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 Results for other workloads are historical and no longer updated.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, Qwen3.5 397B A17B. We suggest considering it instead.
For more information, see comparison of Qwen3.5 397B A17B to other models and API provider benchmarks for Qwen3.5 397B A17B.
Qwen3 235B A22B 2507 (Reasoning) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Qwen3 235B A22B 2507 (Reasoning) for your use-case.
Fastest
DeepInfra (FP8)
Novita
Alibaba CloudOutput speed
Total 3 providers
Lowest Latency
DeepInfra (FP8)NovitaAlibaba CloudTime to first answer token
Total 3 providers
Lowest Price
DeepInfra (FP8)Alibaba CloudNovitaBlended price (per 1M tokens)
Total 3 providers
Qwen3 235B A22B 2507 is available through 3 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 DeepInfra (FP8) (91.9 t/s), Novita (69.6 t/s), and Alibaba Cloud (64.0 t/s).
- For latency, DeepInfra (FP8) (22.49s), Novita (30.92s), and Alibaba Cloud (34.01s) offer the lowest time to first answer token.
- For pricing, DeepInfra (FP8) (0.42), Alibaba Cloud (0.44), and Novita (0.57) offer the lowest blended prices per 1M tokens.
- DeepInfra (FP8) stands out as the overall leader, ranking first across all three categories: speed, latency, and pricing.
Highlights
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 235B A22B 2507 (Reasoning)
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 Qwen3 235B A22B 2507 (Reasoning) providers
Qwen3 235B A22B 2507 (Reasoning) is available through 3 API providers: Alibaba Cloud, DeepInfra (FP8), and Novita. Each provider offers different performance characteristics and pricing.
Qwen3 235B A22B 2507 (Reasoning) is currently available through 3 API providers that we benchmark and track.
The fastest providers for Qwen3 235B A22B 2507 (Reasoning) by output speed are DeepInfra (FP8) (91.9 t/s), Novita (69.6 t/s), and Alibaba Cloud (64.0 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 Qwen3 235B A22B 2507 (Reasoning) are DeepInfra (FP8) (22.49s), Novita (30.92s), and Alibaba Cloud (34.01s). Lower latency means faster initial response time.
The most affordable providers for Qwen3 235B A22B 2507 (Reasoning) by blended price are DeepInfra (FP8) ($0.42 per 1M tokens), Alibaba Cloud ($0.44 per 1M tokens), and Novita ($0.57 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 2507 (Reasoning) are Alibaba Cloud ($0.23 per 1M input tokens), DeepInfra (FP8) ($0.23 per 1M input tokens), and Novita ($0.30 per 1M input tokens).
The providers with the lowest output token pricing for Qwen3 235B A22B 2507 (Reasoning) are Alibaba Cloud ($2.30 per 1M output tokens), DeepInfra (FP8) ($2.30 per 1M output tokens), and Novita ($3.00 per 1M output tokens).
Prices for Qwen3 235B A22B 2507 (Reasoning) vary up to 1.4x across providers. The most affordable is DeepInfra (FP8) at $0.42 per 1M tokens, while Novita charges $0.57 per 1M tokens.
2 of 3 providers support JSON mode for Qwen3 235B A22B 2507 (Reasoning): Alibaba Cloud and DeepInfra (FP8).
All 3 providers of Qwen3 235B A22B 2507 (Reasoning) support function calling (tool use).
DeepInfra (FP8) leads across all key metrics for Qwen3 235B A22B 2507 (Reasoning), offering the fastest speed, lowest latency, and most competitive pricing.
When choosing a provider for Qwen3 235B A22B 2507 (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 2507 (Reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview