This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.
Alibaba has launched a newer model, Qwen3 235B 2507. We suggest considering it instead.
For more information, see comparison of Qwen3 235B 2507 to other models and API provider benchmarks for Qwen3 235B 2507.
Qwen3 235B A22B (Non-reasoning) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Qwen3 235B A22B (Non-reasoning) for your use-case.
Fastest
Alibaba Cloud
Novita (FP8)Output speed
Total 2 providers
Lowest Latency
Novita (FP8)Alibaba CloudTime to first token
Total 2 providers
Lowest Price
Novita (FP8)Alibaba CloudBlended price (per 1M tokens)
Total 2 providers
Qwen3 235B (Non-reasoning) is available through 2 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 Alibaba Cloud (58.3 t/s) and Novita (FP8) (21.6 t/s).
- For latency, Novita (FP8) (2.65s) and Alibaba Cloud (2.75s) offer the lowest time to first token.
- For pricing, Novita (FP8) (0.26) and Alibaba Cloud (0.91) offer the lowest blended prices per 1M tokens.
- Novita (FP8) offers both the lowest latency and best pricing, making it attractive for cost-conscious applications. Alibaba Cloud is the fastest option for throughput-intensive workloads.
Highlights
Pricing
Pricing: Cache Hit, Input, and Output
Pricing: Blended Price
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed: Qwen3 235B A22B (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 235B A22B (Non-reasoning) providers
Qwen3 235B A22B (Non-reasoning) is available through 2 API providers: Novita (FP8) and Alibaba Cloud. Each provider offers different performance characteristics and pricing.
Qwen3 235B A22B (Non-reasoning) is currently available through 2 API providers that we benchmark and track.
The fastest providers for Qwen3 235B A22B (Non-reasoning) by output speed are Alibaba Cloud (58.3 t/s) and Novita (FP8) (21.6 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 235B A22B (Non-reasoning) are Novita (FP8) (2.65s) and Alibaba Cloud (2.75s). Lower latency means faster initial response time.
The most affordable providers for Qwen3 235B A22B (Non-reasoning) by blended price are Novita (FP8) ($0.26 per 1M tokens) and Alibaba Cloud ($0.91 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 235B A22B (Non-reasoning) are Novita (FP8) ($0.20 per 1M input tokens) and Alibaba Cloud ($0.70 per 1M input tokens).
The providers with the lowest output token pricing for Qwen3 235B A22B (Non-reasoning) are Novita (FP8) ($0.80 per 1M output tokens) and Alibaba Cloud ($2.80 per 1M output tokens).
Prices for Qwen3 235B A22B (Non-reasoning) vary up to 3.5x across providers. The most affordable is Novita (FP8) at $0.26 per 1M tokens, while Alibaba Cloud charges $0.91 per 1M tokens.
Output speed for Qwen3 235B A22B (Non-reasoning) varies significantly across providers. Alibaba Cloud is the fastest at 58.3 t/s, which is 2.7x faster than Novita (FP8) at 21.6 t/s.
All 2 providers of Qwen3 235B A22B (Non-reasoning) support JSON mode for structured output.
1 of 2 providers support function calling for Qwen3 235B A22B (Non-reasoning): Alibaba Cloud.
The best provider for Qwen3 235B A22B (Non-reasoning) depends on your priorities: Alibaba Cloud offers the highest output speed, Novita (FP8) has the lowest latency, and Novita (FP8) provides the most competitive pricing.
When choosing a provider for Qwen3 235B A22B (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 235B A22B (Non-reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview