•

Open weights model

•

Released November 2026

Inkling 2 Small API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of Inkling 2 Small for your use-case.

Lowest Time per Task

#1
Together AITogether AI
10.5 min
#2
NebiusNebius
19.9 min
#3
Thinking MachinesThinking Machines
21.6 min
#4
DeepInfraDeepInfra
23.3 min

Time per Intelligence Index task (minutes)

Total 4 providers

Lowest Cost per Task

#1
DeepInfraDeepInfra
$1.15
#2
Thinking MachinesThinking Machines
$1.18
#3
Together AITogether AI
$1.31
#4
NebiusNebius
$2.01

Cost per Intelligence Index task

Total 4 providers

Inkling 2 Small is available through 4 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

  • For time per task, Together AI (10.5 min), Nebius (19.9 min), and Thinking Machines (21.6 min) finish an Intelligence Index task fastest.
  • For cost per task, DeepInfra ($1.15), Thinking Machines ($1.18), and Together AI ($1.31) are the cheapest per Intelligence Index task.
Inference time (minutes) per Intelligence Index task · Lower is better
Weighted average cost (USD) per Intelligence Index task · Lower is better

Pricing

Cost per Intelligence Index Task: Inkling 2 Small

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Pricing: Cache Hit, Input, and Output: Inkling 2 Small

Price (USD per M Tokens) · Lower is better

Output Speed vs. Cost per Task: Inkling 2 Small

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
Pareto line

Speed

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

Time per Intelligence Index Task: Inkling 2 Small

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Lower is better

Latency

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

Time to First Answer Token: Inkling 2 Small

Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better

Reliability

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

Endpoint Error Rate: Inkling 2 Small

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

Caching

Cache Hit Rate: Inkling 2 Small

Median across multi-turn agentic session runs in the last four weeks, updated Oct 26, 2026 · Higher is better

Cost per Task vs. Cache Hit Rate: Inkling 2 Small

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Oct 26, 2026
Most attractive quadrant
Pareto line

Key Comparison Metrics & API Features

Thinking Machines logoThinking Machines
$1.18
28.5
68.69
0.0%
262k
Open

Frequently Asked Questions

Common questions about Inkling 2 Small providers