impulse

Recraft 20B

Image
API id recraft-20b
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Where to run it

2 hosts serve Recraft 20B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
falInference
recraft-20b
-
ReplicateInference
recraft-20b
-

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
Text
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.

Call it

Using fal's API.

Python
from litellm import completion

response = completion(
    model="fal_ai/recraft-20b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer Recraft 20B?

Recraft 20B runs on 2 APIs: fal and Replicate.

Is Recraft 20B being retired?

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

What is Recraft 20B's API model id?

Use recraft-20b with fal.

Sources

Raw catalog entry for recraft-20b on fal
{
  "litellm_provider": "fal_ai",
  "metadata": {
    "notes": "per image at the default realistic_image style, from the fal pricing API; vector styles cost 2x and have no catalog field; the fal.ai page for this id redirects to fal-ai/recraft/v2/text-to-image, which rounds the rate to $0.022"
  },
  "mode": "image_generation",
  "output_cost_per_image": 0.0219,
  "source": "https://api.fal.ai/v1/models/pricing?endpoint_id=fal-ai/recraft-20b",
  "supported_endpoints": [
    "/v1/images/generations"
  ]
}