This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
Institute of Foundation Models has launched a newer release, K2 Horizon 375B A23B. We suggest considering it instead.
K2 Think V2 API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of K2 Think V2 for your use-case.
Lowest Time per Task
Time per Intelligence Index task (minutes)
Total 0 providers
Lowest Cost per Task
Cost per Intelligence Index task
Total 0 providers
No API providers are currently available for K2 Think V2.
Please see the models page for K2 Think V2 for details of the model and its intelligence compared to other models.
Pricing
Cost per Intelligence Index Task: K2 Think V2
Pricing: Cache Hit, Input, and Output: K2 Think V2
Output Speed vs. Cost per Task: K2 Think V2
Speed
Average of the single-request and multi-turn agentic workloads measured
Output Speed: K2 Think V2
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token: K2 Think V2
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate: K2 Think V2
Key Comparison Metrics & API Features
| No results. | ||||||||
Frequently Asked Questions
Common questions about K2 Think V2 providers
K2 Think V2 is not currently available through any API providers we benchmark. As an open weights model, it can be self-hosted.