| gigachat/GigaChat-2-Max | gigachat | 128,000 | |
| gigachat/GigaChat-2-Pro | gigachat | 128,000 | |
| gigachat/Embeddings | gigachat | 512 | |
| gigachat/Embeddings-2 | gigachat | 512 | |
| gigachat/EmbeddingsGigaR | gigachat | 4,096 | |
| gigachat/GigaEmbeddings-3B-2025-09 | gigachat | 4,096 | |
| gmi/anthropic/claude-opus-4.5 | gmi | 409,600 | |
| gmi/anthropic/claude-sonnet-4.5 | gmi | 409,600 | |
| gmi/anthropic/claude-sonnet-4 | gmi | 409,600 | |
| gmi/anthropic/claude-opus-4 | gmi | 409,600 | |
| gmi/openai/gpt-5.2 | gmi | 409,600 | |
| gmi/openai/gpt-5.1 | gmi | 409,600 | |
| gmi/openai/gpt-5 | gmi | 409,600 | |
| gmi/openai/gpt-4o | gmi | 131,072 | |
| gmi/openai/gpt-4o-mini | gmi | 131,072 | |
| gmi/deepseek-ai/DeepSeek-V3.2 | gmi | 163,840 | |
| gmi/deepseek-ai/DeepSeek-V3-0324 | gmi | 163,840 | |
| gmi/google/gemini-3-pro-preview | gmi | 1,048,576 | |
| gmi/google/gemini-3-flash-preview | gmi | 1,048,576 | |
| gmi/moonshotai/Kimi-K2-Thinking | gmi | 262,144 | |
| gmi/MiniMaxAI/MiniMax-M2.1 | gmi | 196,608 | |
| baseten/MiniMaxAI/MiniMax-M2.5 | baseten | — | |
| baseten/nvidia/Nemotron-120B-A12B | baseten | — | |
| baseten/zai-org/GLM-5 | baseten | — | |
| baseten/zai-org/GLM-4.7 | baseten | 200,000 | - Input
- Input (cached read)
- Output
|