Gmi API pricing
Hosted16 language models
As of Oct 14, 2026, Gmi lists 16 language models through its API. Its cheapest language model is DeepSeek V3.2 at $0.28 input / $0.40 output per million tokens.
Language models (16)
Prices per million tokens.
gmi/anthropic/claude-opus-4
- Input
- $15.00
- Output
- $75.00
- Context
- 410K
gmi/anthropic/claude-opus-4.5
- Input
- $5.00
- Output
- $25.00
- Context
- 410K
gmi/anthropic/claude-sonnet-4
- Input
- $3.00
- Output
- $15.00
- Context
- 410K
gmi/anthropic/claude-sonnet-4.5
- Input
- $3.00
- Output
- $15.00
- Context
- 410K
gmi/deepseek-ai/DeepSeek-V3-0324
- Input
- $0.28
- Output
- $0.88
- Context
- 164K
gmi/deepseek-ai/DeepSeek-V3.2
- Input
- $0.28
- Output
- $0.40
- Context
- 164K
gmi/google/gemini-3-flash-preview
- Input
- $0.50
- Output
- $3.00
- Context
- 1.05M
gmi/openai/gpt-4o
- Input
- $2.50
- Output
- $10.00
- Context
- 131K
gmi/openai/gpt-4o-mini
- Input
- $0.15
- Output
- $0.60
- Context
- 131K
gmi/openai/gpt-5
- Input
- $1.25
- Output
- $10.00
- Context
- 410K
gmi/openai/gpt-5.1
- Input
- $1.25
- Output
- $10.00
- Context
- 410K
gmi/openai/gpt-5.2
- Input
- $1.75
- Output
- $14.00
- Context
- 410K
gmi/moonshotai/Kimi-K2-Thinking
- Input
- $0.80
- Output
- $1.20
- Context
- 262K
gmi/MiniMaxAI/MiniMax-M2.1
- Input
- $0.30
- Output
- $1.20
- Context
- 197K
GLM 4.7 Fp8
gmi/zai-org/GLM-4.7-FP8
- Input
- $0.40
- Output
- $2.00
- Context
- 203K
Qwen3 VL 235B A22B Instruct Fp8
gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8
- Input
- $0.30
- Output
- $1.40
- Context
- 262K
Prices in USD from LiteLLM and models.dev, checked daily; confirm on Gmi's pricing page before you rely on a number.