Inkling 2 Small API Provider Benchmarking & Analysis
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
Time per Intelligence Index task (minutes)
Total 4 providers
Lowest Cost per Task
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.
Pricing
Cost per Intelligence Index Task: Inkling 2 Small
Pricing: Cache Hit, Input, and Output: Inkling 2 Small
Output Speed vs. Cost per Task: Inkling 2 Small
Speed
Average of the single-request and multi-turn agentic workloads measured
Time per Intelligence Index Task: Inkling 2 Small
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token: Inkling 2 Small
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate: Inkling 2 Small
Caching
Cache Hit Rate: Inkling 2 Small
Cost per Task vs. Cache Hit Rate: Inkling 2 Small
Key Comparison Metrics & API Features
$1.18 | 28.5 | 68.69 | 0.0% | 262k | Open | |||
Frequently Asked Questions
Common questions about Inkling 2 Small providers
Inkling 2 Small is available through 4 API providers: DeepInfra, Nebius, Together AI, and Thinking Machines. Each provider offers different performance characteristics and pricing.
Inkling 2 Small is currently available through 4 API providers that we benchmark and track.
By time per task, the fastest providers for Inkling 2 Small are Together AI (10.5 min), Nebius (19.9 min), and Thinking Machines (21.6 min). Time per task divides the model's output tokens per Intelligence Index task by each provider's end-to-end output speed.
The providers with the lowest time to first answer token for Inkling 2 Small are Together AI (12.61s), Nebius (25.20s), and Thinking Machines (37.85s). Lower latency means faster initial response time.
The most affordable providers for Inkling 2 Small by blended price are DeepInfra ($0.18 per 1M tokens), Together AI ($0.18 per 1M tokens), and Thinking Machines ($0.18 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
The providers with the lowest input token pricing for Inkling 2 Small are DeepInfra ($0.30 per 1M input tokens), Nebius ($0.30 per 1M input tokens), and Together AI ($0.30 per 1M input tokens).
The providers with the lowest output token pricing for Inkling 2 Small are DeepInfra ($1.00 per 1M output tokens), Nebius ($1.00 per 1M output tokens), and Together AI ($1.00 per 1M output tokens).
Time per task for Inkling 2 Small varies significantly across providers. Together AI is the quickest at 10.5 minutes per Intelligence Index task, 2.2x quicker than DeepInfra at 23.3 minutes.
All 4 providers of Inkling 2 Small support JSON mode for structured output.
All 4 providers of Inkling 2 Small support function calling (tool use).
For Inkling 2 Small, Together AI offers the best performance with the lowest time per task and lowest latency. For cost optimization, DeepInfra provides the most competitive pricing.
When choosing a provider for Inkling 2 Small, consider: time per task (how quickly the provider completes an Intelligence Index task), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
For information about Inkling 2 Small's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview