zaiCertifiedReleased 08/26/2026

GLM 5.3 Flash

GLM-5.3-Flash is Z.ai’s native multimodal coding model, featuring 320B total parameters, 18B activated parameters, and a 1M-token context window. Its efficient hybrid attention architecture supports visual coding, tool use, and end-to-end professional workflows across code, browsers, documents, and graphical interfaces.

View API reference ↓
Input / output priceFrom$0.038 / $0.078per 1M
24h uptime99.78%
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "zai/glm-5.3-flash",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
Baseten1M131K0.6 s103 tps$0.15$0.50Read $0.030Write —6 featuresYesYesUSCertified
boundless1.05M1.05M1.8 s79 tps$0.12$0.40Read $0.024Write —6 featuresNoNoGlobalCertified
DeepInfra1.05M1.05M3.8 s194 tps$0.075$0.25Read $0.015Write —6 featuresNoYesGlobalCertified
digitalocean1.05M1.05M0.7 s207 tps$0.15$0.50Read $0.030Write —6 featuresYesYesGlobalCertified
Fireworks1M131K1.5 s140 tps$0.15$0.50Read $0.030Write —6 featuresYesYesUSCertified
friendli1.05M131K0.2 s203 tps$0.15$0.50Read $0.030Write —6 featuresNoNoGlobalCertified
gmicloud1.05M1.05M1.0 s67 tps$0.075$0.25Read $0.015Write —6 featuresNoNoGlobalCertified
inference-net1.05M128K0.3 s159 tps$0.100$0.45Read $0.030Write —6 featuresNoNoGlobalCertified
modal1M1M0.7 s98 tps$0.45$1.50Read $0.090Write —6 featuresYesYesGlobalCertified
morph1.05M1.05M0.9 s15 tps$0.12$0.25Read $0.052Write —6 featuresYesYesGlobalListed
nebius1.05M00.6 s122 tps$0.15$0.50Read $0.030Write —5 featuresYesYesGlobalListed
novita1M128K22.8 s57 tps$0.090$0.30Read $0.018Write —6 featuresNoNoGlobalCertified
parasail1.05M1.05M1.3 s91 tps$0.15$0.50Read $0.030Write —6 featuresYesYesGlobalCertified
pareto1M131K1.5 s89 tps$0.038$0.13Read $0.0075Write —6 featuresNoYesGlobalListed
particle1M131K1.2 s272 tps$0.100$0.40Read $0.030Write —6 featuresYesYesUSCertified
relace1.05M131K1.7 s111 tps$0.040$0.078Read $0.030Write —5 featuresYesYesGlobalCertified
runinfra1.05M1.05M1.8 s353 tps$0.088$0.36Read $0.024Write —5 featuresNoNoGlobalCertified
runware131K131K0.3 s330 tps$0.19$0.59Read $0.045Write —6 featuresYesYesGlobalCertified
sail-research1.05M131K0.6 s58 tps$0.11$0.35Read $0.020Write —6 featuresNoNoGlobalListed
streamlake1.02M128K0.9 s46 tps$0.15$0.50Read $0.030Write —6 featuresNoNoGlobalCertified
telnyx1.05M1.05M0.4 s155 tps$0.14$0.45Read $0.027Write —6 featuresNoNoGlobalListed
tencent1M128K1.8 s58 tps$0.15$0.50Read $0.030Write —7 featuresNoNoGlobalListed
Together AI1M1M0.7 s202 tps$0.15$0.50Read $0.030Write —6 featuresYesYesGlobalCertified
wafer1M1M0.7 s124 tps$0.065$0.24Read $0.064Write —6 featuresYesYesGlobalCertified
zai1M131K2.9 s58 tps$0.15$0.50Read $0.030Write —6 featuresNoNoGlobalCertified

Uptime

24 hours

Request success rate per provider.

Baseten99.94%
boundless99.79%
DeepInfra99.97%
digitalocean99.95%
Fireworks99.99%
friendli100.00%
gmicloud96.37%
inference-net100.00%
modal99.97%
morph99.93%
nebius100.00%
novita100.00%
parasail99.88%
pareto99.99%
particle99.99%
relace99.82%
runinfra99.99%
runware99.99%
sail-research99.92%
streamlake100.00%
telnyx99.67%
tencent100.00%
Together AI99.87%
wafer99.58%
zai99.92%

Throughput

last hour

P50 output tokens per second.

runinfra353 tps
runware330 tps
particle272 tps
digitalocean207 tps
friendli203 tps
Together AI202 tps
DeepInfra194 tps
inference-net159 tps
telnyx155 tps
Fireworks140 tps
wafer124 tps
nebius122 tps
relace111 tps
Baseten103 tps
modal98 tps
parasail91 tps
pareto89 tps
boundless79 tps
gmicloud67 tps
zai58 tps
sail-research58 tps
tencent58 tps
novita57 tps
streamlake46 tps
morph15 tps

Latency

last hour

P50 time to first token.

friendli0.2 s
runware0.3 s
inference-net0.3 s
telnyx0.4 s
Baseten0.6 s
sail-research0.6 s
nebius0.6 s
Together AI0.7 s
wafer0.7 s
modal0.7 s
digitalocean0.7 s
morph0.9 s
streamlake0.9 s
gmicloud1.0 s
particle1.2 s
parasail1.3 s
pareto1.5 s
Fireworks1.5 s
relace1.7 s
tencent1.8 s
runinfra1.8 s
boundless1.8 s
zai2.9 s
DeepInfra3.8 s
novita22.8 s

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "zai/glm-5.3-flash",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. zai/glm-5.3-flash. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. GLM 5.3 Flash supports up to 131,000 output tokens.
reasoning{ effort: 'low' | 'medium' | 'high' }NoReasoning effort, mapped to the provider's native configuration. Reasoning tokens count toward output usage.
toolsTool[]NoFunction definitions the model can call. Tool calls are returned in choices[].message.tool_calls.
Supportedmax_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs

Input limits

InputSourcesLimits
Text—Prompt and response share the 1M-token context window
ImageURL, base64Sent as image_url content parts; counts as input tokens

More models by zai

ModelContextInputOutputCacheRelease
zai/glm-5.3-flashx-legal1M$0.37$1.25Read $0.075Write —11/02/2026
zai/glm-5.3-flashx1M$0.37$1.25Read $0.075Write —09/18/2026
zai/glm-5.3-fast1.05M$2.10$6.60Read $0.21Write —09/02/2026
zai/glm-5.31M$1.40$4.40Read $0.14Write —08/18/2026
zai/glm-5.2-fast1M$2.80$8.80Read $0.56Write —06/23/2026
zai/glm-5.21M$1.40$4.40Read $0.14Write —06/16/2026
zai/glm-5.1203K$1.40$4.40Read $0.26Write —04/07/2026
zai/glm-5v-turbo200K$1.20$4.00Read $0.24Write —04/01/2026
zai/glm-5-turbo203K$1.20$4.00Read $0.24Write —03/15/2026
zai/glm-5203K$1.00$3.20Read —Write —02/12/2026