GPT-4o (2024-08-06)

openai/gpt-4o-2024-08-06

This is the pinned August 6, 2024 snapshot of OpenAI's GPT-4o, accepting text and image input and producing text output. It was the first GPT-4o snapshot to support Structured Outputs, letting developers supply a JSON schema that responses follow, and it raised the output limit over the May 2024 release. Use it for workloads that need a fixed GPT-4o version, especially schema-constrained extraction and function-calling pipelines.

Input price
$2.50USD / 1M tokens
Output price
$10.00USD / 1M tokens
Cache read
$1.25USD / 1M tokens
Context window
128K
Max output
16.4K

Specifications

CapabilitiesChatVisionStructured outputFunction calling
Input
Text, image
Output
Text
Available

Questions

FAQ

How do I call OpenAI GPT-4o (2024-08-06) through SandBase?

Create a SandBase API key, then send requests with the model ID "openai/gpt-4o-2024-08-06" to Responses API (/v1/responses) or Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

How much does OpenAI GPT-4o (2024-08-06) cost?

$2.50 per 1M input tokens and $10 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

What is the context window of OpenAI GPT-4o (2024-08-06)?

128K tokens of context, with up to 16.4K output tokens per response.

Which features does OpenAI GPT-4o (2024-08-06) support?

OpenAI GPT-4o (2024-08-06) supports vision (image input), function calling, structured output. See Specifications above for the full list.

Do I need a separate OpenAI account?

No. One SandBase API key and balance gives you access to OpenAI GPT-4o (2024-08-06) and the other models in the catalog; you do not need to sign up with OpenAI separately.