Gateway
Charm Hyper
Charm Hyper is a Gateway provider with 19 models across 19 offerings.
Access
- API base URL
- https://hyper.charm.land/v1
- SDK
- @ai-sdk/openai-compatible
- Environment variables
- HYPER_API_KEY
Models
19 of 19 model versions
| Model | Family | Provider model ID | Protocol | Streaming | Organization | Context | Max output | Input | Output | Reasoning | Tool call | Structured | Temperature | Weights | Price | Released | Updated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Kimi K3 moonshotai/kimi-k3 | MAMoonshot AI | Kimi | kimi-k3 | Openai chat | Yes | 1M | 131K | Yes | Yes | Yes | -No | Open | input $3.266/M · output $16.332/M cache read $0.327/M | 2026-07-16 | 2026-07-30 | |||
| GLM-5.2 zhipuai/glm-5.2 | ZAZhipu AI | GLM | glm-5.2 | Openai chat | Yes | 1M | 131K | Yes | Yes | Yes | Yes | Open | input $1.4/M · output $4.4/M cache read $0.28/M | 2026-06-13 | 2026-08-06 | |||
| Kimi K2.7 Code moonshotai/kimi-k2.7-code | MAMoonshot AI | Kimi | kimi-k2.7-code | Openai chat | Yes | 262K | 262K | Yes | Yes | Yes | -No | Open | input $0.95/M · output $4/M cache read $0.19/M | 2026-06-12 | 2026-08-06 | |||
| Qwen3.7 Plus alibaba/qwen3.7-plus | ALAlibaba | Qwen | qwen3.7-plus | Openai chat | Yes | 1M | 64K | Yes | Yes | Yes | Yes | Closed | input $1.2/M · output $4.8/M cache read $0.24/M | 2026-06-02 | 2026-07-22 | |||
| MiniMax-M3 minimax/minimax-m3 | MIMiniMax | Minimax | minimax-m3 | Openai chat | Yes | 512K | 128K | Yes | Yes | -No | Yes | Open | input $0.327/M · output $1.307/M cache read $0.064/M | 2026-06-01 | 2026-08-06 | |||
| Qwen3.7 Max alibaba/qwen3.7-max | ALAlibaba | Qwen | qwen3.7-max | Openai chat | Yes | 1M | 66K | Yes | Yes | Yes | Yes | Closed | input $2.5/M · output $7.5/M cache read $0.5/M | 2026-05-21 | 2026-07-22 | |||
| Qwen3.6 Flash alibaba/qwen3.6-flash | ALAlibaba | Qwen | qwen3.6-flash | Openai chat | Yes | 1M | 66K | Yes | Yes | Yes | Yes | Closed | input $1/M · output $4/M cache read $0.1/M · cache write $1.25/M | 2026-04-27 | 2026-07-22 | |||
| DeepSeek V4 Flash deepseek/deepseek-v4-flash | DEDeepSeek | DeepSeek | deepseek-v4-flash | Openai chat | Yes | 1M | 384K | Yes | Yes | Yes | Yes | Open | input $0.2/M · output $0.4/M cache read $0.04/M | 2026-04-24 | 2026-08-06 | |||
| DeepSeek V4 Pro deepseek/deepseek-v4-pro | DEDeepSeek | DeepSeek | deepseek-v4-pro | Openai chat | Yes | 1M | 384K | Yes | Yes | Yes | Yes | Open | input $2.4/M · output $4.8/M cache read $0.2/M | 2026-04-24 | 2026-08-06 | |||
| Kimi K2.6 moonshotai/kimi-k2.6 | MAMoonshot AI | Kimi | kimi-k2.6 | Openai chat | Yes | 262K | 262K | Yes | Yes | Yes | Yes | Open | input $0.95/M · output $4/M cache write $0.16/M | 2026-04-21 | 2026-08-06 | |||
| GLM-5.1 zhipuai/glm-5.1 | ZAZhipu AI | GLM | glm-5.1 | Openai chat | Yes | 200K | 131K | Yes | Yes | Yes | Yes | Open | input $1.524/M · output $4.791/M cache read $0.283/M | 2026-04-07 | 2026-08-06 | |||
| Gemma 4 26B A4B IT google/gemma-4-26b-a4b-it | GOGoogle | Gemma | gemma-4-26b-a4b-it | Openai chat | Yes | 262K | 33K | Yes | Yes | Yes | Yes | Open | input $0.126/M · output $0.42/M cache write $0.063/M | 2026-04-02 | 2026-08-06 | |||
| Qwen3.6 Plus alibaba/qwen3.6-plus | ALAlibaba | Qwen | qwen3.6-plus | Openai chat | Yes | 1M | 66K | Yes | Yes | Yes | Yes | Closed | input $2/M · output $6/M cache read $0.2/M · cache write $2.5/M | 2026-04-02 | 2026-07-22 | |||
| MiniMax-M2.7 minimax/minimax-m2.7 | MIMiniMax | Minimax | minimax-m2.7 | Openai chat | Yes | 205K | 131K | Yes | Yes | -No | Yes | Open | input $0.42/M · output $1.62/M cache write $0.21/M | 2026-03-18 | 2026-08-06 | |||
| GLM-5 zhipuai/glm-5 | ZAZhipu AI | GLM | glm-5 | Openai chat | Yes | 205K | 131K | Yes | Yes | Yes | Yes | Open | input $0.85/M · output $2.622/M cache write $0.425/M | 2026-02-12 | 2026-08-06 | |||
| Kimi K2.5 moonshotai/kimi-k2.5 | MAMoonshot AI | Kimi | kimi-k2.5 | Openai chat | Yes | 262K | 262K | Yes | Yes | Yes | -No | Open | input $0.54/M · output $2.85/M cache write $0.27/M | 2026-01 | 2026-08-06 | |||
| Qwen3-Next 80B-A3B Instruct alibaba/qwen3-next-80b-a3b-instruct | ALAlibaba | Qwen | qwen3-next-80b-a3b-instruct | Openai chat | Yes | 131K | 33K | -No | Yes | Yes | Yes | Open | input $0.118/M · output $1.136/M cache write $0.059/M | 2025-09 | 2026-08-06 | |||
| gpt-oss-120b openai/gpt-oss-120b | OPOpenAI | GPT | gpt-oss-120b | Openai chat | Yes | 131K | 131K | Yes | Yes | Yes | Yes | Open | input $0.188/M · output $0.7/M cache write $0.094/M | 2025-08-05 | 2026-08-06 | |||
| Llama-3.3-70B-Instruct meta/llama-3.3-70b-instruct | MEMeta | Llama | llama-3.3-70b-instruct | Openai chat | Yes | 128K | 4.1K | -No | Yes | Yes | Yes | Open | input $0.513/M · output $1.045/M cache write $0.256/M | 2024-12-06 | 2026-08-06 |