vercelAIGatewayCatalog/openai/gpt-realtime-2.1
GPT-Realtime-2.1 updates GPT-Realtime-2 with improved alphanumeric recognition, silence and noise handling, and interruption behavior. It supports speech-to-speech interactions with configurable reasoning effort, instruction following, and tool use for complex voice-agent workflo
- Context window
- 128,000
- Maximum output
- 32,000
- Input modalities
- text, audio
- Output modalities
- text, audio
- Capabilities
- audioInput, audioOutput, multimodal, realtime, reasoning, speechOutput
vercelAIGatewayCatalog/openai/gpt-realtime-mini
GPT-Realtime mini is capable of responding to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections.
- Input modalities
- text, audio
- Output modalities
- text, audio
- Capabilities
- audioInput, audioOutput, multimodal, realtime, speechOutput
vercelAIGatewayCatalog/openai/gpt-realtime-whisper
GPT Realtime Whisper is a streaming speech-to-text model for applications that need low-latency transcript deltas from live audio. It is designed for realtime use cases where developers need to tune latency and accuracy. GPT Realtime Whisper is priced by audio duration rather tha
- Input modalities
- audio
- Output modalities
- text
- Capabilities
- audioInput, transcription
cheaperInference/grok-4
- Context window
- 2,000,000
- Maximum output
- 256,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, reasoning, structuredOutputs, toolCalling, visionInput
Inference prices
cheaperInference/grok-4.1-fast-non-reasoning
- Context window
- 1,000,000
- Maximum output
- 1,000,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, structuredOutputs, toolCalling, visionInput
Inference prices
cheaperInference/grok-4.20-multi-agent-batch
- Context window
- 2,000,000
- Maximum output
- 2,000,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
cheaperInference/grok-4.20-multi-agent-beta
- Context window
- 2,000,000
- Maximum output
- 2,000,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
cheaperInference/grok-4.20-non-reasoning-batch
- Context window
- 2,000,000
- Maximum output
- 2,000,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
cheaperInference/grok-4.20-non-reasoning-beta
- Context window
- 2,000,000
- Maximum output
- 2,000,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
cheaperInference/grok-4.20-reasoning-batch
- Context window
- 2,000,000
- Maximum output
- 2,000,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
cheaperInference/grok-4.20-reasoning-beta
- Context window
- 2,000,000
- Maximum output
- 2,000,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
cheaperInference/grok-4.3-batch
- Context window
- 1,000,000
- Maximum output
- 1,000,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
cheaperInference/grok-4.6
- Context window
- 500,000
- Maximum output
- 500,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
cheaperInference/grok-4.7
- Context window
- 500,000
- Maximum output
- 500,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
cheaperInference/grok-stt
cheaperInference/grok-tts
- Output modalities
- audio
- Capabilities
- speechOutput, structuredOutputs
xAI/grok-voice-3.0
Flagship voice model
- Input modalities
- audio, text
- Output modalities
- audio, text
- Capabilities
- audioInput, multimodal, reasoning, speechOutput, toolCalling
cheaperInference/gte-base
- Maximum output
- 512
- Output modalities
- embeddings
- Capabilities
- embeddings