Beta

deepseek-flash

By DeepSeek

Reads images: a question can carry pictures.

Model name for the APIdeepseek-flash
Uptime, last 3 days
1 call so far
Too few to give a percentage
Credits per reply
Not measured yet
Shown after its first replies

Your chats and training

Used to train and improve the provider’s models.

The company that answers for this model states it may use prompts and replies to improve or train its models. Do not send anything private to it.

Which company answers for a model is not published here, so this says what the policy is, not whose it is. Checked against their terms on Sep 28, 2026.

Model facts

Context length
1M tokens
Longest reply
943.7K tokens
Calls tools
Yes
Knowledge cutoff
May 2025
Released
10 Sep 2026
Open weights
Yes

Context, reply length, tool calling, knowledge cutoff, release date and open weights come from the models.dev open dataset, read once a day.

Use in chatAPI docs

Call it through the API

Any OpenAI-compatible client works: use the address in the sample and this model name.

import requests

response = requests.post(
    "https://onomeo.com/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={"model": "deepseek-flash", "messages": [
        {"role": "user", "content": "Hello!"}
    ]}
)
print(response.json())

More from DeepSeek

  1. deepseek-v4-flashFree99% up, last 3 days
  2. deepseek-v4.1-flashFree97% up, last 3 days

Similar price

  1. gpt-6-luna2,917 / callToo few calls yet
  2. mistral-large-332 / callToo few calls yet
  3. nemotron-3-ultra-550b-a55b39 / callToo few calls yet
  4. claude-haiku-4.5641 / call100% up, last 3 days
  5. glm-5.33,149 / call100% up, last 3 days
  6. claude-opus-5.55,185 / call78% up, last 3 days

deepseek-flash against other models

Figures come from real calls made through this site. Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.