SonnelyWorkspace/Models

Models

Compare NEAR AI models by workload and token cost.

3 models

ModelProvider contextInput / 1MCached / 1MOutput / 1MActions

DeepSeek V4.1 Flash

General-purpose reasoning and long document workflows.

1.05M$0.30$0.006$1.20Open in chat

GLM 5.3 Flash

Fast classification, extraction and short replies.

1.05M$0.08$0.012$0.50Open in chat

Qwen 3.6 35B

Code explanation, structured output and multilingual text.

262K$0.17$0.056$1.10Open in chat

NEAR AI lists these models in its Private TEE tier. Sonnely accepts text requests with smaller limits. Provider catalog ↗