Name: Qwen: Qwen3 235B A22B Thinking 2507 API
Brand: Qwen
SKU: qwen/qwen3-235b-a22b-thinking-2507

Best price — Output ($/1M tokens)

Markets

One row per access path (venue → underlying provider). Prices are each venue's published list price; performance is measured by Artificial Analysis. Your actual bill may vary by routing settings, fallbacks, region / ZDR, long-context tiers, and request features (JSON mode, tools, vision).

#	Provider	Class	Input $/M	Output $/M	Cache ($/M Read)	vs consensus	TTFT	Throughput	Uptime 24h	Requests 24h
1	deepinfra → qwen	Reseller	$0.23	$2.3	—	-29.2% vs consensus	—	—	—	—
2	novita → qwen	Reseller	$0.3	$3	—	-7.7% vs consensus	—	—	—	—
3	openrouter → qwen	Reseller	$0.45	$3.5	—	+7.7% vs consensus	—	—	—	—
4	openrouter → venice	Reseller	$0.45	$3.5	—	+7.7% vs consensus	—	—	—	—
5	coreweave Disabled by coreweave · stale	Direct host	$0.1	$0.1	—	-96.9% vs consensus	1.1s reasoning 1.2s	91.5 tps	—	—
6	openrouter → wandb Disabled by openrouter · disabled · bf16	Reseller	$0.1	$0.1	$0.1	-96.9% vs consensus	—	—	—	—
7	wandb → qwen Disabled by wandb · stale	Reseller	$0.1	$0.1	—	-96.9% vs consensus	—	—	—	—
8	eigenai Disabled by eigenai · stale	Direct host	$0.5	$2	—	-38.5% vs consensus	1.0s	167.7 tps	—	—
9	nebius Disabled by nebius · stale	Direct host	$0.5	$2	—	-38.5% vs consensus	2.0s	154.9 tps	—	—
10	alibaba-cloud Disabled by alibaba-cloud · stale	Official	$0.23	$2.3	—	-29.2% vs consensus	2.8s reasoning 2.9s	61.7 tps	—	—
11	deepinfra Disabled by deepinfra · disabled · fp8	Direct host	$0.23	$2.3	$0.2	-29.2% vs consensus	1.1s	42.1 tps	—	—
12	openrouter → deepinfra Disabled by openrouter · disabled · fp8	Reseller	$0.23	$2.3	$0.2	-29.2% vs consensus	—	—	—	—
13	openrouter → atlas-cloud Disabled by openrouter · disabled · fp8	Reseller	$0.28	$2.3	$0.28	-29.2% vs consensus	—	—	—	—
14	novita Disabled by novita · stale	Direct host	$0.3	$3	—	-7.7% vs consensus	2.2s reasoning 2.2s	81.0 tps	—	—
15	openrouter → novita Disabled by openrouter · disabled · fp8	Reseller	$0.3	$3	—	-7.7% vs consensus	—	—	—	—
16	together → qwen Disabled by together · stale	Reseller	$0.65	$3	—	-7.7% vs consensus	—	—	—	—

#
1
Provider
deepinfra → qwen
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.23
Output $ / 1M tokens
$2.3
Cache read $ / 1M tokens
—
-29.2% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
2
Provider
novita → qwen
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.3
Output $ / 1M tokens
$3
Cache read $ / 1M tokens
—
-7.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
3
Provider
openrouter → qwen
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.45
Output $ / 1M tokens
$3.5
Cache read $ / 1M tokens
—
+7.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
4
Provider
openrouter → venice
Class
Reseller
$ / 1M tokens
Input $ / 1M tokens
$0.45
Output $ / 1M tokens
$3.5
Cache read $ / 1M tokens
—
+7.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
5
Provider
coreweave
Class
Direct host
Disabled by coreweave · stale
$ / 1M tokens
Input $ / 1M tokens
$0.1
Output $ / 1M tokens
$0.1
Cache read $ / 1M tokens
—
-96.9% vs consensus
TTFT
1.1s
reasoning 1.2s
Throughput
91.5 tps
Uptime 24h
—
Requests 24h
—
#
6
Provider
openrouter → wandb
Class
Reseller
Disabled by openrouter · disabled · bf16
$ / 1M tokens
Input $ / 1M tokens
$0.1
Output $ / 1M tokens
$0.1
Cache read $ / 1M tokens
$0.1
-96.9% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
7
Provider
wandb → qwen
Class
Reseller
Disabled by wandb · stale
$ / 1M tokens
Input $ / 1M tokens
$0.1
Output $ / 1M tokens
$0.1
Cache read $ / 1M tokens
—
-96.9% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
8
Provider
eigenai
Class
Direct host
Disabled by eigenai · stale
$ / 1M tokens
Input $ / 1M tokens
$0.5
Output $ / 1M tokens
$2
Cache read $ / 1M tokens
—
-38.5% vs consensus
TTFT
1.0s
Throughput
167.7 tps
Uptime 24h
—
Requests 24h
—
#
9
Provider
nebius
Class
Direct host
Disabled by nebius · stale
$ / 1M tokens
Input $ / 1M tokens
$0.5
Output $ / 1M tokens
$2
Cache read $ / 1M tokens
—
-38.5% vs consensus
TTFT
2.0s
Throughput
154.9 tps
Uptime 24h
—
Requests 24h
—
#
10
Provider
alibaba-cloud
Class
Official
Disabled by alibaba-cloud · stale
$ / 1M tokens
Input $ / 1M tokens
$0.23
Output $ / 1M tokens
$2.3
Cache read $ / 1M tokens
—
-29.2% vs consensus
TTFT
2.8s
reasoning 2.9s
Throughput
61.7 tps
Uptime 24h
—
Requests 24h
—
#
11
Provider
deepinfra
Class
Direct host
Disabled by deepinfra · disabled · fp8
$ / 1M tokens
Input $ / 1M tokens
$0.23
Output $ / 1M tokens
$2.3
Cache read $ / 1M tokens
$0.2
-29.2% vs consensus
TTFT
1.1s
Throughput
42.1 tps
Uptime 24h
—
Requests 24h
—
#
12
Provider
openrouter → deepinfra
Class
Reseller
Disabled by openrouter · disabled · fp8
$ / 1M tokens
Input $ / 1M tokens
$0.23
Output $ / 1M tokens
$2.3
Cache read $ / 1M tokens
$0.2
-29.2% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
13
Provider
openrouter → atlas-cloud
Class
Reseller
Disabled by openrouter · disabled · fp8
$ / 1M tokens
Input $ / 1M tokens
$0.28
Output $ / 1M tokens
$2.3
Cache read $ / 1M tokens
$0.28
-29.2% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
14
Provider
novita
Class
Direct host
Disabled by novita · stale
$ / 1M tokens
Input $ / 1M tokens
$0.3
Output $ / 1M tokens
$3
Cache read $ / 1M tokens
—
-7.7% vs consensus
TTFT
2.2s
reasoning 2.2s
Throughput
81.0 tps
Uptime 24h
—
Requests 24h
—
#
15
Provider
openrouter → novita
Class
Reseller
Disabled by openrouter · disabled · fp8
$ / 1M tokens
Input $ / 1M tokens
$0.3
Output $ / 1M tokens
$3
Cache read $ / 1M tokens
—
-7.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—
#
16
Provider
together → qwen
Class
Reseller
Disabled by together · stale
$ / 1M tokens
Input $ / 1M tokens
$0.65
Output $ / 1M tokens
$3
Cache read $ / 1M tokens
—
-7.7% vs consensus
TTFT
—
Throughput
—
Uptime 24h
—
Requests 24h
—

Source ecosystem

Loading…

Qwen: Qwen3 235B A22B Thinking 2507Reasoning

Best price — Output ($/1M tokens)

Best price — Output ($/1M tokens)

Markets