Gemini pro-vision

Google GeminiText

Gemini pro-vision is a text model from Google Gemini with a context window of 31K tokens and max output of 2K tokens. Pricing starts at $0.35 per million input tokens and $1.05 per million output tokens (cheapest at Google Vertex AI).

Specifications

Model Keygemini/gemini-pro-vision
ProviderGoogle Gemini
LiteLLM Providergemini
ModeText
Canonical Namegemini-pro
Context Window31K tokens
Max Output2K tokens

Capabilities

Vision Function Calling Reasoning JSON Schema System Messages Web Search Prompt Caching Audio Input Audio Output

Pricing

TypePer 1K TokensPer 1M Tokens
Input Tokens$0.000350$0.350
Output Tokens$0.0010$1.05

Price Comparison by Provider

Compare prices for Gemini pro-vision across different providers. The same model may be available through multiple providers at different price points.

Provider
Model Key
Input Price
Output Price
Google Geminigemini/gemini-pro$0.350$1.05
Google Vertex AIgemini-pro-experimentalN/AN/A

Similar Models

Models with similar capabilities and context window size.

Model
Provider
Mode
Input Price
Output Price
Context
Max Output
Vision
Functions
CodestralMistral CodestralTextN/AN/A32K8Knono
Codestral 2405Mistral CodestralTextN/AN/A32K8Knono
ERNIE 4.5 Vl 28B A3bNovitaText$0.140$0.56030K8Kyesyes
Llama3 405B Instruct MaasGoogle Vertex AITextN/AN/A32K32Knono
Llama3 70B Instruct MaasGoogle Vertex AITextN/AN/A32K32Knono
Llama3 8B Instruct MaasGoogle Vertex AITextN/AN/A32K32Knono
Mistral Small 3 1 24B Instruct 2503WatsonxText$0.100$0.30032K32Knoyes
Qwen MaxDashscopeText$1.60$6.4031K8Knoyes
Qwen2.5 7B InstructNovitaText$0.070$0.07032K32Knoyes
Qwen3 32BOvhcloudText$0.080$0.23032K32Knoyes