Google Vertex AI
Cloud PlatformModels
74
Prompt Caching
✓
Batch Discount
✓
Tool Calling
✓
Models74
| Model | Input Price | Output Price | Cached Input | Context | Modality |
|---|---|---|---|---|---|
| Claude 3.5 Haiku (Deprecated)Claude | $0.8 | $4 | $0.08 | — | text |
| Claude 3.7 Sonnet (Deprecated)Claude | $3 | $15 | $0.3 | — | text |
| Claude 3 Haiku (Deprecated)Claude | $0.25 | $1.25 | $0.03 | — | text |
| Claude Haiku 4.5Claude | $1 | $5 | $0.1 | — | text |
| Claude Opus 4.1Claude | $15 | $75 | $1.5 | — | text |
| Claude Opus 4.5Claude | $5 | $25 | $0.5 | — | text |
| Claude Opus 4.6Claude | ≤200K$5 >200K$5 | $25 $25 | $0.5 $0.5 | — | text |
| Claude Opus 4.7Claude | ≤200K$5 >200K$5 | $25 $25 | $0.5 $0.5 | — | text |
| Claude Opus 4.8Claude | ≤200K$5 >200K$5 | $25 $25 | $0.5 $0.5 | — | text |
| Claude Opus 4 (Deprecated)Claude | $15 | $75 | $1.5 | — | text |
| Claude Sonnet 4.5Claude | ≤200K$3 >200K$6 | $15 $22.5 | $0.3 $0.6 | — | text |
| Claude Sonnet 4.6Claude | ≤200K$3 >200K$3 | $15 $15 | $0.3 $0.3 | — | text |
| Claude Sonnet 4 (Deprecated)Claude | $3 | $15 | $0.3 | — | text |
| Codestral 2Mistral | $0.3 | $0.9 | — | — | text |
| DeepSeek-OCRDeepSeek | $0.3 | $1.2 | — | — | text |
| DeepSeek-R1 (0528)DeepSeek | $1.35 | $5.4 | — | — | text |
| DeepSeek-V3.1DeepSeek | $0.6 | $1.7 | $0.06 | — | text |
| DeepSeek-V3.2DeepSeek | $0.56 | $1.68 | $0.056 | — | text |
| Embeddings for TextEmbeddings | $0.025/1M chars | — | — | — | embedding |
| Gemini 2.0 FlashGemini | $0.15 | $0.6 | — | — | text |
| Gemini 2.0 Flash Image GenerationGemini | $3 | $0.6 | — | — | text |
| Gemini 2.0 Flash LiteGemini | $0.075 | $0.3 | — | — | text |
| Gemini 2.0 Flash Live APIGemini | $3 | $2 | — | — | text |
| Gemini 2.5 FlashGemini | ≤200K$0.3 >200K$0.3 | $2.5 $2.5 | $0.03 $0.03 | — | text |
| Gemini 2.5 Flash ImageGemini | $0.3 | $2.5 | — | — | text |
| Gemini 2.5 Flash LiteGemini | ≤200K$0.1 >200K$0.1 | $0.4 $0.4 | $0.01 $0.01 | — | text |
| Gemini 2.5 Flash Live APIGemini | ≤200K$3 >200K$3 | $2 $2 | — | — | text |
| Gemini 2.5 ProGemini | ≤200K$1.25 >200K$2.5 | $10 $15 | $0.13 $0.25 | — | text |
| Gemini 2.5 Pro Computer Use-PreviewGemini | ≤200K$1.25 >200K$2.5 | $10 $15 | — | — | text |
| Gemini 3.1 Flash ImageGemini | $0.5 | $3 | — | — | text |
| Gemini 3.1 Flash-LiteGemini | ≤200K$0.25 >200K$0.25 | $1.5 $1.5 | $0.025 $0.025 | — | text |
| Gemini 3.1 ProGemini | ≤200K$2 >200K$4 | $12 $18 | $0.2 $0.4 | — | text |
| Gemini 3.5 FlashGemini | ≤200K$1.5 >200K$1.5 | $9 $9 | $0.15 $0.15 | — | text |
| Gemini 3 FlashGemini | ≤200K$0.5 >200K$0.5 | $3 $3 | $0.05 $0.05 | — | text |
| Gemini 3 Pro ImageGemini | $2 | $12 | — | — | text |
| Gemini EmbeddingGemini | $0.15 | — | — | — | embedding |
| Gemma 4 26BGemma | $0.15 | $0.6 | $0.015 | — | text |
| GLM-4.7GLM | $0.6 | $2.2 | — | — | text |
| GLM-5GLM | $1 | $3.2 | $0.1 | — | text |
| gpt-oss-120bGPT-OSS | $0.09 | $0.36 | — | — | text |
| gpt-oss-20bGPT-OSS | $0.07 | $0.25 | $0.007 | — | text |
| Grok 4.1 Fast Non-ReasoningGrok | $0.2 | $0.5 | $0.05 | — | text |
| Grok 4.1 Fast ReasoningGrok | $0.2 | $0.5 | $0.05 | — | text |
| Grok 4.20 Non-ReasoningGrok | $1.25 | $2.5 | $0.2 | — | text |
| Grok 4.20 ReasoningGrok | $1.25 | $2.5 | $0.2 | — | text |
| ImagenImagen | $0.0015/image | — | — | — | image |
| Imagen 1Imagen | $0.02/image | — | — | — | image |
| Imagen 2Imagen | $0.02/image | — | — | — | image |
| Imagen 3Imagen | $0.04/image | — | — | — | image |
| Imagen 3 FastImagen | $0.02/image | — | — | — | image |
| Imagen 4Imagen | $0.06/image | — | — | — | image |
| Imagen 4 FastImagen | $0.02/image | — | — | — | image |
| Imagen 4 UltraImagen | $0.06/image | — | — | — | image |
| Kimi-K2-ThinkingKimi | $0.6 | $2.5 | $0.06 | — | text |
| Llama 3.3 70BLlama | $0.72 | $0.72 | — | — | text |
| Llama 4 MaverickLlama | $0.35 | $1.15 | — | — | text |
| Llama 4 ScoutLlama | $0.25 | $0.7 | — | — | text |
| Lyria 2Lyria | $0.06/track | — | — | — | audio |
| Lyria 3Lyria | $0.04/track | — | — | — | audio |
| Lyria 3 ProLyria | $0.08/track | — | — | — | audio |
| MiniMax-M2MiniMax | $0.3 | $1.2 | $0.03 | — | text |
| Mistral Medium 3Mistral | $0.4 | $2 | — | — | text |
| Mistral OCR (25.05)Mistral | $0.0005 | $0.0005 | — | — | text |
| Mistral Small 3.1 (25.03)Mistral | $0.1 | $0.3 | — | — | text |
| Qwen3-235B-A22B-Instruct-2507Qwen | $0.22 | $0.88 | — | — | text |
| Qwen3-Coder-480B-A35B-InstructQwen | $0.22 | $1.8 | $0.022 | — | text |
| Qwen3-Next-80B-InstructQwen | $0.15 | $1.2 | — | — | text |
| Qwen3-Next-80B-ThinkingQwen | $0.15 | $1.2 | — | — | text |
| Veo 2Veo | $0.5/video | — | — | — | video |
| Veo 3Veo | $0.4/video | — | — | — | video |
| Veo 3.1Veo | $0.4/video | — | — | — | video |
| Veo 3.1 FastVeo | $0.1/video | — | — | — | video |
| Veo 3.1 LiteVeo | $0.05/video | — | — | — | video |
| Veo 3 FastVeo | $0.1/video | — | — | — | video |
per 1M tokens · US Dollar · Source: Official pricing pages