Compare models

This is the batch-processing endpoint for Thinking Machines Lab's Inkling-Small (276B total parameters, 12B active, Apache 2.0 license), running on a 512K-token context window for queued, non-real-time workloads. Pricing here is essentially flat against the standard endpoint rather than discounted, so it suits throughput-oriented batch jobs rather than latency-sensitive or long-context use.

Claude Haiku 4.5 is Anthropic's fast, affordable small model in the Claude 4 generation, balancing strong instruction-following and coding ability with low latency. It is designed for high-throughput agentic and chat applications where speed and cost efficiency are priorities.