Alex Getmanfrühe KI-Signale

GLM-5

Z.ai

Veröffentlicht Aktualisiert
Kontextfenster
203K
202.752 Tokens
Maximale Ausgabe
131K
131.072 Tokens
Eingabe / Ausgabe
Text → Text

API-Preise

USD / 1 Mio. Token

EingabeAusgabeCache-Eingabe
  • $1,00
zai-pricing
  • $3,20
zai-pricing
  • $0,20
zai-pricing

Zeitverlauf

  1. · Gewichtsversion · Beleglink
Preis Ein-/Ausgabe · USD / 1 Mio. Token
ModellBeleglinksPreis Ein-/Ausgabe
glm-5
standard
zai-pricing
API-Route nicht verfügbar
$1,00 / $3,20
  1. · Beleglinks · GitHub search · Z.ai · pulls · smg-project/smg · @hello-alexmcc
    Auszug
    Atria-Dawn, `glm`, beside Atria-Dawn-Preview: the template writes the GLM-5 shape (`[gMASK]<sop>`, a reasoning-effort system turn, `<|system|>` / `<|user|>` / `<|assistant|>` / `<|observation|>` turns), the tools
  2. · Beleglinks · GitHub search · Z.ai · pulls · milabench/milabench · @bouthilx
    Auszug
    - GLM-5: layout check before launch, loss from the last stage, checkpoint timing and checksums, crash cleanup; `benchmarks/megatron/dev.yaml`, `scripts/trillium/glm/`.
  3. · Beleglinks · GitHub search · Z.ai · pulls · maximhq/bifrost · @mickgvirtu
    Auszug
    is not `schemas.Anthropic`, and the served model -- `glm-5`, `Kimi-K2`, ... -- is neither opus-4.8 nor Fable), so Claude Code's per-turn reminders were hoisted every
  4. · Beleglinks · GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]
  5. · Beleglinks · GitHub search · Z.ai · pulls · ai-dynamo/frontend-crates · @dundysm
  6. · Beleglinks · GitHub search · Z.ai · pulls · ai-dynamo/dynamo · @indrajit96
    Auszug
    for any DSA model (including DeepSeek V3.2 and GLM-5), or matching `flashmla_kv`/`trtllm` kernels on K3.1's sharded DCP path. Kernels SGLang has not resolved at CLI
  7. · Beleglinks · GitHub search · Z.ai · pulls · ROCm/ATOM · @whx-sjtu
  8. · Beleglinks · GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @moraxu
    Auszug
    class is registered for both `DeepseekV3ForCausalLM` and `DeepseekV32ForCausalLM`; GLM-5 (`GlmMoeDsaForCausalLM`) and Mistral Large 3 subclass it, so exact-class matching excludes them. Kimi K2 declares `DeepseekV3ForCausalLM`
  9. · Beleglinks · GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @kaiyux
    Auszug
    - `modeling_glm5_next_vision.py`: the GLM-5 input processor takes the prefix tokenization cache (the fourth commit). Before, it tokenized every text prompt in full and ignored `enable_tokenization_cache`.
Technische Daten

GLM-5 ist ein Modell von Z.ai mit offenen Modellgewichten, veröffentlicht am 2026-02-12. Das Kontextfenster umfasst 202.752 Tokens. Die maximale Ausgabelänge beträgt 131.072 Tokens. Pro Million Tokens kostet die Eingabe $1,00 und die Ausgabe $3,20.

Kontextfenster
202.752
Maximale Ausgabe
131.072
Eingabe
Text
Ausgabe
Text
Modellgewichte
Offen
Eingabe · USD / 1 Mio. Token
$1,00
Ausgabe · USD / 1 Mio. Token
$3,20
Cache-Eingabe · USD / 1 Mio. Token
$0,20

Fragen

Wie groß ist das Kontextfenster von GLM-5?

Das Kontextfenster umfasst 202.752 Tokens. Die maximale Ausgabelänge beträgt 131.072 Tokens.

Was kostet GLM-5?

Pro Million Tokens kostet die Eingabe $1,00 und die Ausgabe $3,20. Cache-Eingabe kostet $0,20 pro Million.

Sind die Modellgewichte von GLM-5 offen?

Ja. Z.ai veröffentlicht die Modellgewichte.

Wann wurde GLM-5 veröffentlicht?

Am 2026-02-12.