Bertrande

Catalogue / OpenRouter / Z.ai: GLM 5.3 Flash (sold by OpenRouter)

Z.ai: GLM 5.3 Flash (sold by OpenRouter)

Prices and limits, each value carrying the date it was observed and the source it came from.

As of 1 November 2026, GLM 5.3 Flash costs $0.0285 per million input tokens and $0.0923 per million output tokens on OpenRouter. Observed on OpenRouter's own published price list on 1 November 2026. This is OpenRouter's resale price, not the model vendor's list price.

Input $0.0285 per 1M
Output $0.0923 per 1M
Context 1 048 576 tokens

What does GLM 5.3 Flash cost?

ParameterValueUnit ObservedSourceProof
Input price $0.0285 USD per 1M tokens 1 November 2026
checked 3 November 2026
official API L1 38debd9be3a7
Output price $0.0923 USD per 1M tokens 1 November 2026
checked 3 November 2026
official API L1 38debd9be3a7
Context window 1 048 576 tokens 28 October 2026
checked 3 November 2026
official API L1 92c29030edee
Maximum output 131 072 tokens 31 October 2026
checked 3 November 2026
official API L1 9ebec09cfd65
Agentic index (Artificial Analysis) 50.9 index 0-100 1 November 2026
checked 3 November 2026
official API L4 f9f3ee2bcea1
Coding index (Artificial Analysis) 71.5 index 0-100 29 October 2026
checked 3 November 2026
official API L4 bed903fd04f5
Intelligence index (Artificial Analysis) 27.8 index 0-100 30 October 2026
checked 3 November 2026
official API L4 7b501cd7e861
Input modalities
  • image
  • text
  • video
list 31 October 2026
checked 3 November 2026
official API L1 aa4b1be8e631
Output modalities
  • text
list 31 October 2026
checked 3 November 2026
official API L1 aa4b1be8e631
Cache read price $0.0285 USD per 1M tokens 1 November 2026
checked 3 November 2026
official API L1 38debd9be3a7
Listed since 2026-08-26 date 31 October 2026
checked 3 November 2026
official API L1 aa4b1be8e631
Supported parameters
  • frequency_penalty
  • include_reasoning
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • parallel_tool_calls
  • presence_penalty
  • reasoning
  • reasoning_effort
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p
list 3 November 2026
checked 3 November 2026
official API L1 2247aa6a02e3

How reliable is each host behind GLM 5.3 Flash?

The cheapest offer is not a bargain if it is down. OpenRouter routes traffic to several upstream hosts for this model and publishes the availability its own router recorded over the last day for each of them. Least reliable first.

HostAvailability, last day Observed
baseten/fp8/us 0.00 % 23 October 2026
modal/nvfp4 0.00 % 22 October 2026
darkbloom/fp4 77.65 % 3 November 2026
siliconflow/fp8 89.43 % 3 November 2026
relace/fp4 94.10 % 3 November 2026
io-net/fp8 94.44 % 5 October 2026
nebius/fp4 96.55 % 3 November 2026
morph 97.09 % 26 September 2026
reka/fp8 97.84 % 24 September 2026
phala/fp8 98.19 % 7 October 2026
streamlake 98.58 % 7 September 2026
together 98.61 % 3 November 2026
mistral 98.66 % 3 November 2026
cloudflare 98.92 % 8 October 2026
makora 98.94 % 3 November 2026
coreweave/fp8 99.24 % 15 September 2026
deepinfra/fp8 99.51 % 4 September 2026
open-inference/fp4 99.58 % 2 November 2026
atlas-cloud/fp8 99.64 % 3 November 2026
primeintellect 99.64 % 3 November 2026
cohere 99.65 % 3 November 2026
parasail/fast 99.65 % 22 October 2026
tenstorrent/fp8 99.75 % 31 October 2026
modal/fp8 99.76 % 24 September 2026
baseten/fp8 99.79 % 2 November 2026
streamlake/fp8 99.79 % 3 November 2026
parasail/fp8 99.83 % 1 October 2026
novita/fp8 99.86 % 3 November 2026
sail-research/fp8 99.87 % 29 September 2026
nextbit/fp4 99.92 % 3 November 2026
coreweave/nvfp4 99.93 % 2 November 2026
fireworks 99.93 % 3 November 2026
gmicloud/fp8 99.93 % 2 November 2026
parasail/fp4 99.93 % 3 November 2026
relace 99.93 % 30 October 2026
wafer/nvfp4 99.93 % 3 November 2026
wafer/us 99.93 % 3 November 2026
z-ai/fp8 99.93 % 3 November 2026
nextbit/fp8 99.97 % 6 October 2026
crusoe/fp4 100.00 % 30 October 2026
decart/fp4 100.00 % 16 October 2026
deepinfra/fp4 100.00 % 31 October 2026
dekallm 100.00 % 12 October 2026
digitalocean 100.00 % 30 October 2026
fireworks/us 100.00 % 3 November 2026
friendli 100.00 % 2 November 2026
inceptron/fp8 100.00 % 2 November 2026
inference-net/fp4 100.00 % 30 October 2026
inference-net/us 100.00 % 30 October 2026
modal/fp4 100.00 % 28 October 2026
morph/fp8 100.00 % 31 October 2026
near-ai/fp8 100.00 % 3 November 2026
particle-ai/nvfp4 100.00 % 30 October 2026
phala/nvfp4 100.00 % 3 November 2026
reka 100.00 % 3 November 2026
sail-research/fp4 100.00 % 2 November 2026
sail-research/us 100.00 % 2 November 2026
venice 100.00 % 3 November 2026
wafer 100.00 % 15 October 2026

This is availability as OpenRouter's router observed it, not as you would measure it calling the host directly: the network path is not the same. We read it once a day and keep every reading, so a host that was unreliable last August can still be shown to have been unreliable last August.

We publish no time to first token and no throughput. OpenRouter's API carries fields for both and leaves them empty on every endpoint we have read, and we will not fill a number the source does not give.

How has GLM 5.3 Flash moved?

Output price, 60 observations between 26 August 2026 and 1 November 2026. Range $0.0625 to $1.20. Drawn as a step: a value holds until the next observation, we do not interpolate between them.

How capable is GLM 5.3 Flash?

IndexScoreObservedSource
Agentic index (Artificial Analysis)50.9 1 November 2026 Artificial Analysis L4
Coding index (Artificial Analysis)71.5 29 October 2026 Artificial Analysis L4
Intelligence index (Artificial Analysis)27.8 30 October 2026 Artificial Analysis L4

These indices are produced by Artificial Analysis and relayed through the catalogue API. They are not our own measurement. See cost per point of capability to compare them against price.

Has GLM 5.3 Flash changed price?

DetectedParameter FromToChange
30 September 2026 Context window 1 310 720 1 048 576 -20.0%
21 September 2026 Supported parameters n/a n/a changed
20 September 2026 Agentic index (Artificial Analysis) 51.2 50.9 -0.6%
17 September 2026 Supported parameters n/a n/a changed
16 September 2026 Supported parameters n/a n/a changed
8 September 2026 Agentic index (Artificial Analysis) 51.5 51.2 -0.6%
26 August 2026 Context window 1 048 576 1 310 720 +25.0%

What did GLM 5.3 Flash cost before we started reading?

Public archived copies of the seller's catalogue show the same output price, $0.250, from 28 August 2026 onwards.

CapturedPrice Per 1M tokensArchived copy
28 August 2026Input $0.075 view the capture
28 August 2026Output $0.250 view the capture

These figures come from 1 public archived copies of the seller's catalogue, not from our own reading: each row shows the day of the capture and links to it, so you can check it. Identical consecutive values are folded into one row, dated by the first capture that shows them.

What does GLM 5.3 Flash cost elsewhere?

We track this model at 7 sellers. The same model rarely costs the same everywhere, and the difference is not visible from any single seller's catalogue.

Compare GLM 5.3 Flash across 7 sellers, side by side, or see every model tracked at more than one seller.

Other services from OpenRouter

All OpenRouter services

Where these figures come from

Source: OpenRouter. Every figure on this page was read from OpenRouter's own published price list, and every row above links straight back to it. We publish factual values with attribution, we do not reproduce OpenRouter's content, and we send readers to them. If you publish this source and want us to stop tracking it, write to contact@bertrande.com and we will act on it without argument.

How is this page verified?

Every figure above comes from OpenRouter's own published price list, which we rank as a level 1 source. We re-check it every 6 hours. Each observation stores the exact source URL and a SHA-256 fingerprint of the source content at that moment, which is what lets us prove what the source said on a given day.

The Proof column shows the first twelve characters of the SHA-256 fingerprint of the source content at the moment we read it. Hover it for the full value. It is what lets us demonstrate later what the source said on a given day, after that page has changed or vanished. The full fingerprints are in data.json.

No value on this page was produced, estimated or completed by a language model. Where we do not have a verified figure, the row is absent rather than filled in. Read the full methodology, or report an error.

Take the data, or watch this page

This page is available as data.json (including the full observation history of every parameter) and data.csv, under CC-BY-4.0, free, with attribution. See all downloads.

Want to know when this changes? Point a feed reader or a script at the Atom feed, which carries every confirmed change and is rebuilt hourly, or poll this page's data.json, where every figure carries its observation date and the fingerprint of its source. Both work today and need no address.

Email alerts are open, and nothing is sent until you confirm from a link we email you. Subscribe, or see what an alert looks like.