Access
- API base URL
- https://api.gmi-serving.com/v1
- SDK
- @ai-sdk/openai-compatible
- Environment variables
- GMICLOUD_API_KEY
Protocols
Openai chat
Organizations
| Organization | Families | Models |
|---|---|---|
| Anthropic | 1 | 4 |
| Moonshot AI | 1 | 2 |
| OpenAI | 1 | 1 |
Models
7 of 7 model versions
| Model | Organization | Family | Provider model ID | Context | Max output | Input | Output | Reasoning | Tool call | Structured | Temperature | Weights | Pricing | Released | Updated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Kimi K2.7 Code Highspeed moonshotai/kimi/k2-7-code-highspeed | Moonshot AI | Kimi | moonshotai/kimi-k2.7-code-highspeed Openai chat · Streaming | 262K | 262K | TextImageVideo | Text | Yes | Yes | Yes | -No | Open weight | input $1.9/M · cache read $0.38/M output $8/M | 2026-06-12 | 2026-06-12 | |
| Claude Opus 4.8 anthropic/claude/opus-4-8 | Anthropic | Claude | anthropic/claude-opus-4.8 Openai chat · Streaming | 1M | 128K | TextImageDocument | Text | Yes | Yes | -No | -No | Closed | input $5/M · cache read $0.5/M output $25/M | 2026-05-28 | 2026-06-11 | |
| GPT-5.5 openai/gpt/5-5 | OpenAI | GPT | openai/gpt-5.5 Openai chat · Streaming | 1.1M | 128K | TextImageDocument | Text | Yes | Yes | Yes | -No | Closed | input $5/M · cache read $0.5/M output $30/M | 2026-04-23 | 2026-04-24 | |
| Kimi K2.6 moonshotai/kimi/k2-6 | Moonshot AI | Kimi | moonshotai/Kimi-K2.6 Openai chat · Streaming | 262K | 262K | TextImageVideo | Text | Yes | Yes | Yes | Yes | Open weight | input $0.855/M · cache read $0.144/M output $3.6/M | 2026-04-21 | 2026-07-22 | |
| Claude Opus 4.7 anthropic/claude/opus-4-7 | Anthropic | Claude | anthropic/claude-opus-4.7 Openai chat · Streaming | 1M | 128K | TextImageDocument | Text | Yes | Yes | -No | -No | Closed | input $4.5/M · cache read $0.45/M output $22.5/M | 2026-04-16 | 2026-06-11 | |
| Claude Sonnet 4.6 anthropic/claude/sonnet-4-6 | Anthropic | Claude | anthropic/claude-sonnet-4.6 Openai chat · Streaming | 1M | 64K | TextImageDocument | Text | Yes | Yes | -No | Yes | Closed | input $3/M · cache read $0.3/M output $15/M | 2026-02-17 | 2026-06-11 | |
| Claude Opus 4.6 anthropic/claude/opus-4-6 | Anthropic | Claude | anthropic/claude-opus-4.6 Openai chat · Streaming | 1M | 128K | TextImageDocument | Text | Yes | Yes | -No | Yes | Closed | input $5/M · cache read $0.5/M output $25/M | 2026-02-05 | 2026-07-17 |