What is the cheapest Qwen model?

Qwen3.7 Flash is the lowest blended-price option among tracked active non-embedding models, or among all models if only embeddings are listed: $0.03 input and $0.13 output per million tokens ($0.06 blended). Blended pricing uses 75% input and 25% output for generation models; your cheapest option may differ with your workload.

Which Qwen model has the highest AA Intelligence score?

Qwen3.8 2.4T A95B has the highest listed Artificial Analysis Intelligence Index score among tracked active Qwen models: 39.9. This is one evaluation, not a guarantee of the best result for every task. Models without measured results are not ranked as zero.

How do I calculate monthly Qwen API costs?

Multiply input tokens in millions by the input rate and add output tokens in millions multiplied by the output rate. For example, 20 million input and 5 million output tokens on Qwen3.7 Flash cost an estimated $1.25 at the listed rates. This excludes tool charges, cache-specific charges, taxes and any endpoint-specific adjustments.

Which Qwen model has the largest context window?

Qwen3.8 2.4T A95B has a listed context window of 1M tokens, the largest among tracked active Qwen models. Context capacity and maximum response length are separate limits; verify both on the model page and in the endpoint documentation.

What is the latest Qwen model in the catalog?

Qwen3.8 Max Prime has the most recent listed release date among tracked active Qwen models: 2026-09-23. Models without a usable release date are excluded from this comparison. Catalog release dates do not guarantee immediate API availability.

Do Qwen models support image inputs?

27 tracked active models list image inputs, including Qwen2.5 VL 72B Instruct, Qwen3.5-122B-A10B, Qwen3.5-27B. Accepting images does not mean a model generates images; check each model's separate input and output formats and endpoint limits.

Can prompt caching lower Qwen API costs?

23 tracked active models have a listed cached-input rate, including Qwen-Plus, Qwen2.5 VL 72B Instruct, Qwen3 235B A22B Instruct 2507. Savings depend on eligible repeated input and the endpoint's cache rules, duration and any write charges.

Do Qwen models support tool calling?

51 tracked active models list tool-calling capabilities, including Qwen2.5 72B Instruct, Qwen2.5 7B Instruct, Qwen-Plus. Verify the exact tool schema and availability with your API endpoint before integrating.

How should I compare Qwen benchmark scores and prices?

Compare scores within the same evaluation: Artificial Analysis Intelligence Index, DesignArena Elo, general Arena Elo and MMLU-Pro use different tasks and scales. Missing results are not zeroes. Pair a relevant measured benchmark with input/output pricing and tests of your own workload; the cheapest or highest-scoring model is not automatically the best fit.

Are retired Qwen models included in the price list?

The price list shows active models by default. Turn on Show retired models to include retired catalog entries, where available. A retained model page preserves reference information, not a promise that its API is still available.

Is Qwen an AI lab or an inference host?

Qwen is categorized as an AI lab in this catalog. Individual model pages list available API hosts separately; model creator and API host are different roles.

AI lab

Qwen API pricing & models

We track 53 Qwen models, priced from $0.03 per 1M input tokens with context windows up to 1M tokens.

Models tracked

Text & Reasoning · Code & SLMs · Vision

$0.06

Cheapest model

Qwen3.7 Flash

39.9

Top quality score

Qwen3.8 2.4T A95B

Largest context

6-mo price trend 20%

Price list

All Qwen models and prices

Current Qwen API prices per 1M tokens, context windows and benchmark scores. Click a column to sort, or a model for full pricing details.

Show retired models


Qwen3.8 2.4T A95B Qwen	$2	$6	1M	39.9	—	—	—	0%
Qwen3.8 27B Qwen	$0.425	$2.55	1M	33.7	—	—	—	203%
Qwen3.7 Max Qwen	$1.475	$4.425	1M	29.5	1280	—	—	0%
Qwen3.6 Max Preview Qwen	$1.027	$6.162	262K	28.4	—	—	—	0%
Qwen3.6 Plus Qwen	$0.325	$1.95	1M	27	1239	—	—	0%
Qwen3.7 Plus Qwen	$0.32	$1.28	1M	25.2	1272	—	—	0%
Qwen3.5-27B Qwen	$0.26	$2.6	262K	22.9	—	—	—	479%
Qwen3.6 27B Qwen	$0.45	$2.7	262K	21.4	—	—	—	322%
Qwen3 Max Thinking Qwen	$0.78	$3.9	262K	21.3	—	—	—	0%
Qwen3.5-35B-A3B Qwen	$0.15	$1	262K	19.3	—	—	—	55%
Qwen3.5 397B A17B Qwen	$0.45	$3	262K	18.4	1183	—	—	163%
Qwen3.6 35B A3B Qwen	$0.15	$1	262K	18.2	—	—	—	0%
Qwen3 Max Qwen	$0.78	$3.9	262K	15.6	1113	—	—	0%
Qwen3.5-122B-A10B Qwen	$0.26	$2.08	262K	15.6	—	—	—	0%
Qwen3.5-9B Qwen	$0.1	$0.15	262K	11.2	—	—	—	0%
Qwen3 VL 235B A22B Instruct Qwen	$0.21	$1.9	262K	9.9	—	—	—	0%
Qwen3 Coder 30B A3B Instruct Qwen	$0.07	$0.28	262K	9.6	—	—	—	0%
Qwen3 Next 80B A3B Instruct Qwen	$0.15	$1.5	262K	9.6	—	—	—	549%
Qwen3 Coder Next Qwen	$0.12	$0.8	262K	9.2	—	—	—	0%
Qwen3 VL 32B Instruct Qwen	$0.104	$0.416	131K	8.4	—	—	—	0%
Qwen3 VL 30B A3B Instruct Qwen	$0.15	$0.6	262K	7.9	—	—	—	0%
Qwen3 30B A3B Instruct 2507 Qwen	$0.1	$0.3	262K	7.5	—	—	—	100%
Qwen3 VL 8B Instruct Qwen	$0.117	$0.455	262K	7.3	—	—	—	0%
Qwen Plus 0728 Qwen	$0.26	$0.78	1M	—	—	—	—	0%
Qwen-Plus Qwen	$0.26	$0.78	1M	—	—	—	—	0%
Qwen2.5 72B Instruct Qwen	$0.36	$0.4	33K	—	—	—	—	0%
Qwen2.5 7B Instruct Qwen	$0.1	$0.2	33K	—	—	—	—	0%
Qwen2.5 Coder 32B Instruct Qwen	$0.66	$1	33K	—	—	—	—	0%
Qwen2.5 VL 72B Instruct Qwen	$0.8	$1	128K	—	—	—	—	0%
Qwen3 14B Qwen	$0.12	$0.24	131K	—	—	—	—	0%
Qwen3 235B A22B Qwen	$0.455	$1.82	131K	—	1006	—	—	0%
Qwen3 235B A22B Instruct 2507 Qwen	$0.09	$0.55	262K	—	—	—	—	211%
Qwen3 235B A22B Thinking 2507 Qwen	$0.23	$2.3	131K	—	1037	—	—	0%
Qwen3 30B A3B Qwen	$0.12	$0.5	131K	—	945	—	—	0%
Qwen3 30B A3B Thinking 2507 Qwen	$0.2	$2.4	82K	—	—	—	—	0%
Qwen3 32B Qwen	$0.08	$0.28	131K	—	—	—	—	0%
Qwen3 8B Qwen	$0.117	$0.455	131K	—	—	—	—	0%
Qwen3 Coder 480B A35B Qwen	$0.3	$1	262K	—	—	—	—	0%
Qwen3 Coder Flash Qwen	$0.195	$0.975	1M	—	—	—	—	0%
Qwen3 Coder Plus Qwen	$0.65	$3.25	1M	—	—	—	—	0%
Qwen3 Next 80B A3B Thinking Qwen	$0.15	$1.2	262K	—	—	—	—	0%
Qwen3 VL 235B A22B Thinking Qwen	$0.4	$4	131K	—	—	—	—	0%
Qwen3 VL 30B A3B Thinking Qwen	$0.2	$2.4	262K	—	—	—	—	0%
Qwen3 VL 8B Thinking Qwen	$0.18	$2.1	131K	—	—	—	—	0%
Qwen3.5 Plus 2026-02-15 Qwen	$0.26	$1.56	1M	—	1171	—	—	0%
Qwen3.5 Plus 2026-04-20 Qwen	$0.3	$1.8	1M	—	—	—	—	0%
Qwen3.5-Flash Qwen	$0.065	$0.26	1M	—	—	—	—	0%
Qwen3.6 Flash Qwen	$0.1875	$1.125	1M	—	—	—	—	0%
Qwen3.7 Flash Qwen	$0.03	$0.13	1M	—	—	—	—	0%
Qwen3.8 Flash Qwen	$0.15	$0.47	1M	—	—	—	—	0%
Qwen3.8 Max (0902)Qwen	$2	$6	1M	—	—	—	—	0%
Qwen3.8 Max Prime Qwen	$4	$12	1M	—	—	—	—	0%
Qwen3.8 Omni Flash Qwen	$0.15	$0.47	1M	—	—	—	—	0%

Qwen3.8 2.4T A95B Qwen

Input /1M: $2
Output /1M: $6
Context: 1M
AA Intelligence: 39.9
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

Qwen3.8 27B Qwen

Input /1M: $0.425
Output /1M: $2.55
Context: 1M
AA Intelligence: 33.7
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 203%

Qwen3.7 Max Qwen

Input /1M: $1.475
Output /1M: $4.425
Context: 1M
AA Intelligence: 29.5
DesignArena Elo: 1280
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

Qwen3.6 Max Preview Qwen

Input /1M: $1.027
Output /1M: $6.162
Context: 262K
AA Intelligence: 28.4
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

Qwen3.6 Plus Qwen

Input /1M: $0.325
Output /1M: $1.95
Context: 1M
AA Intelligence: 27
DesignArena Elo: 1239
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

Qwen3.7 Plus Qwen

Input /1M: $0.32
Output /1M: $1.28
Context: 1M
AA Intelligence: 25.2
DesignArena Elo: 1272
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

Qwen3.5-27B Qwen

Input /1M: $0.26
Output /1M: $2.6
Context: 262K
AA Intelligence: 22.9
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 479%

Qwen3.6 27B Qwen

Input /1M: $0.45
Output /1M: $2.7
Context: 262K
AA Intelligence: 21.4
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 322%

Qwen3 Max Thinking Qwen

Input /1M: $0.78
Output /1M: $3.9
Context: 262K
AA Intelligence: 21.3
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

Qwen3.5-35B-A3B Qwen

Input /1M: $0.15
Output /1M: $1
Context: 262K
AA Intelligence: 19.3
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 55%

Qwen3.5 397B A17B Qwen

Input /1M: $0.45
Output /1M: $3
Context: 262K
AA Intelligence: 18.4
DesignArena Elo: 1183
Arena Elo: —
MMLU-Pro: —
30d trend: 163%

Qwen3.6 35B A3B Qwen

Input /1M: $0.15
Output /1M: $1
Context: 262K
AA Intelligence: 18.2
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

Qwen3 Max Qwen

Input /1M: $0.78
Output /1M: $3.9
Context: 262K
AA Intelligence: 15.6
DesignArena Elo: 1113
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

Qwen3.5-122B-A10B Qwen

Input /1M: $0.26
Output /1M: $2.08
Context: 262K
AA Intelligence: 15.6
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

Qwen3.5-9B Qwen

Input /1M: $0.1
Output /1M: $0.15
Context: 262K
AA Intelligence: 11.2
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

Showing 15 of 53

15 of 53 models

Qwen input vs output prices

USD per 1M tokens for each model.

15 of 53 models

Qwen3.8 2.4T A95B: $2 input, $6 output per million tokens.
Qwen3.8 27B: $0.425 input, $2.55 output per million tokens.
Qwen3.7 Max: $1.475 input, $4.425 output per million tokens.
Qwen3.6 Max Preview: $1.027 input, $6.162 output per million tokens.
Qwen3.6 Plus: $0.325 input, $1.95 output per million tokens.
Qwen3.7 Plus: $0.32 input, $1.28 output per million tokens.
Qwen3.5-27B: $0.26 input, $2.6 output per million tokens.
Qwen3.6 27B: $0.45 input, $2.7 output per million tokens.
Qwen3 Max Thinking: $0.78 input, $3.9 output per million tokens.
Qwen3.5-35B-A3B: $0.15 input, $1 output per million tokens.
Qwen3.5 397B A17B: $0.45 input, $3 output per million tokens.
Qwen3.6 35B A3B: $0.15 input, $1 output per million tokens.
Qwen3 Max: $0.78 input, $3.9 output per million tokens.
Qwen3.5-122B-A10B: $0.26 input, $2.08 output per million tokens.
Qwen3.5-9B: $0.1 input, $0.15 output per million tokens.
Qwen3 VL 235B A22B Instruct: $0.21 input, $1.9 output per million tokens.
Qwen3 Coder 30B A3B Instruct: $0.07 input, $0.28 output per million tokens.
Qwen3 Next 80B A3B Instruct: $0.15 input, $1.5 output per million tokens.
Qwen3 Coder Next: $0.12 input, $0.8 output per million tokens.
Qwen3 VL 32B Instruct: $0.104 input, $0.416 output per million tokens.
Qwen3 VL 30B A3B Instruct: $0.15 input, $0.6 output per million tokens.
Qwen3 30B A3B Instruct 2507: $0.1 input, $0.3 output per million tokens.
Qwen3 VL 8B Instruct: $0.117 input, $0.455 output per million tokens.
Qwen Plus 0728: $0.26 input, $0.78 output per million tokens.
Qwen-Plus: $0.26 input, $0.78 output per million tokens.
Qwen2.5 72B Instruct: $0.36 input, $0.4 output per million tokens.
Qwen2.5 7B Instruct: $0.1 input, $0.2 output per million tokens.
Qwen2.5 Coder 32B Instruct: $0.66 input, $1 output per million tokens.
Qwen2.5 VL 72B Instruct: $0.8 input, $1 output per million tokens.
Qwen3 14B: $0.12 input, $0.24 output per million tokens.
Qwen3 235B A22B: $0.455 input, $1.82 output per million tokens.
Qwen3 235B A22B Instruct 2507: $0.09 input, $0.55 output per million tokens.
Qwen3 235B A22B Thinking 2507: $0.23 input, $2.3 output per million tokens.
Qwen3 30B A3B: $0.12 input, $0.5 output per million tokens.
Qwen3 30B A3B Thinking 2507: $0.2 input, $2.4 output per million tokens.
Qwen3 32B: $0.08 input, $0.28 output per million tokens.
Qwen3 8B: $0.117 input, $0.455 output per million tokens.
Qwen3 Coder 480B A35B: $0.3 input, $1 output per million tokens.
Qwen3 Coder Flash: $0.195 input, $0.975 output per million tokens.
Qwen3 Coder Plus: $0.65 input, $3.25 output per million tokens.
Qwen3 Next 80B A3B Thinking: $0.15 input, $1.2 output per million tokens.
Qwen3 VL 235B A22B Thinking: $0.4 input, $4 output per million tokens.
Qwen3 VL 30B A3B Thinking: $0.2 input, $2.4 output per million tokens.
Qwen3 VL 8B Thinking: $0.18 input, $2.1 output per million tokens.
Qwen3.5 Plus 2026-02-15: $0.26 input, $1.56 output per million tokens.
Qwen3.5 Plus 2026-04-20: $0.3 input, $1.8 output per million tokens.
Qwen3.5-Flash: $0.065 input, $0.26 output per million tokens.
Qwen3.6 Flash: $0.1875 input, $1.125 output per million tokens.
Qwen3.7 Flash: $0.03 input, $0.13 output per million tokens.
Qwen3.8 Flash: $0.15 input, $0.47 output per million tokens.
Qwen3.8 Max (0902): $2 input, $6 output per million tokens.
Qwen3.8 Max Prime: $4 input, $12 output per million tokens.
Qwen3.8 Omni Flash: $0.15 input, $0.47 output per million tokens.

Qwen price history

Blended price per 1M tokens over the last 6 months.

By use case

Qwen models by category

Text & Reasoning

53 models · cheapest

Qwen3.7 Flash

$0.06 blended / 1M

Vision

27 models · cheapest

Qwen3.7 Flash

$0.06 blended / 1M

Code & SLMs

6 models · cheapest

Qwen3 Coder 30B A3B Instruct

$0.12 blended / 1M

Comparisons

Qwen vs other AI providers

Compare Qwen3.8 2.4T A95B with models from other AI providers, including pricing and benchmark results.

Qwen vs Google

Qwen3.8 2.4T A95B vs Nano Banana Pro (Gemini 3 Pro Image)

$3.00 vs $4.50 · Arena Elo — vs 1211

Qwen vs Anthropic

Qwen3.8 2.4T A95B vs Claude Opus 5.5

$3.00 vs $8.00 · Arena Elo — vs —

Qwen vs OpenAI

Qwen3.8 2.4T A95B vs GPT-5.2 Pro

$3.00 vs $58 · Arena Elo — vs 1255

Qwen vs xAI

Qwen3.8 2.4T A95B vs Grok 4.7

$3.00 vs $3.00 · Arena Elo — vs —

Qwen vs Meta

Qwen3.8 2.4T A95B vs Muse Spark 1.3

$3.00 vs $2.00 · Arena Elo — vs —

Qwen vs DeepSeek

Qwen3.8 2.4T A95B vs DeepSeek V4.1 Flash

$3.00 vs $0.34 · Arena Elo — vs —

FAQ

Qwen pricing FAQ

Tracked active Qwen models range from $0.03 to $4.00 per million input tokens. Output rates are listed separately for each model. Prices vary by model and API endpoint; these are token rates, not a subscription quote.