Gmi LLM API pricing
Every model Gmi serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.
Models served
17
on this provider
Cheapest input
$0.15
per 1M tokens
Cheapest output
$0.40
per 1M tokens
Max context
1M
tokens
| Model ID | |||||
|---|---|---|---|---|---|
| GPT-4o-mini | OpenAI | 131K | $0.15 | $0.60 | gmi/openai/gpt-4o-mini |
| DeepSeek V3.2 | DeepSeek | 164K | $0.28 | $0.40 | gmi/deepseek-ai/DeepSeek-V3.2 |
| DeepSeek V3 0324 | DeepSeek | 164K | $0.28 | $0.88 | gmi/deepseek-ai/DeepSeek-V3-0324 |
| MiniMax M2.1 | MiniMax | 1M | $0.30 | $1.20 | gmi/MiniMaxAI/MiniMax-M2.1 |
| Qwen3 VL 235B A22b Instruct FP8 | Alibaba | 262K | $0.30 | $1.40 | gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8 |
| GLM 4.7 FP8 | Zhipu | 203K | $0.40 | $2.00 | gmi/zai-org/GLM-4.7-FP8 |
| Gemini 3 Flash Preview | 1M | $0.50 | $3.00 | gmi/google/gemini-3-flash-preview | |
| Kimi K2 Thinking | Moonshot | 262K | $0.80 | $1.20 | gmi/moonshotai/Kimi-K2-Thinking |
| GPT-5.1 | OpenAI | 410K | $1.25 | $10.00 | gmi/openai/gpt-5.1 |
| GPT-5 | OpenAI | 410K | $1.25 | $10.00 | gmi/openai/gpt-5 |
| GPT-5.2 | OpenAI | 410K | $1.75 | $14.00 | gmi/openai/gpt-5.2 |
| Gemini 3 Pro Preview | 1M | $2.00 | $12.00 | gmi/google/gemini-3-pro-preview | |
| GPT-4o | OpenAI | 131K | $2.50 | $10.00 | gmi/openai/gpt-4o |
| Claude Sonnet 4.5 | Anthropic | 1M | $3.00 | $15.00 | gmi/anthropic/claude-sonnet-4.5 |
| Claude Sonnet 4 | Anthropic | 1M | $3.00 | $15.00 | gmi/anthropic/claude-sonnet-4 |
| Claude Opus 4.5 | Anthropic | 410K | $5.00 | $25.00 | gmi/anthropic/claude-opus-4.5 |
| Claude Opus 4 | Anthropic | 410K | $15.00 | $75.00 | gmi/anthropic/claude-opus-4 |
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI