impulse

Seedream5 Lite

Image
API id seedream5_lite
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Where to run it

1 host serve Seedream5 Lite. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
seedream5_lite
-

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
Images

Similar models

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

Smaller Independent models

No similar Independent model keeps its key capabilities.

Other frontier labs

Open-weight picks

No similar open-weight match.

Model line

Newer and older versions, at each lab's own price.

  1. UndatedSeedream 5.0 LiteLatestNot listed
  2. UndatedSeedream 5 LiteNot listed
  3. UndatedSeedream5 LiteThis pageNot listed

Call it

Using RunwayML's API.

Python
from litellm import completion

response = completion(
    model="runwayml/seedream5_lite",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer Seedream5 Lite?

Seedream5 Lite runs on 1 API: RunwayML.

Is Seedream5 Lite being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Seedream5 Lite?

Yes. Seedream 5.0 Lite is the newest model in this line.

What is Seedream5 Lite's API model id?

Use seedream5_lite with RunwayML.

Sources

Raw catalog entry for seedream5_lite on RunwayML
{
  "litellm_provider": "runwayml",
  "metadata": {
    "comment": "4 credits per image (any resolution) @ $0.01 per credit = $0.04 per image"
  },
  "mode": "image_generation",
  "output_cost_per_image": 0.04,
  "source": "https://docs.dev.runwayml.com/guides/pricing/",
  "supported_modalities": [
    "text",
    "image"
  ],
  "supported_output_modalities": [
    "image"
  ]
}