Z.AIOpen weightsReleased Aug 20, 2026

GLM 5.3 Flash pricing, benchmarks and cost analysis

Compare Z.AI guide

Intelligence#39 / 66

153.1

Epoch Capabilities Index (ECI)range 150.8 to 155.5

Speed#20 / 28

69 tok/s

Median output tokens per second

Cost#2 / 101

$32.85 / mo

In $0.005Out $0.199 per 1MCache discount 0%

Context#3 / 101

Context window, tokens

Ranks are among the 101 models we track (intelligence = Epoch Capabilities Index by Epoch AI, CC BY 4.0; intelligence and speed: among those with data; cost: #1 is cheapest). Monthly cost uses the default workload of 2,000 input and 500 output tokens, 10,000 requests a day, 40% cached.

Comparison summary

On the default workload (2,000 input and 500 output tokens, 10,000 requests a day, 40% cached), GLM 5.3 Flash comes to $32.85 a month, 96% below the $873 median of the 101 models we track. It ranks #2 of 101 on cost, where #1 is the cheapest.

It scores 153.1 on the Epoch Capabilities Index (#39 of 66). Among the 11 other models within 2 points, none costs less, and it costs 97% less than their median ($1,266). Among stable-priced models, nothing that scores as high on ECI is cheaper for this workload.

It generates 69 tokens per second, 17% slower than the median model (84), #20 of 28. Cached input is billed at the full input rate, so prompt caching does not lower the bill. The weights are open, so other hosts can serve it and prices may differ from the provider's own. The batch API cuts the default workload to $47.40 a month. Its listed price changed on five or more days in the last month, usually because the cheapest host changed, so check the provider before relying on the figures above.

Technical specifications

Context window: 1M tokens
Input price: $0.005 / 1M
Cached input price: $0.005 / 1M
Output price: $0.199 / 1M
Cache discount: 0%
Batch API: Available
Batch input / cached / output: $0.050 / $0.010 / $0.180
Open weights: Yes
Release date: Aug 20, 2026
Time to first token: 3.38 s
Price volatility: Volatile (5+ changes in 30 days)

Benchmarks

Best score for this model on each leaderboard, ranked against the other models listed there.

Your monthly bill

Standard

$32.85 / month

Input: $1.80
Cached input: $1.20
Output: $29.85

Batch

$47.40 / month

Input: $18.00
Cached input: $2.40
Output: $27.00

On the default workload the batch API costs $47.40 a month against $32.85 standard.

Price history

Oct 22, 2026Input $0.150 â†’ $0.005â–¼ 97%
Oct 22, 2026Output $0.500 â†’ $0.199â–¼ 60%
Oct 22, 2026Cached input $0.030 â†’ $0.005â–¼ 83%
Oct 21, 2026Input $0.037 â†’ $0.150â–² 305%
Oct 21, 2026Output $0.160 â†’ $0.500â–² 212%
Oct 21, 2026Cached input $0.006 â†’ $0.030â–² 400%
Oct 20, 2026Input $0.048 â†’ $0.037â–¼ 23%
Oct 19, 2026Output $0.200 â†’ $0.160â–¼ 20%
Oct 18, 2026Input $0.025 â†’ $0.048â–² 92%
Oct 18, 2026Output $0.397 â†’ $0.200â–¼ 50%
Oct 18, 2026Cached input $0.008 â†’ $0.006â–¼ 25%
Oct 17, 2026Input $0.015 â†’ $0.025â–² 67%
Oct 17, 2026Output $0.900 â†’ $0.397â–¼ 56%
Oct 17, 2026Cached input $0.011 â†’ $0.008â–¼ 27%
Oct 16, 2026Input $0.150 â†’ $0.015â–¼ 90%
Oct 16, 2026Output $0.500 â†’ $0.900â–² 80%
Oct 16, 2026Cached input $0.030 â†’ $0.011â–¼ 63%
Oct 15, 2026Input $0.036 â†’ $0.150â–² 317%
Oct 15, 2026Output $0.900 â†’ $0.500â–¼ 44%
Oct 15, 2026Cached input $0.011 â†’ $0.030â–² 173%
Oct 14, 2026Input $0.026 â†’ $0.036â–² 38%
Oct 13, 2026Input $0.023 â†’ $0.026â–² 13%
Oct 13, 2026Output $1.20 â†’ $0.900â–¼ 25%
Oct 13, 2026Cached input $0.023 â†’ $0.011â–¼ 52%
Oct 12, 2026Input $0.150 â†’ $0.023â–¼ 85%
Oct 12, 2026Output $0.500 â†’ $1.20â–² 140%
Oct 12, 2026Cached input $0.030 â†’ $0.023â–¼ 23%
Sep 28, 2026Input $0.045 â†’ $0.150â–² 233%
Sep 28, 2026Output $0.140 â†’ $0.500â–² 257%
Sep 28, 2026Cached input $0.010 â†’ $0.030â–² 200%
Sep 27, 2026Input $0.040 â†’ $0.045â–² 12%
Sep 27, 2026Output $0.500 â†’ $0.140â–¼ 72%
Sep 27, 2026Cached input $0.015 â†’ $0.010â–¼ 33%
Sep 26, 2026Input $0.045 â†’ $0.040â–¼ 11%
Sep 26, 2026Output $0.140 â†’ $0.500â–² 257%
Sep 26, 2026Cached input $0.010 â†’ $0.015â–² 50%
Sep 25, 2026Input $0.150 â†’ $0.045â–¼ 70%
Sep 25, 2026Output $0.500 â†’ $0.140â–¼ 72%
Sep 25, 2026Cached input $0.050 â†’ $0.010â–¼ 80%
Sep 22, 2026Input $0.090 â†’ $0.150â–² 67%
Sep 22, 2026Output $0.300 â†’ $0.500â–² 67%
Sep 22, 2026Cached input $0.018 â†’ $0.050â–² 178%
Sep 17, 2026Input $0.100 â†’ $0.090â–¼ 10%
Sep 17, 2026Output $0.333 â†’ $0.300â–¼ 10%
Sep 17, 2026Cached input $0.020 â†’ $0.018â–¼ 10%
Sep 16, 2026Input $0.150 â†’ $0.100â–¼ 33%
Sep 16, 2026Output $0.500 â†’ $0.333â–¼ 33%
Sep 16, 2026Cached input $0.030 â†’ $0.020â–¼ 33%
Sep 13, 2026Input $0.075 â†’ $0.150â–² 100%
Sep 13, 2026Output $0.250 â†’ $0.500â–² 100%
Sep 13, 2026Cached input $0.015 â†’ $0.030â–² 100%
Sep 12, 2026Input $0.150 â†’ $0.075â–¼ 50%
Sep 12, 2026Output $0.500 â†’ $0.250â–¼ 50%
Sep 12, 2026Cached input $0.030 â†’ $0.015â–¼ 50%
Sep 10, 2026Input $0.075 â†’ $0.150â–² 100%
Sep 10, 2026Output $0.250 â†’ $0.500â–² 100%
Sep 10, 2026Cached input $0.015 â†’ $0.030â–² 100%