impulse

Sora 2

Frontier labVideo
API id sora-2
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
2
3 listings
Released
-
date not published

Where to run it

2 hosts serve Sora 2. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
sora-2
-
sora-2
-
Show 1 more listings: regions, snapshots and variants
OpenAI
Alias
sora-2
-

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
ImagesText
Produces
Video

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller OpenAI models

No similar OpenAI model keeps its key capabilities.

Other frontier labs

No similar match from another frontier lab.

Open-weight picks

No similar open-weight match.

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="sora-2", input="Hello")
print(response.output_text)

Quick answers

Which APIs offer Sora 2?

Sora 2 runs on 2 APIs: OpenAI and Azure OpenAI.

Is Sora 2 being retired?

It has been retired: Azure OpenAI retired it on 15 Oct 2026.

What is Sora 2's API model id?

Use sora-2 with OpenAI.

Sources

Raw catalog entry for sora-2 on OpenAI
{
  "deprecation_date": "2026-09-24",
  "deprecation_source": "https://developers.openai.com/api/docs/deprecations",
  "litellm_provider": "openai",
  "mode": "video_generation",
  "output_cost_per_video_per_second": 0.1,
  "source": "https://platform.openai.com/docs/api-reference/videos",
  "supported_modalities": [
    "text",
    "image"
  ],
  "supported_output_modalities": [
    "video"
  ]
}