GLM-5.3 Flash

Z.aiKey glm-5.3-flashAlso reported as z-ai/glm-5.3-flash, combo/glm-5.3-flash, zai/glm-5.3-flash, cutad/glm-5.3-flash, zhipu/glm-5.3-flash, openrouter/z-ai/glm-5.3-flash, zai-org/glm-5.3-flash, b.ai/glm-5.3-flash, ollama-cloud/glm-5.3-flash, cutad/cbcn/glm-5.3-flash, glm/glm-5.3-flash, @cf/zai-org/glm-5.3-flash, cbcn/glm-5.3-flash, workbuddy/glm-5.3-flash, sk/glm-5.3-flash, bai/glm-5.3-flash, opencode-go/glm-5.3-flash, sumo/glm-5.3-flash, inco/glm-5.3-flash, zcode/glm-5.3-flash

Rank
#13
by active users
Active users
50
Down 15 from 65 active users in the previous 7 days. vs previous 7 days
Adoption
8.4%
of 598 accounts
Tokens
12.2B
cache included
Est. cost
$311
at public list prices
First seen
Jun 11, 2026
in any submission

Nov 7–13, 2026 (UTC)598 accounts100% of tokens from an identified modelData through Nov 13, 2026, 01:19 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

4 active users on Nov 13, 2026

Daily active users for GLM-5.3 Flash, Nov 7, 2026 to Nov 13, 2026. Peak 26. Use the left and right arrow keys to read each day.30150
Show daily values
Daily active users and tokens for GLM-5.3 Flash
Date (UTC)Active usersTokens
Nov 7, 2026243.1B
Nov 8, 2026262.5B
Nov 9, 2026262.4B
Nov 10, 2026222B
Nov 11, 2026201.4B
Nov 12, 202618771.8M
Nov 13, 20264113.9M

Token mix

How the 12.2B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input2.6%
  • Output0.3%
  • Cache read97%
  • Cache write<0.1%
  • Reasoning<0.1%

Agents that carry GLM-5.3 Flash

Each agent's share of this model's tokens, and how many accounts used the model through it.

  1. Hermes Agent46% of this model's tokens10active users
  2. ZCode23% of this model's tokens7active users
  3. Oh My Pi13% of this model's tokens5active users
  4. OpenCode6.6% of this model's tokens11active users
  5. Claude Code4.4% of this model's tokens4active users
  6. Pi4.3% of this model's tokens8active users
  7. WorkBuddy1.3% of this model's tokens4active users
  8. DeepSeek Harness1.0% of this model's tokens2active users
  9. Senpi (OmO Native)0.2% of this model's tokens2active users
  10. Gajae Code0.1% of this model's tokens1active users
  11. Amp<0.1% of this model's tokens2active users
  12. Codex CLI<0.1% of this model's tokens1active users
  13. Cherry Studio<0.1% of this model's tokens1active users
  14. cc-mirror/python-urllib<0.1% of this model's tokens1active users
  15. Synthetic<0.1% of this model's tokens1active users
  16. cc-mirror/curl<0.1% of this model's tokens1active users
  17. cc-mirror/mozilla<0.1% of this model's tokens1active users

Benchmarks

The best result for GLM-5.3 Flash in each benchmark Tokscale tracks. Each benchmark has its own unit, run conditions and source, so compare a score only with other models on the same benchmark. Rank is among the models Tokscale matched in that benchmark. Agent rows also show Tokscale usage through that agent, side by side with the score. Usage does not explain the score.

All benchmarks
  • Epoch Capabilities IndexOverall · Epoch AI
    153.8
    Rank #52 of 158 matched modelsNo conditions reportedModel released Aug 20, 2026Source: epoch.ai (opens in a new tab)
  • Terminal-Bench 4.1Agentic coding · Terminal-Bench
    35.4%
    Rank #12 of 23 matched modelsNo reasoning · Claude CodePublished Nov 3, 2026Source: tbench.ai (opens in a new tab)

    Tokscale usage: Claude Code carried 4.4% of GLM-5.3 Flash tokens in the last 7 days (4 active users).

  • CursorBenchAgentic coding · Cursor, collected by Epoch AI
    36.8%
    Rank #18 of 21 matched modelsMaxModel released Aug 20, 2026Source: cursor.com (opens in a new tab)
    Show 2 more results with other run conditionsHide the other results
    • Listed as GLM 5.3 Flash High
      31.1%
      HighModel released Aug 20, 2026Source: cursor.com (opens in a new tab)
    • Listed as GLM 5.3 Flash Low
      26.9%
      LowModel released Aug 20, 2026Source: cursor.com (opens in a new tab)
  • DeepSWEAgentic coding · Datacurve, collected by Epoch AI
    63.4%
    Rank #13 of 26 matched modelsMax · mini-swe-agentModel released Aug 20, 2026Source: deepswe.datacurve.ai (opens in a new tab)
  • FrontierSWEAgentic coding · FrontierSWE, collected by Epoch AI
    18.1%
    Rank #19 of 23 matched modelsMax · proximusModel released Aug 20, 2026Source: frontierswe.com (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,607
    Rank #25 of 110 matched modelsNo conditions reportedPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • Agent ArenaAgents · LMArena
    −0.02
    Rank #32 of 48 matched modelsArena Agent ModePublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    90.2%
    Rank #46 of 160 matched modelsMaxRun date Aug 26, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 96.5%, and Epoch AI estimates the reachable maximum at 97%. Differences between top models are small.

  • FrontierMath Tiers 1–3 (v2)Reasoning · Epoch AI
    55.8%
    Rank #50 of 90 matched modelsMaxRun date Aug 27, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 95.1%, and Epoch AI estimates the reachable maximum at 95%. Differences between top models are small.

Not evaluated: Humanity's Last Exam, SimpleQA Verified. A missing result is not a score of zero.

Pricing

List prices from models.dev in US dollars per 1M tokens, retrieved Nov 12, 2026. Z.AI is the lab's own API and the reference price for the estimates below.

Price at real agent usageEstimate at list prices

What 1M tokens cost at the reference list price when they split into input, output and cache the way Tokscale users' agents used them. It is not what anyone paid.

At this model's mix
$0.03
Est. per 1M tokens
97% cache reads
At the community mix
$0.03
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$0.24
Per 1M tokens at list prices
No cache

Cache reads were 97% of GLM-5.3 Flash tokens in the last 7 days and 96% of all tokens. The 3:1 blend, (3 × input + output) ÷ 4, is the usual comparison and ignores cache.

Assumptions

  • Z.AI list prices per 1M tokens: input $0.15, output $0.50, cache read $0.03, cache write $0.
  • This model's mix is its own input, output, cache and reasoning tokens in the last 7 days.
  • The community mix is the tokens of every identified model in the last 7 days.
  • This is an estimate at list prices, not what anyone paid.
  • Reasoning tokens are priced as output.
  • Long-context tiers, batch pricing and discounts are not applied.
  • Token mixes come from public Tokscale submissions. Hidden accounts are excluded.

List prices by provider

  • Z.AIReferenceglm-5.3-flash
    $0.15 input per 1M tokens$0.50 output per 1M tokens$0.03 cache read per 1M tokens$0 cache write per 1M tokens1M tokens of context
  • OpenRouterz-ai/glm-5.3-flash
    $0.04 input per 1M tokens$0.08 output per 1M tokens$0.03 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Vercel AI Gatewayzai/glm-5.3-flash
    $0.15 input per 1M tokens$0.50 output per 1M tokens$0.03 cache read per 1M tokensCache write not listed1M tokens of context
  • Together AIzai-org/GLM-5.3-Flash
    $0.15 input per 1M tokens$0.50 output per 1M tokens$0.03 cache read per 1M tokensCache write not listed1.05M tokens of context
Show 3 more providersShow fewer providers
  • Fireworks AIaccounts/fireworks/models/glm-5p3-flash
    $0.15 input per 1M tokens$0.50 output per 1M tokens$0.03 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Deep Infrazai-org/GLM-5.3-Flash
    $0.15 input per 1M tokens$0.50 output per 1M tokens$0.03 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Basetenzai-org/GLM-5.3-Flash
    $0.15 input per 1M tokens$0.50 output per 1M tokens$0.03 cache read per 1M tokensCache write not listed1.05M tokens of context

Specs

From models.dev (MIT), retrieved Nov 12, 2026, as the lab or the first listed provider reports them. A dash means models.dev does not list the value.

Context window
1M tokens
Max output
131K tokens
Input
Text, Image, Video, PDF
Output
Text
Knowledge cutoff
— not listed
Release date
Aug 26, 2026
Open weights
Yes
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used GLM-5.3 Flash most in this period, by tokens. Hidden accounts are never listed.

  1. 1Benjamin Hodgens@bhodgens5.2Btokens$169est. cost5active days$169 est. cost · 5 active days
  2. 2LinYU@rinchao07212.4Btokens—est. cost7active daysno price · 7 active days
  3. 3Brad Lishman@bradlishman1.5Btokens$51est. cost5active days$51 est. cost · 5 active days
  4. 4Arthur Brownlee IV@nulluserid602.6Mtokens<$1est. cost5active days<$1 est. cost · 5 active days
  5. 5Daniel Alvim@limineol420.7Mtokens$15est. cost3active days$15 est. cost · 3 active days
  6. 6Gordon Lee@g0rdonL420.2Mtokens$18est. cost6active days$18 est. cost · 6 active days
  7. 7siddicky@siddicky402.5Mtokens$9est. cost6active days$9 est. cost · 6 active days
  8. 8WaifuAI@thewaifuai148.3Mtokens$5est. cost3active days$5 est. cost · 3 active days
  9. 9Christopher Butler@techsaint131.5Mtokens$7est. cost4active days$7 est. cost · 4 active days
  10. 10fanziyun@fanziyun128.7Mtokens$4est. cost3active days$4 est. cost · 3 active days

More from Z.ai

Other Z.ai models in the same period, by active users.

  1. GLM-5.37.5% adoption45active users
  2. GLM-5.3 Flash Free2.0% adoption12active users
  3. GLM-5.20.7% adoption4active users
  4. GLM-5 3 Flash0.5% adoption3active users
  5. GLM-5.3 Flash Ultrafast0.3% adoption2active users
  6. GLM-5.3 Flashx0.3% adoption2active users
All models

Sources and attribution

Each score keeps its own source, unit and run conditions. Tokscale does not combine benchmarks into one score, and a missing score means the model was not evaluated, not that it scored zero.

  • Epoch AIEpoch Capabilities Index, Epoch's own runs and the external results it collects.CC BY 4.0 · Retrieved Nov 12, 2026 · Data through Nov 9, 2026Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from https://epoch.ai/benchmarks.
  • LMArenaWebDev Arena and Agent Arena leaderboards.CC BY 4.0 · Retrieved Oct 21, 2026 · Data through Oct 19, 2026LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), Hugging Face.
  • Terminal-BenchTerminal-Bench 4.1 official leaderboard rows (results only, no task content).Terms not stated · Retrieved Nov 12, 2026 · Data through Nov 11, 2026Terminal-Bench 4.1 leaderboard, tbench.ai. Every score links back to the leaderboard.
  • models.devSpecs and list prices per provider.MIT · Retrieved Nov 12, 2026models.dev, an open catalog of AI models (github.com/anomalyco/models.dev).
  • TokscaleActive users, tokens and token mix from public Tokscale submissions. Hidden accounts are excluded.How we count