Qwen3.6 35B A3B (Non-reasoning) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Qwen3.6 35B A3B (Non-reasoning) for your use-case.
Fastest
CoreWeave (FP8)
Scaleway
Alibaba Cloud
Novita
Parasail (FP8)Output speed
Total 7 providers
Lowest Latency
CoreWeave (FP8)
DeepInfra (FP8)Parasail (FP8)ScalewayNovitaTime to first token
Total 7 providers
Lowest Price
Parasail (FP8)DeepInfra (FP8)CoreWeave (FP8)Novita
GMI FP8Blended price (per 1M tokens)
Total 7 providers
Qwen3.6 35B A3B (Non-reasoning) is available through 7 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 CoreWeave (FP8) (181.8 t/s), Scaleway (142.4 t/s), and Alibaba Cloud (139.4 t/s). Speed varies significantly across providers, with a 367% difference between the fastest and slowest.
- For latency, CoreWeave (FP8) (1.06s), DeepInfra (FP8) (1.07s), and Parasail (FP8) (1.13s) offer the lowest time to first token.
- For pricing, Parasail (FP8) (0.16), DeepInfra (FP8) (0.18), and CoreWeave (FP8) (0.35) offer the lowest blended prices per 1M tokens. Prices vary up to 3.4x across providers.
- CoreWeave (FP8) offers the best performance with both the highest speed and lowest latency. For cost optimization, Parasail (FP8) provides the most competitive pricing.
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: Qwen3.6 35B A3B (Non-reasoning)
Latency vs. Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First 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 Qwen3.6 35B A3B (Non-reasoning) providers
Qwen3.6 35B A3B (Non-reasoning) is available through 7 API providers: Scaleway, CoreWeave (FP8), DeepInfra (FP8), Novita, GMI FP8, Parasail (FP8), and Alibaba Cloud. Each provider offers different performance characteristics and pricing.
Qwen3.6 35B A3B (Non-reasoning) is currently available through 7 API providers that we benchmark and track.
The fastest providers for Qwen3.6 35B A3B (Non-reasoning) by output speed are CoreWeave (FP8) (181.8 t/s), Scaleway (142.4 t/s), and Alibaba Cloud (139.4 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 Qwen3.6 35B A3B (Non-reasoning) are CoreWeave (FP8) (1.06s), DeepInfra (FP8) (1.07s), and Parasail (FP8) (1.13s). Lower latency means faster initial response time.
The most affordable providers for Qwen3.6 35B A3B (Non-reasoning) by blended price are Parasail (FP8) ($0.16 per 1M tokens), DeepInfra (FP8) ($0.18 per 1M tokens), and CoreWeave (FP8) ($0.35 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 Qwen3.6 35B A3B (Non-reasoning) are DeepInfra (FP8) ($0.10 per 1M input tokens), Parasail (FP8) ($0.15 per 1M input tokens), and Novita ($0.25 per 1M input tokens).
The providers with the lowest output token pricing for Qwen3.6 35B A3B (Non-reasoning) are DeepInfra (FP8) ($0.95 per 1M output tokens), Parasail (FP8) ($1.00 per 1M output tokens), and CoreWeave (FP8) ($1.25 per 1M output tokens).
Prices for Qwen3.6 35B A3B (Non-reasoning) vary up to 3.4x across providers. The most affordable is Parasail (FP8) at $0.16 per 1M tokens, while Alibaba Cloud charges $0.56 per 1M tokens.
Output speed for Qwen3.6 35B A3B (Non-reasoning) varies significantly across providers. CoreWeave (FP8) is the fastest at 181.8 t/s, which is 4.7x faster than DeepInfra (FP8) at 38.9 t/s.
All 7 providers of Qwen3.6 35B A3B (Non-reasoning) support JSON mode for structured output.
All 7 providers of Qwen3.6 35B A3B (Non-reasoning) support function calling (tool use).
For Qwen3.6 35B A3B (Non-reasoning), CoreWeave (FP8) offers the best performance with highest speed and lowest latency. For cost optimization, Parasail (FP8) provides the most competitive pricing.
When choosing a provider for Qwen3.6 35B A3B (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 Qwen3.6 35B A3B (Non-reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview