Last refreshed 2026-05-10. Next refresh: weekly.
Why use GPT-5 on Replicate API?
Replicate API offers GPT-5 with pay-as-you-go pricing at $1.25/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.
Compare GPT-5 across 4 providers to find the best fit for your use caseInput / 1M
$1.25
Output / 1M
$10.00
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install replicateAuth
export REPLICATE_API_TOKEN=...Call
import replicate
output = replicate.run(
"openai/gpt-5",
input={"prompt": "Hello"}Model ID
openai/gpt-5Request example
import replicate
# reads REPLICATE_API_TOKEN from env
# openai/gpt-5 format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"openai/gpt-5",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Gotchas
- Use provider model ID "openai/gpt-5", not the LLMReference slug "gpt-5".
- Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
- The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.
Compare GPT-5 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Replicate API | $1.25 | $10.00 |
| OpenRouter | $1.25 | $10.00 |
| OpenAI API | $1.25 | $10.00 |
| Vercel AI Gateway | $1.25 | $10.00 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.25 |
| Output tokens | $10.00 |
Capabilities
VisionMultimodalReasoningJSON / Tool useStructured OutputsCode ExecutionPrompt CachingBatch API
About GPT-5
OpenAI's previous intelligent reasoning model with configurable reasoning effort. Released August 2025. Supports minimal, low, medium, and high reasoning levels. Succeeded by GPT-5.1 and later models.
Get Started
Model Specs
Released2025-08-07
Context400k
ArchitectureDecoder Only
Knowledge cutoff2024-09