Is Step 3.7 Flash (NovitaAI) or DeepSeek V4 Pro (reka-ai) cheaper?

Step 3.7 Flash (NovitaAI) is cheaper on output tokens ($1.15 vs $3.30 per 1M).

Which has the larger context window, Step 3.7 Flash (NovitaAI) or DeepSeek V4 Pro (reka-ai)?

DeepSeek V4 Pro (reka-ai) has the larger context window (1M tokens).

Step 3.7 Flash (NovitaAI) vs DeepSeek V4 Pro (reka-ai)

Step 3.7 Flash (NovitaAI) is cheaper on output tokens, while DeepSeek V4 Pro (reka-ai) offers a larger context window. Choose Step 3.7 Flash (NovitaAI) or DeepSeek V4 Pro (reka-ai) based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Step 3.7 Flash (NovitaAI)	DeepSeek V4 Pro (reka-ai)
Provider	LLM Gateway	LLM Gateway
Input / 1M tokens	$0.20	$1.20
Output / 1M tokens	$1.15	$3.30
Context window	262K	1M
Parameters	—	—
Open weights	Yes	Yes
Released	May 2026	Apr 2026

Step 3.7 Flash (NovitaAI) details →DeepSeek V4 Pro (reka-ai) details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.