zaiCertifiedReleased 08/18/2026

GLM 5.3

GLM 5.3 delivers comprehensive advancements in complex software engineering and agent capabilities. It uses the same base model as GLM-5.2, with all improvements driven by post-training.

View API reference ↓
Input / output priceFrom$0.070 / $1.40per 1M
24h uptime99.02%
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",
  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
alibaba1M128K0.8 s69 tps$1.40$4.40Read $0.28Write —5 featuresYesYesGlobalCertified
Amazon Bedrock1M128K0.3 s339 tps$1.68$5.28Read $0.31Write $2.106 featuresYesYesUSListed
Baseten1M1M1.5 s122 tps$1.40$4.40Read $0.14Write —5 featuresYesYesUSCertified
boundless1.05M1.05M0.4 s287 tps$1.12$3.52Read $0.14Write —4 featuresNoNoGlobalCertified
crusoe1.05M1.05M15.4 s204 tps$1.40$4.40Read $0.26Write —5 featuresNoNoGlobalCertified
DeepInfra1.05M1.05M0.9 s93 tps$0.56$2.50Read $0.13Write —5 featuresNoYesGlobalCertified
digitalocean1.05M1.05M0.2 s263 tps$1.40$4.40Read $0.26Write —5 featuresYesYesGlobalCertified
Fireworks1M262K0.3 s126 tps$1.40$4.40Read $0.26Write —5 featuresYesYesUSCertified
friendli1M1M0.2 s112 tps$1.26$3.96Read $0.23Write —5 featuresNoNoGlobalCertified
gmicloud1.05M1.05M1.3 s95 tps$0.70$2.20Read $0.13Write —5 featuresNoNoGlobalCertified
inceptron1.05M1.05M0.5 s202 tps$1.25$4.40Read $0.26Write —5 featuresNoYesGlobalCertified
inference-net1M131K0.4 s158 tps$0.90$3.00Read $0.15Write —5 featuresNoNoGlobalCertified
modal1M1M2.9 s218 tps$1.40$4.40Read $0.26Write —5 featuresYesYesGlobalCertified
morph1.05M1.05M0.4 s72 tps$0.74$3.00Read $0.25Write —5 featuresYesYesGlobalListed
novita1M128K0.9 s190 tps$0.91$2.86Read $0.17Write —5 featuresNoNoGlobalListed
parasail1M1M1.6 s270 tps$1.40$4.40Read $0.26Write —5 featuresYesYesGlobalCertified
relace1.05M131K3.1 s121 tps$0.070$4.38Read $0.070Write —4 featuresYesYesGlobalCertified
runinfra1.05M1.05M0.4 s151 tps$1.04$3.36Read $0.10Write —5 featuresNoNoGlobalListed
runware1.05M1.05M0.8 s165 tps$1.73$5.79Read $0.31Write —5 featuresYesYesGlobalCertified
sail-research1.05M1.05M0.4 s154 tps$0.98$3.08Read $0.18Write —5 featuresNoNoGlobalListed
streamlake1.02M128K1.1 s111 tps$1.40$4.40Read $0.26Write —5 featuresNoNoGlobalCertified
subconscious1M128K0.3 s178 tps$1.40$4.40Read $0.26Write —5 featuresNoNoGlobalListed
telnyx1.05M1.05M1.6 s55 tps$1.25$4.00Read $0.24Write —5 featuresNoNoGlobalListed
tencent1M128K1.7 s30 tps$1.40$4.40Read $0.26Write —5 featuresNoNoGlobalListed
Together AI1M1M0.5 s117 tps$1.40$4.40Read $0.26Write —5 featuresYesYesGlobalCertified
wafer1.05M1.05M0.3 s—$0.18$1.40Read $0.18Write —5 featuresYesYesUSCertified
zai1M128K1.1 s99 tps$1.40$4.40Read $0.26Write —5 featuresNoNoGlobalCertified

Uptime

24 hours

Request success rate per provider.

alibaba100.00%
Amazon Bedrock98.45%
Baseten99.98%
boundless100.00%
crusoe77.00%
DeepInfra99.96%
digitalocean100.00%
Fireworks100.00%
friendli100.00%
gmicloud99.59%
inceptron99.93%
inference-net100.00%
modal99.99%
morph100.00%
novita99.19%
parasail100.00%
relace99.88%
runinfra100.00%
runware100.00%
sail-research100.00%
streamlake100.00%
subconscious100.00%
telnyx99.66%
tencent100.00%
Together AI99.90%
wafer99.99%
zai100.00%

Throughput

last hour

P50 output tokens per second.

Amazon Bedrock339 tps
boundless287 tps
parasail270 tps
digitalocean263 tps
modal218 tps
crusoe204 tps
inceptron202 tps
novita190 tps
subconscious178 tps
runware165 tps
inference-net158 tps
sail-research154 tps
runinfra151 tps
Fireworks126 tps
Baseten122 tps
relace121 tps
Together AI117 tps
friendli112 tps
streamlake111 tps
zai99 tps
gmicloud95 tps
DeepInfra93 tps
morph72 tps
alibaba69 tps
telnyx55 tps
tencent30 tps
wafer—

Latency

last hour

P50 time to first token.

friendli0.2 s
digitalocean0.2 s
subconscious0.3 s
wafer0.3 s
Fireworks0.3 s
Amazon Bedrock0.3 s
boundless0.4 s
inference-net0.4 s
morph0.4 s
sail-research0.4 s
runinfra0.4 s
Together AI0.5 s
inceptron0.5 s
runware0.8 s
alibaba0.8 s
DeepInfra0.9 s
novita0.9 s
streamlake1.1 s
zai1.1 s
gmicloud1.3 s
Baseten1.5 s
telnyx1.6 s
parasail1.6 s
tencent1.7 s
modal2.9 s
relace3.1 s
crusoe15.4 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",
  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. 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 supports up to 1,000,000 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

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-5.3-flash1M$0.15$0.50Read $0.030Write —08/26/2026
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