FactQuire

fireworks

GLM 5.1 Fast on Fireworks

glm-5.1-fast

Fields

provider"fireworks"
model_id"glm-5.1-fast"
display_name"GLM 5.1 Fast on Fireworks"
status"ga"
release_datenull
deprecation_datenull
retirement_datenull
pricing{"input_per_mtok": 2.8, "output_per_mtok": 8.8, "cached_input_per_mtok": 0.52, "batch_discount_pct": null}
context_window_tokensnull
max_output_tokensnull
modalities{"input": ["text"], "output": ["text"]}
knowledge_cutoffnull
verified_at"2026-07-20T01:30:00Z"
notes"Provider is Fireworks serving platform; upstream model family named in display_name. Context window not captured from Fireworks model page."
permalink"/models/fireworks/glm-5_1-fast.html"

Sources

  1. https://docs.fireworks.ai/serverless/pricing

    Accessed: 2026-07-20T01:30:00Z

    Fields: pricing.input_per_mtok, pricing.output_per_mtok, pricing.cached_input_per_mtok

    Text and vision models ... prices are input / cached input / output (USD per 1M tokens) ... GLM 5.1 Fast $2.80 / $0.52 / $8.80

Verified At

2026-07-20T01:30:00Z

Changelog History

Price & deprecation alerts

One weekly email when any tracked model changes price or limits, or gets deprecated. Every change source-verified. No spam, unsubscribe anytime. Want per-model alerts within a day? Create a free watchlist →