Vercel AI Gateway — 模型目录与真实网关流量排行榜

Vercel AI Gateway

模型目录 · 能力/定价/性能对比 + 真实网关流量排行

目录 369 个模型 · 更新于 2026-09-03
Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
gemini-3.8-flash
google· 2026-09-02
1M 2.9 s 388 tps $0.75 $3.75 $0.07 $14.00
+3
glm-5.3-fast
zai· 2026-09-02
1.0M 713 ms 150 tps $2.10 $6.60 $0.21
qwen3.8-max-0902
alibaba· 2026-09-01
991K 1.2 s 56 tps $2.00 $6.00 $0.25
+1
claude-fable-5.1
anthropic· 2026-08-31
1M 1.4 s 80 tps $10.00 $50.00 $0.25 $10.00
+1
wan-v3.0-video-prime
alibaba· 2026-08-28
hy4-preview
tencent· 2026-08-28
1.0M 5.6 s 62 tps $0.83 $2.50 $0.04
ling-3.0-flash-fin
inclusionai· 2026-08-27
256K 559 ms 119 tps $0.00 $0.00
ling-3.0-flash-fin-free
inclusionai· 2026-08-27
256K $0.00 $0.00
minimax-h3-max
minimax· 2026-08-27
qwen3.8-flash
alibaba· 2026-08-26
991K 4.7 s 86 tps $0.16 $0.47 $0.02
+1
qwen3.8-flash-next
alibaba· 2026-08-26
1.0M $0.12 $0.40 $0.01
gemini-3.5-transcribe
google· 2026-08-26
$2.00 $12.00
gemini-3.5-transcribe-live
google· 2026-08-26
$0.00
muse-image-1.0
meta· 2026-08-26
glm-5.3-flash
zai· 2026-08-26
1M 572 ms 215 tps $0.15 $0.50 $0.03
wan-v3.0-video
alibaba· 2026-08-23
deepseek-v4-flash-vision-exp
deepseek· 2026-08-21
1.0M 592 ms 187 tps $0.22 $0.66 $0.01
glm-5.3
zai· 2026-08-18
1M 178 ms 343 tps $0.70 $2.20 $0.13
glm-5.3-promo-50
zai· 2026-08-18
1.0M 329 ms 191 tps $0.70 $2.20 $0.13
qwen3.8-27b
alibaba· 2026-08-14
1M 574 ms 133 tps $0.50 $3.00 $0.10
+2
gemini-3.7-flash
google· 2026-08-13
1M 2.0 s 408 tps $0.75 $3.75 $0.07 $14.00
+3
deepseek-v4-pro-0813
deepseek· 2026-08-12
1M 460 ms 140 tps $0.66 $1.98 $0.07
grok-4.6
spacexai· 2026-08-12
500K $2.00 $6.00 $0.50 $5.00
nemotron-3.5-lightning
nvidia· 2026-08-11
262K 193 ms 464 tps $0.05 $0.20 $0.01
muse-glimmer-30b
meta· 2026-08-10
131K 190 ms 107 tps $0.35 $1.50 $0.04
seedance-2.5
bytedance· 2026-08-07
grok-imagine-image-2.0
spacexai· 2026-08-07
ling-3.0-flash
inclusionai· 2026-08-06
256K 972 ms 271 tps $0.06 $0.18 $0.01
muse-spark-1.2
meta· 2026-08-05
1.0M 3.8 s 123 tps $1.25 $4.25 $0.15
+1
muse-spark-1.2-contributor
meta· 2026-08-05
1.0M 4.2 s 153 tps $0.10 $0.20 $0.00
+1
flux-3-video
bfl· 2026-08-04
namazu
sakana· 2026-08-03
256K 668 ms 153 tps $0.95 $4.00 $0.15
+3
qwen3.8-2.4t-a95b
alibaba· 2026-08-02
262K 390 ms 100 tps $2.00 $6.00 $0.25
qwen3.8-max
alibaba· 2026-08-02
1M 911 ms 117 tps $2.00 $6.00 $0.25
minimax-h3
minimax· 2026-07-30
inkling-small
thinkingmachines· 2026-07-30
1M 256 ms 302 tps $0.50 $1.20 $0.10
+1
grok-voice-think-fast-2.0
spacexai· 2026-07-29
qwen3.7-flash
alibaba· 2026-07-28
991K 1.4 s 135 tps $0.03 $0.13 $0.01
+1
s2.1-pro
fish-audio· 2026-07-28
s2.1-pro-free
fish-audio· 2026-07-28
kimi-k3-fast
moonshotai· 2026-07-27
1M 1.3 s 101 tps $4.50 $22.50 $0.45
+1
claude-opus-5
anthropic· 2026-07-24
1M 4.7 s 90 tps $5.00 $25.00 $0.50 $10.00
+3
claude-opus-5-fast
anthropic· 2026-07-24
1M 3.7 s 262 tps $10.00 $50.00 $1.00 $10.00
+3
gemini-3.5-flash-lite
google· 2026-07-21
1M 538 ms 430 tps $0.30 $2.50 $0.03 $14.00
+3
gemini-3.6-flash
google· 2026-07-21
1M 1.8 s 156 tps $0.75 $3.75 $0.07 $14.00
+3
laguna-s-2.1-free
poolside· 2026-07-21
256K 1.1 s 62 tps $0.00 $0.00
laguna-s-2.1
poolside· 2026-07-20
1M 836 ms 107 tps $0.10 $0.20 $0.01
kimi-k3
moonshotai· 2026-07-16
1M 386 ms 402 tps $3.00 $15.00 $0.30
+2
inkling
thinkingmachines· 2026-07-15
256K 138 ms 210 tps $1.00 $4.05 $0.17
seedream-5.0-pro
bytedance· 2026-07-11
$0.00
kat-coder-air-v2.5
kwaipilot· 2026-07-10
256K $0.15 $0.60 $0.03
kat-coder-pro-v2.5
kwaipilot· 2026-07-10
256K $0.74 $2.96 $0.15
muse-spark-1.1
meta· 2026-07-09
1.0M 3.6 s 177 tps $1.25 $4.25 $0.15
+1
gpt-5.6-luna
openai· 2026-07-09
1.1M 1.5 s 129 tps $0.20 $1.20 $0.02 $10.00
+4
gpt-5.6-luna-fast
openai· 2026-07-09
1.1M 2.1 s 136 tps $0.40 $2.40 $0.04 $10.00
+4
gpt-5.6-sol
openai· 2026-07-09
1.1M 3.9 s 84 tps $2.00 $10.00 $0.20 $10.00
+4
gpt-5.6-sol-fast
openai· 2026-07-09
1.1M 2.9 s 37 tps $4.00 $20.00 $0.40 $10.00
+4
gpt-5.6-terra
openai· 2026-07-09
1.1M 1.7 s 108 tps $2.00 $12.00 $0.20 $10.00
+4
gpt-5.6-terra-fast
openai· 2026-07-09
1.1M 4.0 s 66 tps $4.00 $24.00 $0.40 $10.00
+4
gpt-realtime-2.1
openai· 2026-07-09
128K $4.00 $24.00 $0.40 $10.00
共 369 个模型 · 第 1 / 7 页
口径:Latency=p50 首字延迟 · Throughput=p50 吞吐 · 价格均为每百万 token($/M)· 数据来源 vercel.com/ai-gateway · 每 2h 同步