impulse

Parse V5.0

OCR
API id parse-v5.0
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 Parse V5.0. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
CohereLab API
parse-v5.0
-

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
Text

Similar models

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

Smaller Cohere models

No similar Cohere 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 Cohere's API.

Python
from litellm import completion

response = completion(
    model="cohere/parse-v5.0",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer Parse V5.0?

Parse V5.0 runs on 1 API: Cohere.

Is Parse V5.0 being retired?

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

What is Parse V5.0's API model id?

Use parse-v5.0 with Cohere.

Sources

Raw catalog entry for parse-v5.0 on Cohere
{
  "litellm_provider": "cohere",
  "mode": "ocr",
  "ocr_cost_per_page": 0.0015,
  "source": "https://cohere.com/blog/parse",
  "supported_endpoints": [
    "/v1/ocr"
  ]
}