All models

Deepseek V4.1 Flash

@cf/deepseek-ai/deepseek-v4.1-flash-1017
DeepSeek

Quick start

# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/chat/completions \
  -H "content-type: application/json" \
  -d '{
    "model": "@cf/deepseek-ai/deepseek-v4.1-flash-1017",
    "messages": [{"role": "user", "content": "<your message>"}]
  }'

# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/chat/completions \
  -J '{"model": "@cf/deepseek-ai/deepseek-v4.1-flash-1017", "messages": [{"role": "user", "content": "<your message>"}]}'

Parameters

Input
messages array required

A list of messages comprising the conversation so far.

audio object optional

Parameters for audio output. Required when modalities includes 'audio'.

chat_template_kwargs object optional
frequency_penalty number optional default: 0

Penalizes new tokens based on their existing frequency in the text so far.

function_call string optional
functions array optional
logit_bias object optional

Modify the likelihood of specified tokens appearing in the completion. Maps token IDs to bias values from -100 to 100.

logprobs boolean optional default: false

Whether to return log probabilities of the output tokens.

max_completion_tokens integer optional

An upper bound for the number of tokens that can be generated for a completion.

max_tokens integer optional

Deprecated in favor of max_completion_tokens. The maximum number of tokens to generate.

metadata object optional

Set of 16 key-value pairs that can be attached to the object.

modalities array optional

Output types requested from the model (e.g. ['text'] or ['text', 'audio']).

model string optional

ID of the model to use (e.g. '@cf/zai-org/glm-4.7-flash, etc').

n integer optional default: 1

How many chat completion choices to generate for each input message.

parallel_tool_calls boolean optional default: true

Whether to enable parallel function calling during tool use.

prediction object optional
presence_penalty number optional default: 0

Penalizes new tokens based on whether they appear in the text so far.

reasoning_effort string optional default: "high"

Reasoning effort. Supported levels: max, high, low, none. Compatibility aliases: auto maps to high; minimal maps to none; medium maps to high; xhigh maps to max.

response_format optional

How the result is returned (e.g. a URL or base64 data).

seed integer optional

If specified, the system will make a best effort to sample deterministically.

stop string optional

Up to 4 sequences where the API will stop generating further tokens.

store boolean optional default: false

Whether to store the output for model distillation / evals.

stream boolean optional default: false

If true, partial message deltas will be sent as server-sent events.

stream_options object optional
temperature number optional default: 1

Sampling temperature between 0 and 2.

tool_choice optional
tools array optional

A list of tools the model may call.

top_logprobs integer optional

How many top log probabilities to return at each token position (0-20). Requires logprobs=true.

top_p number optional default: 1

Nucleus sampling: considers the results of the tokens with top_p probability mass.

user string optional

A unique identifier representing your end-user, for abuse monitoring.

web_search_options object optional

Options for the web search tool (when using built-in web search).

Output