Cheaper Inference

Service status

unknown

568 indexed models

568 matching models

FLUX.1 Kontext [pro]

blackForestLabs/flux-kontext-pro

Submits an image creation task with FLUX.1 Kontext [pro]. For image editing, prefer FLUX.2 [pro] (/flux-2-pro) or FLUX.2 [flex] (/flux-2-flex) which are the recommended default models for editing workflows.

Input modalities
text, image
Output modalities
image
Capabilities
imageOutput, multimodal, visionInput

flux-2-flex

cheaperInference/flux-2-flex

Output modalities
image
Capabilities
imageOutput, structuredOutputs

FLUX.2 [klein] 4B

blackForestLabs/flux-2-klein-4b

Submits an image generation or editing task with FLUX.2 [klein] 4B. The fastest, most lightweight FLUX.2 model, with open weights that run on consumer GPUs.

Input modalities
text, image
Output modalities
image
Capabilities
imageOutput, structuredOutputs

flux-2-klein-9b

cheaperInference/flux-2-klein-9b

Output modalities
image
Capabilities
imageOutput

flux-2-max

cheaperInference/flux-2-max

Context window
67,300
Maximum output
67,300
Output modalities
image
Capabilities
imageOutput

FLUX.2 [pro]

blackForestLabs/flux-2-pro

Submits an image generation or editing task with FLUX.2 [pro]. This is the recommended default model for image editing and generation. Supports text-to-image and image-to-image editing workflows.

Input modalities
text, image
Output modalities
image
Capabilities
imageOutput, multimodal, visionInput

flux-3-image

cheaperInference/flux-3-image

Output modalities
image
Capabilities
imageOutput, structuredOutputs

flux-3-image-klein

cheaperInference/flux-3-image-klein

Output modalities
image
Capabilities
imageOutput

flux-3-video

cheaperInference/flux-3-video

Output modalities
video
Capabilities
videoOutput

flux-fast-schnell

cheaperInference/flux-fast-schnell

Context window
512
Output modalities
image
Capabilities
imageOutput

fugu-max

cheaperInference/fugu-max

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

Inference prices

fugu-ultra

cheaperInference/fugu-ultra

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

fugu-ultra-v2

cheaperInference/fugu-ultra-v2

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

Inference prices

Gemini 2.5 Flash (Batch)

vercelAIGatewayCatalog/google/gemini-2.5-flash-batch

Gemini 2.5 Flash is a thinking model that offers great, well-rounded capabilities. It is designed to offer a balance between price and performance with multimodal support and a 1M token context window.

Context window
1,000,000
Maximum output
64,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Gemini 2.5 Flash Lite (Batch)

vercelAIGatewayCatalog/google/gemini-2.5-flash-lite-batch

Gemini 2.5 Flash-Lite is a balanced, low-latency model with configurable thinking budgets and tool connectivity (e.g., Google Search grounding and code execution). It supports multimodal input and offers a 1M-token context window.

Context window
1,048,576
Maximum output
65,535
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Gemini 2.5 Pro (Batch)

vercelAIGatewayCatalog/google/gemini-2.5-pro-batch

Gemini 2.5 Pro is our most advanced reasoning Gemini model, capable of solving complex problems. Gemini 2.5 Pro can comprehend vast datasets and challenging problems from different information sources, including text, audio, images, video, and even entire code repositories.

Context window
1,048,576
Maximum output
65,535
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Gemini 3.1 Flash Lite (Batch)

vercelAIGatewayCatalog/google/gemini-3.1-flash-lite-batch

Gemini 3.1 Flash Lite outperforms 2.5 Flash Lite on overall quality and lands close to 2.5 Flash performance across key capability areas. It is a workhorse model for high-volume use cases, with improvements across audio input/ASR, RAG snippet ranking, translation, data extraction

Context window
1,000,000
Maximum output
65,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Gemini 3.1 Pro Preview (Batch)

vercelAIGatewayCatalog/google/gemini-3.1-pro-preview-batch

Improved SWE and agentic capabilities, improved token efficiency and thinking, and expanded thinking levels.

Context window
1,000,000
Maximum output
64,000
Input modalities
text, image, pdf
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

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