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.

•

Open weights model

•

Released December 2025

K2 Think V2 API Provider Benchmarking & Analysis

Model Comparison

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.

Benchmarks of providers are not available for this model.

Please see the models page for K2 Think V2 for details of the model and its intelligence compared to other models.

Inference time (minutes) per Intelligence Index task · Lower is better
No data available
Weighted average cost (USD) per Intelligence Index task · Lower is better
No data available

Pricing

Cost per Intelligence Index Task: K2 Think V2

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better
No data available

Pricing: Cache Hit, Input, and Output: K2 Think V2

Price (USD per M Tokens) · Lower is better
No data available

Output Speed vs. Cost per Task: K2 Think V2

Output speed: output tokens divided by total request time, including time to first token · Weighted average cost (USD) per Intelligence Index task
Most attractive quadrant
No data available

Speed

Average of the single-request and multi-turn agentic workloads measured

Output Speed: K2 Think V2

Output tokens divided by total request time · Includes time to first token · Average of the single-request and multi-turn agentic workloads measured · Higher is better
No data available

Latency

Average of the single-request and multi-turn agentic workloads measured

Time to First Answer Token: K2 Think V2

Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better
No data available

Reliability

Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured

Endpoint Error Rate: K2 Think V2

Share of requests the endpoint failed with an error, a rate limit or a timeout · Across all the single-request and multi-turn agentic workloads measured · Lower is better
No data available

Key Comparison Metrics & API Features

No results.

Frequently Asked Questions

Common questions about K2 Think V2 providers