Cerebras

Use fast open AI models on Cerebras: generate replies, continue conversations, pull fields out of text, sort text into categories, ask about images, and compare models by price and ability.

Actions

Action	What it does
Ask about an image	Ask a question about an image, or have it described, such as reading a receipt, a chart or a screenshot.
Classify text	Put a text into exactly one of the categories you list, with a one-sentence reason.
Continue a conversation	Send a conversation so far, oldest message first, and get the model's next reply.
Continue text	Have a model carry on writing from where a text leaves off, such as the start of a sentence, a list or a template.
Extract data from text	Pull the pieces of information you name out of a text, such as a name, a date or an amount from an email or invoice.
Generate a Cerebras response	Send a prompt to a model on Cerebras and get back its written response.
Get model details	Get one model's details: its name, what it costs, how much text it can take and what it can do.
List models	List the models your Cerebras account can use, with what each costs, how much text it can take and what it can do.

Ask about an image

Ask a question about an image, or have it described, such as reading a receipt, a chart or a screenshot.

Inputs

ImageimagetextRequired: The image to ask about: upload a file, pick an image from an earlier step, or paste a link to one. PNG, JPEG, WebP and GIF all work.
Questionquestiontext: What to ask about the image. Leave empty to get a detailed description.
Modelmodeltext: Which model looks at the image. Leave empty to use one that can read images.
Maximum response lengthmax_tokensnumber: The longest the reply may be, in tokens (a token is about three quarters of a word). The model's thinking counts toward it. Leave empty for the model's own limit.At least 1.

Outputs

completion_tokensnumber: Tokens in the reply, including the model's thinking.
finish_reasontext: Why the reply ended: 'stop' when it was complete, 'length' when it reached Maximum response length.
modeltext: The model that replied.
prompt_tokensnumber: Tokens in what was sent.
reasoningtext: The model's thinking before it replied, when the model shares it. Empty otherwise.
response_secondsnumber: How long Cerebras took to answer, in seconds.
response_texttext: The model's reply.
total_tokensnumber: Tokens billed in total.

Example output

{
  "completion_tokens": 96,
  "finish_reason": "stop",
  "model": "qwen-3.8-27b",
  "prompt_tokens": 42,
  "reasoning": "",
  "response_seconds": 0.214,
  "response_text": "The receipt is from Corner Market; the total is $23.17.",
  "total_tokens": 138
}

Classify text

Put a text into exactly one of the categories you list, with a one-sentence reason. Use it to route emails, tickets or leads.

Inputs

TexttexttextRequired: The text to read, such as an email, a message or a document.
CategoriescategorieslistRequired: The categories to choose from, at least two. The answer is always exactly one of these.
Extra instructionsinstructionstext: Optional guidance for tricky cases, in plain words.
Modelmodeltext: Which model answers. Leave empty to use the model Cerebras recommends.

Outputs

categorytext: The category chosen, exactly as listed.
completion_tokensnumber: Tokens in the reply, including the model's thinking.
modeltext: The model used.
prompt_tokensnumber: Tokens in what was sent.
reasontext: Why the model chose it, in one sentence.
response_secondsnumber: How long Cerebras took to answer, in seconds.
total_tokensnumber: Tokens billed in total.

Example output

{
  "category": "Billing",
  "completion_tokens": 96,
  "model": "gpt-oss-120b",
  "prompt_tokens": 42,
  "reason": "The customer asks why they were charged twice.",
  "response_seconds": 0.214,
  "total_tokens": 138
}

Continue a conversation

Send a conversation so far, oldest message first, and get the model's next reply. Use it for chat assistants that remember what was said.

Inputs

MessagesmessageslistRequired: The conversation so far, oldest first. Each message has a role (user for the person, assistant for the model) and its text. The model writes the next reply.
System instructionssystem_prompttext: Optional instructions that set the model's role, tone or format for every reply, e.g. 'You are a concise support agent. Reply in two sentences.'
Modelmodeltext: Which model answers. Leave empty to use the model Cerebras recommends.
Reasoning effortreasoning_efforttext: How much the model thinks before it answers. More helps with hard problems but takes longer and uses more tokens. A model that cannot stop thinking uses its lightest setting when Off is chosen.One of: default (Model's default), none (Off), low, medium, high. Default: default.
Maximum response lengthmax_tokensnumber: The longest the reply may be, in tokens (a token is about three quarters of a word). The model's thinking counts toward it. Leave empty for the model's own limit.At least 1.
Creativity (temperature)temperaturenumber: How varied the wording is, from 0 (focused and repeatable) to 2 (most varied). Leave empty for the model's default.From 0 to 2.0.

Outputs

completion_tokensnumber: Tokens in the reply, including the model's thinking.
finish_reasontext: Why the reply ended: 'stop' when it was complete, 'length' when it reached Maximum response length.
modeltext: The model that replied.
prompt_tokensnumber: Tokens in what was sent.
reasoningtext: The model's thinking before it replied, when the model shares it. Empty otherwise.
response_secondsnumber: How long Cerebras took to answer, in seconds.
response_texttext: The model's reply.
total_tokensnumber: Tokens billed in total.

Example output

{
  "completion_tokens": 96,
  "finish_reason": "stop",
  "model": "gpt-oss-120b",
  "prompt_tokens": 42,
  "reasoning": "",
  "response_seconds": 0.214,
  "response_text": "Thanks for reaching out! Your order shipped this morning and should arrive by Thursday.",
  "total_tokens": 138
}

Continue text

Have a model carry on writing from where a text leaves off, such as the start of a sentence, a list or a template. For questions and instructions, use 'Generate a Cerebras response'.

Inputs

Text to continuetexttextRequired: The beginning the model should carry on from.
Modelmodeltext: Which model answers. Leave empty to use the model Cerebras recommends.
Maximum response lengthmax_tokensnumber: The longest the continuation may be, in tokens (a token is about three quarters of a word). Leave empty for up to 1,000.At least 1.
Creativity (temperature)temperaturenumber: How varied the wording is, from 0 (focused and repeatable) to 2 (most varied). Leave empty for the model's default.From 0 to 2.0.
Stop atstop_sequenceslist: Up to 4 pieces of text that end the continuation as soon as the model writes one. Type \n for a line break.

Outputs

completion_tokensnumber: Tokens in the reply, including the model's thinking.
finish_reasontext: Why it ended: 'stop' at a natural end or a Stop at entry, 'length' at Maximum response length.
full_texttext: The start and the continuation together.
modeltext: The model used.
prompt_tokensnumber: Tokens in what was sent.
response_secondsnumber: How long Cerebras took to answer, in seconds.
texttext: What the model wrote, without the start.
total_tokensnumber: Tokens billed in total.

Example output

{
  "completion_tokens": 96,
  "finish_reason": "length",
  "full_text": "Five names for a coffee shop:\n1. Daily Grind\n2. Bean There\n3. Brew Haven",
  "model": "gpt-oss-120b",
  "prompt_tokens": 42,
  "response_seconds": 0.214,
  "text": " Daily Grind\n2. Bean There\n3. Brew Haven",
  "total_tokens": 138
}

Extract data from text

Pull the pieces of information you name out of a text, such as a name, a date or an amount from an email or invoice. A field the text does not mention comes back empty rather than guessed.

Inputs

TexttexttextRequired: The text to read, such as an email, a message or a document.
Fields to fillfieldslistRequired: The pieces of information you want back, one per entry. Add what each means after a colon to steer it: 'total: the amount due in US dollars'.
Extra instructionsinstructionstext: Optional guidance for tricky cases, in plain words.
Modelmodeltext: Which model answers. Leave empty to use the model Cerebras recommends.

Outputs

completion_tokensnumber: Tokens in the reply, including the model's thinking.
dataobject: Each field you named, with its value from the text, or empty when the text does not say.
found_fieldslist: The fields that were found.
missing_fieldslist: The fields the text does not mention.
modeltext: The model used.
prompt_tokensnumber: Tokens in what was sent.
response_secondsnumber: How long Cerebras took to answer, in seconds.
total_tokensnumber: Tokens billed in total.

Example output

{
  "completion_tokens": 96,
  "data": {
    "customer name": "Dana Whitfield",
    "order number": "A-10442",
    "total": "$84.50"
  },
  "found_fields": [
    "customer name",
    "order number",
    "total"
  ],
  "missing_fields": [],
  "model": "gpt-oss-120b",
  "prompt_tokens": 42,
  "response_seconds": 0.214,
  "total_tokens": 138
}

Generate a Cerebras response

Send a prompt to a model on Cerebras and get back its written response.

Inputs

PromptprompttextRequired: The message or question to send to the model.
System instructionssystem_prompttext: Optional instructions that set the model's role, tone or format for every reply, e.g. 'You are a concise support agent. Reply in two sentences.'
Modelmodeltext: Which model answers. Leave empty to use the model Cerebras recommends.
Reasoning effortreasoning_efforttext: How much the model thinks before it answers. More helps with hard problems but takes longer and uses more tokens. A model that cannot stop thinking uses its lightest setting when Off is chosen.One of: default (Model's default), none (Off), low, medium, high. Default: default.
Maximum response lengthmax_tokensnumber: The longest the reply may be, in tokens (a token is about three quarters of a word). The model's thinking counts toward it. Leave empty for the model's own limit.At least 1.
Creativity (temperature)temperaturenumber: How varied the wording is, from 0 (focused and repeatable) to 2 (most varied). Leave empty for the model's default.From 0 to 2.0.

Outputs

completion_tokensnumber: Tokens in the reply, including the model's thinking.
finish_reasontext: Why the reply ended: 'stop' when it was complete, 'length' when it reached Maximum response length.
modeltext: The model that replied.
prompt_tokensnumber: Tokens in what was sent.
reasoningtext: The model's thinking before it replied, when the model shares it. Empty otherwise.
response_secondsnumber: How long Cerebras took to answer, in seconds.
response_texttext: The model's reply.
total_tokensnumber: Tokens billed in total.

Example output

{
  "completion_tokens": 96,
  "finish_reason": "stop",
  "model": "gpt-oss-120b",
  "prompt_tokens": 42,
  "reasoning": "",
  "response_seconds": 0.214,
  "response_text": "Thanks for reaching out! Your order shipped this morning and should arrive by Thursday.",
  "total_tokens": 138
}

Get model details

Get one model's details: its name, what it costs, how much text it can take and what it can do.

Inputs

ModelmodeltextRequired: The model to look up.

Outputs

can_read_imagestrue/false: Whether the model works with 'Ask about an image'.
can_reasontrue/false: Whether the model thinks before it answers.
context_lengthnumber: The most tokens a request and its reply can hold together.
deprecatedtrue/false: Whether Cerebras is retiring the model.
descriptiontext: What the model is good at.
hugging_face_idtext: The model's page on Hugging Face, as owner/name.
idtext: The model's id, as steps use it.
input_price_per_million_tokensnumber: US dollars per million tokens sent.
max_output_tokensnumber: The longest reply the model can write, in tokens.
nametext: The model's name.
output_price_per_million_tokensnumber: US dollars per million tokens written.
owned_bytext: Who made the model.
previewtrue/false: Whether the model is in preview.
supports_structured_outputstrue/false: Whether the model can answer in a fixed JSON shape.
supports_tool_callingtrue/false: Whether the model can call tools.

Example output

{
  "can_read_images": false,
  "can_reason": true,
  "context_length": 131072,
  "deprecated": false,
  "description": "This model excels at efficient reasoning across science, math, and coding applications.",
  "hugging_face_id": "openai/gpt-oss-120b",
  "id": "gpt-oss-120b",
  "input_price_per_million_tokens": 0.35,
  "max_output_tokens": 40960,
  "name": "OpenAI GPT OSS",
  "output_price_per_million_tokens": 0.75,
  "owned_by": "OpenAI",
  "preview": false,
  "supports_structured_outputs": true,
  "supports_tool_calling": true
}

List models

List the models your Cerebras account can use, with what each costs, how much text it can take and what it can do.

Inputs

None.

Outputs

countnumber: How many models.
model_idslist: Just the model ids.
modelslist: The models, in the order Cerebras lists them.

Example output

{
  "count": 1,
  "model_ids": [
    "gpt-oss-120b"
  ],
  "models": [
    {
      "can_read_images": false,
      "can_reason": true,
      "context_length": 131072,
      "deprecated": false,
      "description": "This model excels at efficient reasoning across science, math, and coding applications.",
      "hugging_face_id": "openai/gpt-oss-120b",
      "id": "gpt-oss-120b",
      "input_price_per_million_tokens": 0.35,
      "max_output_tokens": 40960,
      "name": "OpenAI GPT OSS",
      "output_price_per_million_tokens": 0.75,
      "owned_by": "OpenAI",
      "preview": false,
      "supports_structured_outputs": true,
      "supports_tool_calling": true
    }
  ]
}

ActionsCopy Anchor Link

Ask about an imageCopy Anchor Link

Inputs

Outputs

Classify textCopy Anchor Link

Inputs

Outputs

Continue a conversationCopy Anchor Link

Inputs

Outputs

Continue textCopy Anchor Link

Inputs

Outputs

Extract data from textCopy Anchor Link

Inputs

Outputs

Generate a Cerebras responseCopy Anchor Link

Inputs

Outputs

Get model detailsCopy Anchor Link

Inputs

Outputs

List modelsCopy Anchor Link

Inputs

Outputs

On this page

Actions

Ask about an image

Classify text

Continue a conversation

Continue text

Extract data from text

Generate a Cerebras response

Get model details

List models