Qwen3.5 397B A17B (Non-reasoning) API Provider Benchmarking & Analysis
Analysis of API providers for Qwen3.5 397B A17B (Non-reasoning) across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Eigen AI, Alibaba Cloud, Nebius Fast, Nebius (Base, FP4), Novita, DeepInfra FP8.
Fastest
Nebius Fast
Eigen AI
DeepInfra FP8
NovitaAlibaba CloudOutput speed
Total 6 providers
Lowest Latency
DeepInfra FP8Eigen AINovitaNebius (Base, FP4)Nebius FastTime to first token
Total 6 providers
Lowest Price
DeepInfra FP8Eigen AIAlibaba CloudNebius FastNebius (Base, FP4)Blended price (per 1M tokens)
Total 6 providers
Qwen3.5 397B A17B is available through 6 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 Nebius Fast (144.9 t/s), Eigen AI (142.3 t/s), DeepInfra FP8 (140.3 t/s). Speed varies significantly across providers, with a 62% difference between the fastest and slowest.
- For latency, DeepInfra FP8 (0.70s), Eigen AI (1.62s), Novita (1.71s) offer the lowest time to first token.
- For pricing, DeepInfra FP8 (1.25), Eigen AI (1.35), Alibaba Cloud (1.35) 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. Nebius Fast is the fastest option for throughput-intensive workloads.
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: Input and Output Prices: Qwen3.5 397B A17B Providers
Speed vs. Price: Qwen3.5 397B A17B Providers
Speed
Measured by Output Speed (tokens per second)
Output Speed: Qwen3.5 397B A17B Providers
Latency vs. Output Speed: Qwen3.5 397B A17B Providers
Latency
Measured by Time (seconds) to First Token
Time to First Token: Qwen3.5 397B A17B Providers
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: Qwen3.5 397B A17B Providers
API Features
Function (Tool) Calling & JSON Mode: Qwen3.5 397B A17B Providers
DeepInfra FP8Context Window: Qwen3.5 397B A17B Providers
Summary Table of Key Comparison Metrics
Frequently Asked Questions
Common questions about Qwen3.5 397B A17B (Non-reasoning) providers
Qwen3.5 397B A17B (Non-reasoning) is available through 6 API providers: Eigen AI, Alibaba Cloud, Nebius Fast, Nebius (Base, FP4), Novita, and DeepInfra FP8. Each provider offers different performance characteristics and pricing.
Qwen3.5 397B A17B (Non-reasoning) is currently available through 6 API providers that we benchmark and track.
The fastest providers for Qwen3.5 397B A17B (Non-reasoning) by output speed are Nebius Fast (144.9 t/s), Eigen AI (142.3 t/s), and DeepInfra FP8 (140.3 t/s). Output speed measures how quickly tokens are generated after the model starts responding.
The providers with the lowest time to first token for Qwen3.5 397B A17B (Non-reasoning) are DeepInfra FP8 (0.70s), Eigen AI (1.62s), and Novita (1.71s). Lower latency means faster initial response time.
The most affordable providers for Qwen3.5 397B A17B (Non-reasoning) by blended price are DeepInfra FP8 ($1.25 per 1M tokens), Eigen AI ($1.35 per 1M tokens), and Alibaba Cloud ($1.35 per 1M tokens). Blended price uses a 3:1 input to output token ratio.
The providers with the lowest input token pricing for Qwen3.5 397B A17B (Non-reasoning) are DeepInfra FP8 ($0.54 per 1M input tokens), Eigen AI ($0.60 per 1M input tokens), and Alibaba Cloud ($0.60 per 1M input tokens).
The providers with the lowest output token pricing for Qwen3.5 397B A17B (Non-reasoning) are DeepInfra FP8 ($3.40 per 1M output tokens), Eigen AI ($3.60 per 1M output tokens), and Alibaba Cloud ($3.60 per 1M output tokens).
Output speed for Qwen3.5 397B A17B (Non-reasoning) varies significantly across providers. Nebius Fast is the fastest at 144.9 t/s, which is 1.7x faster than Nebius (Base, FP4) at 85.9 t/s.
5 of 6 providers support JSON mode for Qwen3.5 397B A17B (Non-reasoning): Eigen AI, Alibaba Cloud, Nebius Fast, Nebius (Base, FP4), and Novita.
5 of 6 providers support function calling for Qwen3.5 397B A17B (Non-reasoning): Alibaba Cloud, Nebius Fast, Nebius (Base, FP4), Novita, and DeepInfra FP8.
The best provider for Qwen3.5 397B A17B (Non-reasoning) depends on your priorities: Nebius Fast offers the highest output speed, DeepInfra FP8 has the lowest latency, and DeepInfra FP8 provides the most competitive pricing.
When choosing a provider for Qwen3.5 397B A17B (Non-reasoning), 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 Qwen3.5 397B A17B (Non-reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview