | N/A | N/A | N/A |
| Capabilities | ||||
| Vision | No | Yes | Yes | No |
| Function Calling | No | Yes | Yes | No |
| JSON Mode | No | Yes | Yes | No |
| Streaming | No | Yes | Yes | Yes |
| Catalogue | ||||
| Provider | Deepgram | OpenAI | DeepSeek | Perceptron |
| Category | voice | chat | chat | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | 2026-07-15 | — | — | 2026-09-25 |
| Description | ||||
| Summary | Deepgram Nova-3 speech-to-text. Billed per second of audio. | GPT-6 Luna Pro uses the same underlying model as GPT-6 Luna, but runs with reasoning.mode set to pro for higher-quality responses on complex tasks. It combines Luna's speed and cost efficiency with deeper reasoning and more reliable multi-step execution, making it well suited for advanced coding, computer use, and agentic workflows where higher solution quality is needed without moving to a larger GPT-6 tier. | DeepSeek V4.1 Flash is a cost-efficient sparse Mixture-of-Experts (MoE) model in DeepSeek's V4.1 family, optimized for coding, reasoning, and agentic workflows. Despite its efficiency-focused positioning, DeepSeek reports that it surpasses the previous V4 Pro in performance, inference speed, and overall task completion time. The model is particularly strong at long-horizon, multi-step execution, making it well suited for coding agents, complex problem solving, and autonomous workflows that must reliably carry tasks through to completion. | Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token. |