impulse

GMI Cloud

Inference
Models
116
Frontier
34
Cheaper here
17
than the headline price
Dearer here
29
than the headline price
Cheapest listing per model, USD per million tokens.
ModelHere, input / output
Kimi K2 Instruct
Moonshot AIKimi-K2-Instruct-0905
$0.57 / $2.29
+14% vs DeepInfra
Qwen3 Coder 480B A35B Instruct
Alibaba QwenQwen3-Coder-480B-A35B-Instruct-FP8
$0.90 / $4.50
+193% vs Vertex AI
DeepSeek R1 Distill Qwen 32B
DeepSeekDeepSeek-R1-Distill-Qwen-32B
$0.50 / $0.90
+300% vs Nscale
MiniMax M2
MiniMaxMiniMax-M2
$0.30 / $1.20
Qwen3 235B A22B
Alibaba QwenQwen3-235B-A22B-FP8
$0.17 / $1.09
+48% vs DeepInfra
MiniMax M2.1
MiniMaxMiniMax-M2.1
$0.30 / $1.20
DeepSeek R1 Distill Qwen 14B
DeepSeekDeepSeek-R1-Distill-Qwen-14B
$0.20 / $0.20
+186% vs Nscale
Kimi K2.7 Code Highspeed
Moonshot AIkimi-k2.7-code-highspeed
$1.90 / $8.00
DeepSeek R1 Distill Llama 8B
DeepSeekDeepSeek-R1-Distill-Llama-8B
$0.14 / $0.39
+710% vs Nscale
DeepSeek R1 Distill Qwen 7B
DeepSeekDeepSeek-R1-Distill-Qwen-7B
$0.10 / $0.20
Nvidia Nemotron 3.5 Super VL 120B A12B
NVIDIANVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
$0.10 / $0.50
DeepSeek Prover V2 671B
DeepSeekDeepSeek-Prover-V2-671B
$0.50 / $2.18
DeepSeek V3.2 Speciale
DeepSeekDeepSeek-V3.2-Speciale
$0.28 / $0.40
Nvidia Nemotron 3.5 Lightning 30B A3B
NVIDIANVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
$0.15 / $1.00
+254% vs W&B Inference
Hy4$0.417 / $1.25
Hunyuanocr
IndependentHunyuanOCR
$0.50 / $0.50
101-116 of 116