Inkling (xhigh) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Inkling (xhigh) for your use-case.
Fastest
Databricks
DeepInfra (FP8)
Baseten
Together AI
Thinking MachinesOutput speed
Total 5 providers
Lowest Latency
DeepInfra (FP8)DatabricksBasetenTogether AIThinking MachinesTime to first answer token
Total 5 providers
Lowest Price
DeepInfra (FP8)BasetenTogether AIThinking MachinesDatabricksBlended price (per 1M tokens)
Total 5 providers
Inkling is available through 5 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.
- For output speed, the top providers are Databricks (211.7 t/s), DeepInfra (FP8) (209.9 t/s), and Baseten (192.4 t/s). Speed varies significantly across providers, with a 140% difference between the fastest and slowest.
- For latency, DeepInfra (FP8) (10.09s), Databricks (10.44s), and Baseten (11.05s) offer the lowest time to first answer token.
- For pricing, DeepInfra (FP8) (0.71), Baseten (0.72), and Together AI (0.72) offer the lowest blended prices per 1M tokens.
- DeepInfra (FP8) offers both the lowest latency and best pricing, making it attractive for cost-conscious applications. Databricks is the fastest option for throughput-intensive workloads.
Highlights
Update: Default performance benchmarking workload has updated to 10k input tokens to better reflect production use cases. You can still select different workloads above.
Pricing
Pricing: Cache Hit, Input, and Output
Pricing: Blended Price
Pricing: Cache Discount
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed: Inkling (xhigh)
Latency vs. Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Inkling (xhigh) providers
Inkling (xhigh) is available through 5 API providers: DeepInfra (FP8), Baseten, Together AI, Thinking Machines, and Databricks. Each provider offers different performance characteristics and pricing.
Inkling (xhigh) is currently available through 5 API providers that we benchmark and track.
The fastest providers for Inkling (xhigh) by output speed are Databricks (211.7 t/s), DeepInfra (FP8) (209.9 t/s), and Baseten (192.4 t/s). Output speed measures how quickly tokens are generated after the model starts responding.
The providers with the lowest time to first answer token for Inkling (xhigh) are DeepInfra (FP8) (10.09s), Databricks (10.44s), and Baseten (11.05s). Lower latency means faster initial response time.
The most affordable providers for Inkling (xhigh) by blended price are DeepInfra (FP8) ($0.71 per 1M tokens), Baseten ($0.72 per 1M tokens), and Together AI ($0.72 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 (xhigh) are DeepInfra (FP8) ($0.95 per 1M input tokens), Baseten ($1.00 per 1M input tokens), and Together AI ($1.00 per 1M input tokens).
The providers with the lowest output token pricing for Inkling (xhigh) are DeepInfra (FP8) ($4.05 per 1M output tokens), Baseten ($4.05 per 1M output tokens), and Together AI ($4.05 per 1M output tokens).
Output speed for Inkling (xhigh) varies significantly across providers. Databricks is the fastest at 211.7 t/s, which is 2.4x faster than Thinking Machines at 88.0 t/s.
4 of 5 providers support JSON mode for Inkling (xhigh): DeepInfra (FP8), Baseten, Together AI, and Thinking Machines.
All 5 providers of Inkling (xhigh) support function calling (tool use).
The best provider for Inkling (xhigh) depends on your priorities: Databricks offers the highest output speed, DeepInfra (FP8) has the lowest latency, and DeepInfra (FP8) provides the most competitive pricing.
When choosing a provider for Inkling (xhigh), consider: output speed (for throughput-intensive tasks), 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 (xhigh)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview