Back to AI Developer ToolsHistorical Trend Charts

Track AI route trends over time

Review a focused chart set for tracked models across latency, uptime, throughput, and token price signals.

Tracked models

273

Featured charts

Samples

752

Latest update

May 20, 12:07 PM

Featured trend set

Showing 24 of 24 charted models from 273 tracked models.

Qwen3-14B

alibaba/qwen-3-14b

1 providers

Latency

270ms

Uptime

100%

Throughput

39 tok/s

Price

$0.36

Latency p50

1 lines

Model detail Routes

Qwen3 235B A22b Instruct 2507

alibaba/qwen-3-235b

4 providers

Latency

104ms

Uptime

100%

Throughput

72 tok/s

Price

$0.534

Latency p50

4 lines

Model detail Routes

Qwen3-30B-A3B

alibaba/qwen-3-30b

1 providers

Latency

233ms

Uptime

100%

Throughput

55 tok/s

Price

$0.37

Latency p50

1 lines

Model detail Routes

Qwen 3 32B

alibaba/qwen-3-32b

4 providers

Latency

245ms

Uptime

100%

Throughput

285 tok/s

Price

$0.40

Latency p50

4 lines

Model detail Routes

Qwen 3.6 Max Preview

alibaba/qwen-3.6-max-preview

1 providers

Latency

2.84s

Uptime

100%

Throughput

80 tok/s

Price

$9.10

Latency p50

1 lines

Model detail Routes

Qwen3 VL 235B A22B Thinking

alibaba/qwen3-235b-a22b-thinking

3 providers

Latency

279ms

Uptime

100%

Throughput

88 tok/s

Price

$2.53

Latency p50

3 lines

Model detail Routes

Qwen3 Coder 480B A35B Instruct

alibaba/qwen3-coder

4 providers

Latency

398ms

Uptime

100%

Throughput

95 tok/s

Price

$2.00

Latency p50

4 lines

Model detail Routes

Qwen 3 Coder 30B A3B Instruct

alibaba/qwen3-coder-30b-a3b

2 providers

Latency

161ms

Uptime

100%

Throughput

116 tok/s

Price

$0.34

Latency p50

2 lines

Model detail Routes

Qwen3 Coder Next

alibaba/qwen3-coder-next

2 providers

Latency

2.35s

Uptime

68.75%

Throughput

27.5 tok/s

Price

$1.70

Latency p50

1 lines

Model detail Routes

Qwen3 Coder Plus

alibaba/qwen3-coder-plus

1 providers

Latency

1.05s

Uptime

100%

Throughput

51 tok/s

Price

$6.00

Latency p50

1 lines

Model detail Routes

Qwen3 Embedding 0.6B

alibaba/qwen3-embedding-0.6b

1 providers

Latency

Uptime

100%

Throughput

Price

$0.01

Latency p50

0 lines

Need at least two samples.

Model detail Routes

Qwen3 Embedding 4B

alibaba/qwen3-embedding-4b

1 providers

Latency

Uptime

100%

Throughput

Price

$0.02

Latency p50

0 lines

Need at least two samples.

Model detail Routes

Qwen3 Embedding 8B

alibaba/qwen3-embedding-8b

1 providers

Latency

Uptime

100%

Throughput

Price

$0.05

Latency p50

0 lines

Need at least two samples.

Model detail Routes

Qwen3 Max

alibaba/qwen3-max

2 providers

Latency

1.15s

Uptime

100%

Throughput

34 tok/s

Price

$4.23

Latency p50

2 lines

Model detail Routes

Qwen3 Max Preview

alibaba/qwen3-max-preview

1 providers

Latency

1.62s

Uptime

100%

Throughput

44 tok/s

Price

$7.20

Latency p50

1 lines

Model detail Routes

Qwen 3 Max Thinking

alibaba/qwen3-max-thinking

1 providers

Latency

1.26s

Uptime

100%

Throughput

34 tok/s

Price

$7.20

Latency p50

1 lines

Model detail Routes

Qwen3 Next 80B A3B Instruct

alibaba/qwen3-next-80b-a3b-instruct

4 providers

Latency

315ms

Uptime

100%

Throughput

139 tok/s

Price

$1.19

Latency p50

4 lines

Model detail Routes

Qwen3 Next 80B A3B Thinking

alibaba/qwen3-next-80b-a3b-thinking

3 providers

Latency

312ms

Uptime

100%

Throughput

436 tok/s

Price

$1.35

Latency p50

3 lines

Model detail Routes

Qwen3 VL 235B A22B Instruct

alibaba/qwen3-vl-235b-a22b-instruct

2 providers

Latency

428ms

Uptime

100%

Throughput

52 tok/s

Price

$1.08

Latency p50

2 lines

Model detail Routes

Qwen3 VL 235B A22B Instruct

alibaba/qwen3-vl-instruct

3 providers

Latency

561ms

Uptime

100%

Throughput

53.5 tok/s

Price

$1.08

Latency p50

3 lines

Model detail Routes

Qwen3 VL 235B A22B Thinking

alibaba/qwen3-vl-thinking

2 providers

Latency

1.07s

Uptime

100%

Throughput

91.5 tok/s

Price

$4.40

Latency p50

2 lines

Model detail Routes

Qwen 3.5 Flash

alibaba/qwen3.5-flash

1 providers

Latency

994ms

Uptime

100%

Throughput

250 tok/s

Price

$0.50

Latency p50

1 lines

Model detail Routes

Qwen 3.5 Plus

alibaba/qwen3.5-plus

1 providers

Latency

1.47s

Uptime

100%

Throughput

110 tok/s

Price

$2.80

Latency p50

1 lines

Model detail Routes

Qwen 3.6 27B

alibaba/qwen3.6-27b

1 providers

Latency

1.15s

Uptime

100%

Throughput

145 tok/s

Price

$4.20

Latency p50

1 lines

Model detail Routes

Related AI tools

Continue the model decision workflow

AI Model Explorer

Browse model pricing, context, providers, and capabilities.

AI Model Comparison

Compare shortlisted models side by side.

LLM Route Finder

Rank provider routes by latency, uptime, throughput, and price.

AI Cost Calculator

Estimate monthly API spend from token usage.

FAQ

AI Model Trend Charts FAQ

Answers for route trend data, latency movement, uptime history, and monitoring caveats.

What are AI model trend charts?

AI model trend charts show how route signals such as latency, uptime, throughput, and token price change across collected endpoint snapshots.

How can trend charts help with model routing?

Trend charts help identify whether a provider route is consistently fast and reliable or only looks good in the latest snapshot.

Why do AI latency trends change over time?

Latency can change because of provider capacity, region, routing infrastructure, model updates, traffic patterns, or measurement conditions.

Should trend data replace live monitoring?

No. Trend data is useful for planning and comparison, but production systems should still use live monitoring, alerts, and fallback routing.