Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

DeepSeek R1 Distill Qwen 1.5B vs LightOnOCR-3 0.8B

Both have similar output pricing, while LightOnOCR-3 0.8B offers a larger context window. Choose DeepSeek R1 Distill Qwen 1.5B or LightOnOCR-3 0.8B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

SpecDeepSeek R1 Distill Qwen 1.5BLightOnOCR-3 0.8B
ProviderAlibaba (China)Scaleway
Input / 1M tokens$0.00$2.46
Output / 1M tokens$0.00$0.00
Context window33K262K
Parameters——
Open weightsNoYes
ReleasedJan 2025Oct 2026
GPQA Diamond score33.6—
DeepSeek R1 Distill Qwen 1.5B details →LightOnOCR-3 0.8B details →

FAQ

Is DeepSeek R1 Distill Qwen 1.5B or LightOnOCR-3 0.8B cheaper?

DeepSeek R1 Distill Qwen 1.5B and LightOnOCR-3 0.8B have comparable output pricing.

Which has the larger context window, DeepSeek R1 Distill Qwen 1.5B or LightOnOCR-3 0.8B?

LightOnOCR-3 0.8B has the larger context window (262K tokens).

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