LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GLM-4.7-Flash

zhipuai·zhipuai/glm-4.7-flash·GA·Open weights·glm-flash series
Budget GLM lane for fast coding help, routing, and everyday automation

Specs & pricing

Input / output per 1M tokens
Official price·Z.AI
$0 / $0
Blended $0 · Cache read $0
Lowest paid·Eden AIGateway
$0.06 / $0.40
Blended $0.15 · 2.2× spread
8 more $0 channels
Context
200,000
Output limit
131,072
Knowledge cutoff
2025-04
Released / updated
2026-01-19 / 2026-01-19
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
Text
Weights
Hugging Face

GLM-4.7-Flash by zhipuai is offered by 28 providers on this page. Public prices are shown for 20 of them. Its official list price is $0 per 1M tokens. No paid channel is priced below the official list price. Prices vary about 2.2× across the providers that host it. It also has 8 free ($0) channels; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Median output speed is 93 tokens per second, with 1.64s to the first token.

The context window is 200,000 tokens at the reference host, but hosts report different limits, from 131,072 to 203,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Its training knowledge cuts off at 2025-04.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier Reasoning

Intelligence—
Value—
Output speed93 tok/s
TTFT1.64 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 28 providers20 with public prices · 8 free

  • ProviderInput / Output
  • Z.AIOfficialFirst-party
    Free
    Cache read $0Context 200,000Output limit 131,072
  • Zhipu AIOfficialFirst-party
    Free
    Cache read $0Context 200,000Output limit 131,072
  • PendraGateway
    Free
    Context 200,000Output limit 131,072
  • AIHubMixGateway
    glm-4.7-flash-free
    Free
    Context 200,000Output limit 131,072
  • ZenMuxGateway
    z-ai/glm-4.7-flash-free
    Free
    Cache read $0Context 200,000Output limit 128,000
  • Hugging FaceCloud
    zai-org/GLM-4.7-Flash
    Free
    Context 200,000Output limit 128,000
  • KenariGateway
    glm-4-7-flash:free
    Free
    Context 200,000Output limit 131,072
  • EmpirioLabs AIGateway
    glm-4-7-flash
    Free
    Context 202,752 ⚠Output limit 131,072
  • Eden AIGateway
    deepinfra/zai-org/GLM-4.7-Flash
    $0.06 / $0.40
    Cache read $0.01Context 202,752 ⚠Output limit 131,072
  • Deep InfraCloud
    zai-org/GLM-4.7-Flash
    $0.06 / $0.40
    Cache read $0.01Context 202,752 ⚠Output limit 16,384deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Z.AIOfficialFirst-partyFree$0$0200,000131,072
Zhipu AIOfficialFirst-partyFree$0$0200,000131,072
PendraGatewayFree——200,000131,072
AIHubMix
glm-4.7-flash-free
GatewayFree——200,000131,072
ZenMux
z-ai/glm-4.7-flash-free
GatewayFree$0—200,000128,000
Hugging Face
zai-org/GLM-4.7-Flash
CloudFree——200,000128,000
Kenari
glm-4-7-flash:free
GatewayFree——200,000131,072
EmpirioLabs AI
glm-4-7-flash
GatewayFree——202,752 ⚠131,072
Eden AI
deepinfra/zai-org/GLM-4.7-Flash
Gateway$0.06$0.40$0.01—202,752 ⚠131,072
Deep Infra
zai-org/GLM-4.7-Flash
Cloud$0.06$0.40$0.01—202,752 ⚠16,384deprecated

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

Toggle (on / off)effort = noneeffort = higheffort = loweffort = medium

Interleaved thinking (reasoning between tool calls) is declared by 12 of 28 providers.

14 / 28 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Eden AI$26.00
2Deep Infra$26.00
3Jiekou.AI$26.80
4Novita AI$26.80
5NanoGPT$28.47
6NanoGPT$28.47

8 more channels offer $0 (Z.AI, Zhipu AI, Pendra etc.); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.15$02026-08-052026-08-23
2026-08-23Input list $0Output list $0Min blended $0.15

Benchmark1 items

NameConditionsScoreMetricSource
SWE-Bench Verified—59.2resolvedSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

GLM 5.3 Flash Uncensoredsame series—GLM Flash Latestsame series—GLM-5.3-Flashsame series$0.15 / $0.50GLM-4.7same lab$0.60 / $2.20GLM-4.7-FlashXsame lab$0.07 / $0.40
Data partly from models.dev (MIT) · Z.AI official docs ↗