GLM-4.7 Flash API

Billed from your GPUniq balance as you use it — no subscription, no monthly minimum, no per-seat fee. Prices refresh from the live catalog hourly.

API identifier

glm-4.7-flash

Pass this exact string as the "model" field of your request.

Type

Chat & text

Served by Zhipu.

Context window

202,752 tokens

About roughly 152,064 words — about 304 printed pages. Prompt, conversation history and attachments all count against it.

Max output

16,384 tokens

Ceiling for a single reply. Set max_tokens below it to cap cost per request.

Accepts

Text

What you can put in the request body besides plain text.

Returns

Text

Measured speed

≈66 tokens/sec

Rolling average of real GPUniq traffic. This sample comes from non-streaming requests, so it includes the wait before the first token.

Tokenizer

Other

Determines how your text splits into billable tokens.

Available since

2026-01-19

Upstream moderation

No

No vendor-side safety filter is applied on top of the model.

• Function calling: supported

  Send tool definitions, get back the call the model wants made.

• Structured outputs: supported

  Replies constrained to your JSON Schema.

• Vision input: not supported

  Accepts images in the message content.

• Extended reasoning: supported

  Thinks before answering; thinking tokens bill as output.

curl https://api.gpuniq.com/v1/openai/chat/completions \
  -H "Authorization: Bearer YOUR_GPUNIQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-4.7-flash",
    "messages": [{"role": "user", "content": "Explain rate limiting in one paragraph."}]
  }'

Create a key on /chat and send it as a bearer token. The same key works across every model in the catalog, so switching models means changing one string.

frequency_penalty

Discourages repeating tokens the model has already used often.

include_reasoning

Returns the reasoning trace alongside the answer instead of hiding it.

logit_bias

Nudges specific tokens up or down before sampling.

logprobs

Returns token probabilities — handy for confidence scoring and evals.

max_tokens

Hard cap on the reply length. Also your cost ceiling per request, since output is the expensive half of the bill.

min_p

Drops tokens below a share of the top token’s probability.

presence_penalty

Pushes the model toward introducing new topics.

reasoning

Extended thinking. The model works through the problem before answering; the thinking tokens are billed as output.

repetition_penalty

Blunt anti-loop control, mostly useful on open-weight models.

response_format

Selects the response shape — plain text or JSON. The weaker cousin of structured outputs: it enforces valid JSON, not your particular schema.

seed

Asks for repeatable sampling. Best effort on every vendor — it makes runs similar, it does not make them identical.

stop

Stop sequences that cut generation as soon as they appear.

structured_outputs

Schema-constrained decoding: the reply is guaranteed to parse against the JSON Schema you supply, so no retry loop around JSON.parse.

temperature

Randomness. Near 0 for extraction and classification, higher for drafting and ideation.

tool_choice

Forces or forbids a tool call for one request — useful when you want a guaranteed structured answer instead of prose.

tools

Function calling. You describe callable functions in JSON Schema and the model replies with the call it wants made, which is what agent frameworks are built on.

top_k

Limits sampling to the k most likely next tokens.

top_logprobs

Returns the n most likely alternatives per position.

top_p

Nucleus sampling — an alternative to temperature. Tune one or the other, not both.