Hyper
hyper
Chat
Updated 3 minutes ago
Hyper is an AI inference platform offering low-latency access to frontier models including DeepSeek, GLM, Qwen, Kimi, and MiniMax series. Known for aggressive pricing on cached inputs and a developer-focused API.
Browse 23 LLM models available from Hyper. Compare prices and features.
Models (23)
| Organization | Model Name | Original Model | Input | Output | Free | |||
|---|---|---|---|---|---|---|---|---|
|
Z.ai | GLM-5.3-Flash |
glm-5.3-flash
|
$0.16 | $0.54 |
|
||
|
DeepSeek | DeepSeek-V4.1-Flash |
deepseek-v4.1-flash
|
$0.30 | $1.20 |
|
||
|
|
Z.ai | GLM-5.3 |
glm-5.3
|
$1.52 | $4.79 |
|
||
|
qwen | Qwen3.8 Flash |
qwen3.8-flash
|
$0.15 | $0.47 |
|
||
|
|
qwen | Qwen3.8-27B |
qwen3.8-27b
|
$0.50 | $3.00 | |||
|
Alibaba | Qwen3.8 Max |
qwen3.8-max
|
$2.00 | $6.00 |
|
||
|
Moonshot AI | Kimi K3 |
kimi-k3
|
$3.27 | $16.33 |
|
||
|
BaseTen | Inkling |
inkling
|
$1.09 | $4.41 | |||
|
|
qwen | Qwen: Qwen3.7 Flash |
qwen3.7-flash
|
$0.20 | $0.80 |
|
||
|
|
Z.ai | GLM-5.2 |
glm-5.2
|
$1.52 | $4.79 |
|
||
|
|
Moonshot AI | Kimi K2.7 Code |
kimi-k2.7-code
|
$1.03 | $4.36 | |||
|
Minimax | MiniMax M3 |
minimax-m3
|
$0.33 | $1.31 | |||
|
|
qwen | Qwen3.7 Max |
qwen3.7-max
|
$2.50 | $7.50 | |||
|
|
Alibaba | Qwen3.7-Plus |
qwen3.7-plus
|
$1.20 | $4.80 | |||
|
|
DeepSeek | DeepSeek V4 Pro 0424 |
deepseek-v4-pro
|
$2.40 | $4.80 |
|
||
|
|
DeepSeek | DeepSeek V4 Pro 0424 |
deepseek-v4-pro-0813
|
$1.44 | $4.31 |
|
||
|
|
DeepSeek | DeepSeek V4 Flash 0420 |
deepseek-v4-flash
|
$0.20 | $0.40 |
|
||
|
|
DeepSeek | DeepSeek V4 Flash 0420 |
deepseek-v4-flash-0731
|
$0.44 | $1.32 |
|
||
|
|
Minimax | MiniMax M2.7 |
minimax-m2.7
|
$0.48 | $1.85 | |||
|
Gemma 4 26B-A4B |
gemma-4-26b-a4b-it
|
$0.10 | $0.33 |
|
|||
|
OpenAI | GPT OSS 120B |
gpt-oss-120b
|
$0.18 | $0.68 |
|
||
|
|
qwen | Qwen3.8-2.4T-A95B |
qwen3.8-2.4t-a95b
|
$2.00 | $6.00 | |||
|
|
Moonshot AI | Kimi K2 Thinking |
kimi-k2-thinking
|
$0.60 | $2.50 |