Cheaper Inference

Service status

unknown

568 indexed models

568 matching models

GPT-5 (Fast)

vercelAIGatewayCatalog/openai/gpt-5-fast

GPT-5 is OpenAI's flagship language model that excels at complex reasoning, broad real-world knowledge, code-intensive, and multi-step agentic tasks.

Context window
400,000
Maximum output
128,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Inference prices

GPT-5 mini (Batch)

vercelAIGatewayCatalog/openai/gpt-5-mini-batch

GPT-5 mini is a cost optimized model that excels at reasoning/chat tasks. It offers an optimal balance between speed, cost, and capability.

Context window
400,000
Maximum output
128,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

GPT-5 mini (Fast)

vercelAIGatewayCatalog/openai/gpt-5-mini-fast

GPT-5 mini is a cost optimized model that excels at reasoning/chat tasks. It offers an optimal balance between speed, cost, and capability.

Context window
400,000
Maximum output
128,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Inference prices

GPT-5 nano (Batch)

vercelAIGatewayCatalog/openai/gpt-5-nano-batch

GPT-5 nano is a high throughput model that excels at simple instruction or classification tasks.

Context window
400,000
Maximum output
128,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

GPT-5 pro (Batch)

vercelAIGatewayCatalog/openai/gpt-5-pro-batch

GPT-5 pro uses more compute to think harder and provide consistently better answers. Since GPT-5 pro is designed to tackle tough problems, some requests may take several minutes to finish.

Context window
400,000
Maximum output
272,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, reasoning, toolCalling, visionInput

GPT-6.1 Sol (Batch)

vercelAIGatewayCatalog/openai/gpt-6.1-sol-batch

GPT-6.1 Sol is OpenAI's reasoning model for complex coding, computer use, and professional work. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt c

Context window
1,050,000
Maximum output
128,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

GPT-6.1 Sol (Fast)

vercelAIGatewayCatalog/openai/gpt-6.1-sol-fast

GPT-6.1 Sol is OpenAI's reasoning model for complex coding, computer use, and professional work. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt c

Context window
1,050,000
Maximum output
128,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

GPT-6.1 Terra (Fast)

vercelAIGatewayCatalog/openai/gpt-6.1-terra-fast

GPT-6.1 Terra is OpenAI’s model for visual reasoning, precise computer use, and natural writing. It accepts text and images and generates text, with configurable reasoning effort, structured outputs, tool calling through the Responses API, and implicit and explicit prompt caching

Context window
1,050,000
Maximum output
128,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

GPT-6 Astra (Batch)

vercelAIGatewayCatalog/openai/gpt-6-astra-batch

GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.

Context window
1,050,000
Maximum output
128,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

GPT-6 Astra (Fast)

vercelAIGatewayCatalog/openai/gpt-6-astra-fast

GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.

Context window
1,050,000
Maximum output
128,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

GPT-6 Luna (Batch)

vercelAIGatewayCatalog/openai/gpt-6-luna-batch

GPT-6 Luna is OpenAI's efficient reasoning model for focused, high-volume tasks. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Resp

Context window
1,050,000
Maximum output
128,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

GPT-6 Luna (Fast)

vercelAIGatewayCatalog/openai/gpt-6-luna-fast

GPT-6 Luna is OpenAI's efficient reasoning model for focused, high-volume tasks. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Resp

Context window
1,050,000
Maximum output
128,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

GPT-6 Sol (Batch)

vercelAIGatewayCatalog/openai/gpt-6-sol-batch

GPT-6 Sol is OpenAI's reasoning model for complex coding and agentic workflows. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Respo

Context window
1,050,000
Maximum output
128,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

GPT-6 Sol (Fast)

vercelAIGatewayCatalog/openai/gpt-6-sol-fast

GPT-6 Sol is OpenAI's reasoning model for complex coding and agentic workflows. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Respo

Context window
1,050,000
Maximum output
128,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

GPT-Live 1

vercelAIGatewayCatalog/openai/gpt-live-1

Our premier model for natural, expressive voice conversations with smooth interruption handling.

Input modalities
text, audio
Output modalities
text, audio
Capabilities
audioInput, audioOutput, multimodal, realtime, speechOutput

GPT Live Transcribe

vercelAIGatewayCatalog/openai/gpt-live-transcribe

GPT Live Transcribe is a low-latency streaming speech-to-text model for live audio, with tunable latency, context, keyword hints, and multiple language hints. Priced by audio duration.

Input modalities
audio
Output modalities
text
Capabilities
audioInput, transcription

GPT-Realtime-1.5

vercelAIGatewayCatalog/openai/gpt-realtime-1.5

GPT-Realtime-1.5 is our flagship audio model for voice agents and customer support.

Input modalities
text, audio
Output modalities
text, audio
Capabilities
audioInput, audioOutput, multimodal, realtime, speechOutput

gpt-realtime-2

vercelAIGatewayCatalog/openai/gpt-realtime-2

GPT Realtime 2 is our most capable realtime voice model. It supports speech-to-speech interactions with configurable reasoning effort, stronger instruction following, and more reliable tool use for complex voice-agent workflows.

Input modalities
text, audio
Output modalities
text, audio
Capabilities
audioInput, audioOutput, multimodal, realtime, reasoning, speechOutput

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace