GLM 4.7 Flash Heretic

venice fast tier Chat & reasoning uncensored (NSFW-capable, site-scoped)

Cheap, fast uncensored variant of GLM-4.7-Flash via Venice (200K context, tool calling) — for high-volume explicit-text classification/rewriting where quality matters less than cost. Text only. Thinking is disabled by default; pass options.venice_parameters.disable_thinking=false to enable reasoning.

$0.00011 in / $0.0006 out per 1K tokens
Published price
glm-4.7-flash-heretic
species_name
2026-09-24
Verified since
Call it

One request, the price in the response.

Pass species_name to pin this model; omit it and Fire uses the default for the endpoint. Every response carries meta.price.usd and meta.call_id.

curl -X POST https://fire.prosaga.net/v1/chat \
  -H "Authorization: Bearer $FIRE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"species_name":"glm-4.7-flash-heretic",
      "messages":[{"role":"user","content":"Hello"}]}'

Strengths

uncensoredfastcheapreasoning

Modality

In: text  ·  Out: text

Lineage

Family zai · genus glm · served by venice

Capabilities

modality
text
context window
200000
supports streaming
yes
Similar models

Same job, different trade-offs.

Call GLM 4.7 Flash Heretic with one key.

Free to sign up. Pay only when you top up.