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 Results for other workloads are historical and no longer updated.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 release, Qwen3.8 27B. We suggest considering it instead.

Alibaba

•

Qwen3.6 27B

•

Open weights model

•

Released April 2026

Qwen3.6 27B (Non-reasoning) API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of Qwen3.6 27B (Non-reasoning) for your use-case.

Fastest

Novita

59.7 t/s

DeepInfra FP8

59.7 t/s

Alibaba Cloud

59.2 t/s

Output speed

Total 3 providers

Lowest Latency

DeepInfra FP8

1.01 s

Novita

3.37 s

Alibaba Cloud

3.60 s

Time to first token

Total 3 providers

Lowest Price

DeepInfra FP8

$0.61

Alibaba Cloud

$0.90

Novita

$0.90

Blended price (per 1M tokens)

Total 3 providers

Qwen3.6 27B (non-reasoning) 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 Novita (59.7 t/s), DeepInfra FP8 (59.7 t/s), and Alibaba Cloud (59.2 t/s).
For latency, DeepInfra FP8 (1.01s), Novita (3.37s), and Alibaba Cloud (3.60s) offer the lowest time to first token.
For pricing, DeepInfra FP8 (0.61), Alibaba Cloud (0.90), and Novita (0.90) 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. Novita is the fastest option for throughput-intensive workloads.

Speed

Output tokens per second · Higher is better

Latency

Seconds to first answer token received · Lower is better

Price

USD per 1M tokens (blended) · Lower is better

Pricing

Pricing: Cache Hit, Input, and Output: Qwen3.6 27B (Non-reasoning)

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Cost per Intelligence Index Task: Qwen3.6 27B (Non-reasoning)

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

No data available

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Output Speed vs. Price: Qwen3.6 27B (Non-reasoning)

Blended at 7:2:1 (cache-input-output) · Output speed: output tokens per second · USD per 1M tokens (blended)

Most attractive quadrant

Pareto line

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Speed

Measured by Output Speed (tokens per second)

Output Speed: Qwen3.6 27B (Non-reasoning)

Output speed: output tokens per second · 10,000 input tokens

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

Time per Intelligence Index Task: Qwen3.6 27B (Non-reasoning)

Weighted average decode time (minutes) per Intelligence Index task · Excludes TTFT and overhead time · Lower is better

No data available

The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.

Cost per Task vs. Time per Task: Qwen3.6 27B (Non-reasoning)

Weighted average cost (USD) per Intelligence Index task · Weighted average decode time (minutes) per Intelligence Index task

Most attractive quadrant

No data available

Latency

Measured by Time (seconds) to First Token

Time to First Token: Qwen3.6 27B (Non-reasoning)

Seconds to first token received · Lower is better · 10,000 input tokens

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Cache Behaviour

Cache Hit Rate: Qwen3.6 27B (Non-reasoning)

Share of cacheable input tokens served from cache · Median of the last four weeks, updated Oct 26, 2026

The share of cacheable input tokens served from the provider's prompt cache, measured during multi-turn agentic coding sessions. We regularly measure each endpoint and report a representative rate based on recent measurements. Higher values mean more of the input is billed at the cheaper cache-hit price, where the provider offers one, which lowers the effective cost of agentic workloads. For further details, see our methodology page.

Cost per Task vs. Cache Hit Rate: Qwen3.6 27B (Non-reasoning)

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Oct 26, 2026

Most attractive quadrant

No data available

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: Qwen3.6 27B (Non-reasoning)

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 input tokens

Seconds to receive a 500 token response. Key components:

Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed

Key Comparison Metrics & API Features



Alibaba Cloud	262k	Open	--	59	3.60	12.04	--
DeepInfra	262k	Open	--	60	1.01	9.38	--
Novita	262k	Open	--	60	3.37	11.74	--

Frequently Asked Questions

Common questions about Qwen3.6 27B (Non-reasoning) providers

Qwen3.6 27B (Non-reasoning) is available through 3 API providers: DeepInfra FP8, Alibaba Cloud, and Novita. Each provider offers different performance characteristics and pricing.

Qwen3.6 27B (Non-reasoning) is currently available through 3 API providers that we benchmark and track.

The fastest providers for Qwen3.6 27B (Non-reasoning) by output speed are Novita (59.7 t/s), DeepInfra FP8 (59.7 t/s), and Alibaba Cloud (59.2 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 27B (Non-reasoning) are DeepInfra FP8 (1.01s), Novita (3.37s), and Alibaba Cloud (3.60s). Lower latency means faster initial response time.

The most affordable providers for Qwen3.6 27B (Non-reasoning) by blended price are DeepInfra FP8 ($0.61 per 1M tokens), Alibaba Cloud ($0.90 per 1M tokens), and Novita ($0.90 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 27B (Non-reasoning) are DeepInfra FP8 ($0.32 per 1M input tokens), Alibaba Cloud ($0.60 per 1M input tokens), and Novita ($0.60 per 1M input tokens).

The providers with the lowest output token pricing for Qwen3.6 27B (Non-reasoning) are DeepInfra FP8 ($3.20 per 1M output tokens), Alibaba Cloud ($3.60 per 1M output tokens), and Novita ($3.60 per 1M output tokens).

Prices for Qwen3.6 27B (Non-reasoning) vary up to 1.5x across providers. The most affordable is DeepInfra FP8 at $0.61 per 1M tokens, while Alibaba Cloud charges $0.90 per 1M tokens.

All 3 providers of Qwen3.6 27B (Non-reasoning) support JSON mode for structured output.

All 3 providers of Qwen3.6 27B (Non-reasoning) support function calling (tool use).

The best provider for Qwen3.6 27B (Non-reasoning) depends on your priorities: Novita offers the highest output speed, DeepInfra FP8 has the lowest latency, and DeepInfra FP8 provides the most competitive pricing.

When choosing a provider for Qwen3.6 27B (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 27B (Non-reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview

Qwen3.6 27B (Non-reasoning) API Provider Benchmarking & Analysis

Fastest

Lowest Latency

Lowest Price

Speed

Latency

Price

Pricing

Pricing: Cache Hit, Input, and Output: Qwen3.6 27B (Non-reasoning)

Cache Hit

Cost per Intelligence Index Task: Qwen3.6 27B (Non-reasoning)

Cost per Intelligence Index Task

Output Speed vs. Price: Qwen3.6 27B (Non-reasoning)

Output Speed

Speed

Output Speed: Qwen3.6 27B (Non-reasoning)

Output Speed

Model Performance Representation

Time per Intelligence Index Task: Qwen3.6 27B (Non-reasoning)

Time per Intelligence Index Task

Cost per Task vs. Time per Task: Qwen3.6 27B (Non-reasoning)

Cost per Intelligence Index Task

Latency

Time to First Token: Qwen3.6 27B (Non-reasoning)

Latency (Time to First Token)

Median

Cache Behaviour

Cache Hit Rate: Qwen3.6 27B (Non-reasoning)

What Cache Hit Rate Shows

Cost per Task vs. Cache Hit Rate: Qwen3.6 27B (Non-reasoning)

Cost per Intelligence Index Task

End-to-End Response Time

End-to-End Response Time: Qwen3.6 27B (Non-reasoning)

End-to-End Response Time

Key Comparison Metrics & API Features

Frequently Asked Questions

Where can I access Qwen3.6 27B (Non-reasoning)?

How many API providers offer Qwen3.6 27B (Non-reasoning)?

Which provider is fastest for Qwen3.6 27B (Non-reasoning)?

Which provider has the lowest latency for Qwen3.6 27B (Non-reasoning)?

Which provider is cheapest for Qwen3.6 27B (Non-reasoning)?

Which provider has the lowest input price for Qwen3.6 27B (Non-reasoning)?

Which provider has the lowest output price for Qwen3.6 27B (Non-reasoning)?

How much do prices vary across Qwen3.6 27B (Non-reasoning) providers?

Which Qwen3.6 27B (Non-reasoning) providers support JSON mode?

Which Qwen3.6 27B (Non-reasoning) providers support function calling?

Which is the best provider for Qwen3.6 27B (Non-reasoning)?

How do I choose a provider for Qwen3.6 27B (Non-reasoning)?

Does provider performance for Qwen3.6 27B (Non-reasoning) change over time?

What are the overall capabilities of Qwen3.6 27B (Non-reasoning)?