Inkling Small API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Inkling Small for your use-case.
Lowest Time per Task
DeepInfra
Thinking MachinesTime per Intelligence Index task (minutes)
Total 2 providers
Lowest Cost per Task
Thinking MachinesDeepInfraCost per Intelligence Index task
Total 2 providers
Inkling Small is available through 2 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.
- For time per task, DeepInfra (4.3 min) and Thinking Machines (8.0 min) finish an Intelligence Index task fastest.
- For cost per task, Thinking Machines ($0.20) and DeepInfra ($0.29) are the cheapest per Intelligence Index task.
Pricing
Cost per Intelligence Index Task: Inkling Small
Pricing: Cache Hit, Input, and Output: Inkling Small
Output Speed vs. Cost per Task: Inkling Small
Speed
Average of the single-request and multi-turn agentic workloads measured
Time per Intelligence Index Task: Inkling Small
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token: Inkling Small
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate: Inkling Small
Caching
Cache Hit Rate: Inkling Small
Cost per Task vs. Cache Hit Rate: Inkling Small
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Inkling Small providers
Inkling Small is available through 2 API providers: DeepInfra and Thinking Machines. Each provider offers different performance characteristics and pricing.
Inkling Small is currently available through 2 API providers that we benchmark and track.
By time per task, the fastest providers for Inkling Small are DeepInfra (4.3 min) and Thinking Machines (8.0 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 Small are Thinking Machines (29.41s) and DeepInfra (48.55s). Lower latency means faster initial response time.
The most affordable providers for Inkling Small by blended price are Thinking Machines ($0.22 per 1M tokens) and DeepInfra ($0.28 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 Small are Thinking Machines ($0.30 per 1M input tokens) and DeepInfra ($0.45 per 1M input tokens).
The providers with the lowest output token pricing for Inkling Small are DeepInfra ($1.20 per 1M output tokens) and Thinking Machines ($1.20 per 1M output tokens).
Prices for Inkling Small vary up to 1.3x across providers. The most affordable is Thinking Machines at $0.22 per 1M tokens, while DeepInfra charges $0.28 per 1M tokens.
Time per task for Inkling Small varies significantly across providers. DeepInfra is the quickest at 4.3 minutes per Intelligence Index task, 1.9x quicker than Thinking Machines at 8.0 minutes.
All 2 providers of Inkling Small support JSON mode for structured output.
All 2 providers of Inkling Small support function calling (tool use).
The best provider for Inkling Small depends on your priorities: DeepInfra has the lowest time per task, Thinking Machines has the lowest latency, and Thinking Machines provides the most competitive pricing.
When choosing a provider for Inkling 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 Small's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview