Skip to main content
Watch: Stop Building Apps. Build Tools for AI Agents

Open-weight API pricing - last verified

GLM-5.3: where to run it and what it costs

10 offers from 9 providers list GLM-5.3 at a per-token price. The lowest listed input price is $0.563 per 1M input tokens at DeepInfra (GLM-5.3), card shows 38% off, with output at $2.50. First-party, Z.ai lists $1.40 input and $4.40 output per 1M tokens. Prices are as listed on October 18, 2026; they change often and are not a benchmark.

753.3B, mixture of experts. Native context 1,048,576 tokens, per our local-models record (from the Hugging Face model card).

Every offerQuotesRun it yourselfAll open-weight models

Offers
10
Providers
9
Lowest listed input
$0.563
First-party input
$1.40

Per-token prices

Every GLM-5.3 offer, sorted by input price

Each row is one build as the provider lists it, with its own model ID: dated snapshots, Fast and turbo builds and regional rows are never merged. Sorted by listed input price in USD per 1M input tokens; every price is in that same unit. Not stated means the provider's page does not say.
10 hosted offers for GLM-5.3, sorted by listed input price in USD per 1M input tokens
Provider and model IDInputUSD per 1M tokensOutputUSD per 1M tokensCached inputUSD per 1M tokensContext servedas the provider lists itQuantizationStatusSource
DeepInfrazai-org/GLM-5.3Quotes for this row$0.563Card shows 38% off - may be a temporary discount$2.50$0.1251,048,576Inferred from an unlabelled card tagfp4Not stateddeepinfra.com
Z.ai (first-party)GLM-5.3First-partyQuotes for this row$1.40$4.40$0.26Not statedNot statedNot stateddocs.z.ai
Together AIzai-org/GLM-5.3Quotes for this row$1.40$4.40$0.261,048,575FP4Serverless Inferencetogether.ai
Fireworks AIglm-5p3Listed as: GLM 5.3Quotes for this row$1.40$4.40$0.26Not statedNot statedStandarddocs.fireworks.ai
Basetenzai-org/GLM-5.3Quotes for this row$1.40$4.40$0.141048kNot statedModel APIsbaseten.co
Novitazai-org/glm-5.3Listed as: GLM 5.3Quotes for this row$1.40$4.40$0.261Mfp8Not statednovita.ai
Cloudflare Workers AI@cf/zai-org/glm-5.3Quotes for this row$1.40$4.40$0.26Not statedNot statedNot stateddevelopers.cloudflare.com
Mistral AI (third-party hosted)Z.ai GLM 5.3Quotes for this row$1.40$4.40$0.14Not statedNot statedThird-party models hosted by Mistraldocs.mistral.ai
Amazon BedrockNo API model ID on the pricing pageListed as: GLM 5.3Quotes for this row$1.68$5.28$0.312Not statedNot statedGlobal CRISaws.amazon.com
Basetenzai-org/GLM-5.3-FastListed as: GLM-5.3 FastQuotes for this row$2.10$6.60$0.211048kNot statedModel APIsbaseten.co
First-party
The model's own developer selling its API.
Peak-hour price
DeepSeek's listed price during its peak hours; off-peak is half, per its page. Alibaba's busy-hour rows work the same way.
Card shows N% off
A discount tag sits beside the price on the provider's catalog card. The number is the discounted one and may be temporary.
Inferred
Our reading, not the page's words: a name-only model match, a region taken from table order, or a context figure from an unlabelled tag.
Below native
The provider serves a shorter context than the model's native window in our local-models data.
Preview
The provider lists the model as a preview, for evaluation rather than production.

Evidence

The quote behind every value

Each value is copied from the provider's own page; one quote that backs several values shows once.

DeepInfra

GLM-5.3

Model ID, Variant, Input, Output, Cached input

“$0.125 cached, $0.563 in, $2.50 out / 1M”
deepinfra.com

Context served, Quantization

“Zero retention fp4 1,048,576”
deepinfra.com

Discount tag on the same card

“38% off $0.125 cached, $0.563 in, $2.50 out / 1M”
deepinfra.com
“promotional pricing, 38% off already applied”
Model page - deepinfra.com
  • Inferred from an unlabelled card tag. Context inferred from an unlabelled card tag: the 1,048,576 figure is a header chip on the model page with no Context label.

Not stated

  • Batch: No per-model batch price listed on the pricing page.
  • Status: No availability tier or release-stage label stated for this offer on the pages used.

Source notes: Not on the main /pricing table; price is from the text-generation catalog card.

Z.ai (first-party)

GLM-5.3

Model ID, Variant, Input, Output, Cached input

“GLM-5.3 $1.4 $0.26 Limited-time Free $4.4”
docs.z.ai

Input column, Output column, Cached input column

“Model Input Cached Input Cached Input Storage Output”
docs.z.ai

Not stated

  • Batch: No per-model batch price listed on the pricing page.
  • Context served: Served context length not stated on the pages used.
  • Quantization: Quantization not stated on the pages used.
  • Status: No availability tier or release-stage label stated for this offer on the pages used.

Source notes: Cached input storage listed as "Limited-time Free". The table shows the display name GLM-5.3; the lowercase API string is not on this page.

Together AI

GLM-5.3

Model ID

“Z.ai GLM-5.3 zai-org/GLM-5.3 1048575 $1.40 $0.26 $4.40 FP4”
docs.together.ai

Variant, Input, Output, Cached input

“GLM-5.3 $1.40 $0.26 (cached) $4.40”
together.ai

Context served

“zai-org/GLM-5.3 1048575”
docs.together.ai

Quantization

“zai-org/GLM-5.3 1048575 $1.40 $0.26 $4.40 FP4”
docs.together.ai

Status

“Serverless Inference Most teams start with serverless inference”
together.ai

Not stated

  • Batch: No per-model batch price listed on the pricing page.

Fireworks AI

GLM 5.3

Model ID

“app.fireworks.ai/models/fireworks/glm-5p3”
docs.fireworks.ai

Variant, Input, Output, Cached input

“GLM 5.3 $1.40 / $0.26 / $4.40 $1.75 / $0.325 / $5.50”
docs.fireworks.ai

Input column, Output column, Cached input column

“prices are input / cached input / output (USD per 1M tokens), in that order”
docs.fireworks.ai

Status

“In each Standard or Priority cell, prices are input / cached input / output (USD per 1M tokens), in that order”
docs.fireworks.ai

Not stated

  • Batch: No per-model batch price listed; the page states batch inference is billed at 50% of serverless pricing.
  • Context served: Served context length not stated on the pages used.
  • Quantization: Quantization not stated on the pages used.

Source notes: Priority $1.75 / $0.325 / $5.50. GLM 5.3 (US) and GLM 5.3 Fast rows are $2.10 / $0.39 / $6.60; not merged.

Baseten

GLM-5.3

Model ID, Context served

“GLM 5.3 zai-org/GLM-5.3 1048k 262k”
docs.baseten.co

Variant, Input, Output, Cached input

“GLM-5.3 GLM-5.3 $1.40 $1.40 $0.14 $0.14 $4.40”
baseten.co

Input column, Output column, Cached input column

“Price per 1M tokens Model Input Cache Input Output”
baseten.co

Status

“Model APIs Instant access to pre-optimized models running on the Baseten Inference Stack.”
baseten.co

Not stated

  • Batch: No per-model batch price listed on the pricing page.
  • Quantization: Quantization not stated on the pages used.

Source notes: GLM-5.3 Fast (zai-org/GLM-5.3-Fast) recorded separately.

Novita

GLM 5.3

Model ID

“GLM 5.3 zai-org/glm-5.3”
novita.ai

Variant, Input, Output, Cached input

“GLM 5.3 1M $1.4 /Mt· Cache Read$0.26 /Mt $4.4 /Mt”
novita.ai

Context served

“GLM 5.3 1M $1.4”
novita.ai

Quantization

“Provider Z.ai Quantization fp8”
novita.ai

Not stated

  • Batch: No per-model batch price listed; the pricing page states batch inference is at an introductory 50% discount for supported models.
  • Status: No availability tier or release-stage label stated for this offer on the pages used.

Cloudflare Workers AI

glm-5.3

Model ID, Input, Output, Cached input

“@cf/zai-org/glm-5.3 $1.400 per M input tokens $0.260 per M cached input tokens $4.400 per M output tokens”
developers.cloudflare.com

Variant

“@cf/zai-org/glm-5.3 $1.400 per M input tokens”
developers.cloudflare.com

Not stated

  • Batch: No per-model batch price listed on the pricing page.
  • Context served: Served context length not stated on the pages used.
  • Quantization: Quantization not stated on the pages used.
  • Status: No availability tier or release-stage label stated for this offer on the pages used.

Mistral AI (third-party hosted)

Z.ai GLM 5.3

Model ID

“Third-party models hosted by Mistral. Prices /M Tokens USDEUR Regional inference StandardBatchPriority Model Input Cached input Output Z.ai GLM 5.3 $1.4 $0.14 $4.4”
docs.mistral.ai

Variant

“Z.ai GLM 5.3 $1.4 $0.14 $4.4”
docs.mistral.ai

Input, Output, Cached input

“Model Input Cached input Output Z.ai GLM 5.3 $1.4 $0.14 $4.4”
docs.mistral.ai

Status

“Third-party models hosted by Mistral.”
docs.mistral.ai

Not stated

  • Batch: Batch is a separate tab on the pricing page; the default Standard tab lists no batch price for this model.
  • Context served: Served context length not stated on the pages used.
  • Quantization: Quantization not stated on the pages used.

Amazon Bedrock

GLM 5.3

Variant, Input, Output, Cached input, Status

“GLM 5.3 - On-Demand pricing Inference option Price per 1M input tokens Price per 1M output tokens Cache read Cache write - 30m Global CRIS $ 1.68 $ 5.28 $ 0.312 $ 2.10”
aws.amazon.com

Not stated

  • Model ID: No API model ID string on the pricing page.
  • Batch: No per-model batch price listed; the page says Flex tier and Batch pricing is at 50% discount to Standard tier pricing.
  • Context served: Served context length not stated on the pages used.
  • Quantization: Quantization not stated on the pages used.

Source notes: US CRIS: $1.848 / $5.808 / $0.3432 cache read. Cache write (30 min) $2.10 Global.

Baseten

GLM-5.3 Fast

Model ID, Context served

“GLM 5.3 Fast zai-org/GLM-5.3-Fast 1048k 262k”
docs.baseten.co

Variant, Input, Output, Cached input

“GLM-5.3 Fast GLM-5.3 Fast $2.10 $2.10 $0.21 $0.21 $6.60”
baseten.co

Input column, Output column, Cached input column

“Price per 1M tokens Model Input Cache Input Output”
baseten.co

Status

“Model APIs Instant access to pre-optimized models running on the Baseten Inference Stack.”
baseten.co

Not stated

  • Batch: No per-model batch price listed on the pricing page.
  • Quantization: Quantization not stated on the pages used.

Coverage

Not listed on the pages read

  • Fireworks AI: only the headline-model price table is covered; models outside it fall under size-based pricing and are not listed on the pages read.
  • Cerebras: the pay-as-you-go Developer tier lists only GPT OSS 120B and Qwen 3.8 27B; other models are Dedicated Inference by quote.
  • Azure AI Foundry: no gpt-oss, Azure-direct Kimi K3, GLM-5.3 or Mistral Large 3 rows on the pages read.
  • Fireworks AI says batch inference is billed at 50% of serverless pricing, with no per-model batch figure.
  • Novita says batch inference is at an introductory 50% discount for supported models, with no per-model batch prices.
  • Together AI shows a Batch API price toggle but lists no per-model batch figures.
  • Amazon Bedrock says Flex tier and Batch pricing is at 50% discount to Standard tier pricing; per-model batch prices are listed only for gpt-oss, in the Asia Pacific (Sydney) table.
  • Mistral AI keeps Batch and Priority prices on separate tabs; the default Standard tab lists no batch price.

Alternatives

Run GLM-5.3 yourself, or compare its first-party API

FAQ

How much does the GLM-5.3 API cost?

Listed input prices run from $0.563 to $2.10 per 1M input tokens across 10 offers on October 18, 2026, and output from $2.50 to $6.60 per 1M output tokens. The lowest listed input price is at DeepInfra (GLM-5.3), card shows 38% off. First-party: Z.ai at $1.40 input.

Which providers serve GLM-5.3?

Together AI, Fireworks AI, DeepInfra, Baseten, Novita AI, Cloudflare Workers AI, Amazon Bedrock, Z.ai and Mistral AI. Baseten lists more than one build (a dated snapshot, a Fast or turbo build, or a second deployment); each is its own row on this page, under the provider's own model name.

Do all providers serve GLM-5.3's full context window?

GLM-5.3's native context is 1,048,576 tokens in our local-models data. No provider that states a served context lists one clearly below that. Not stated by 5 offers.

Is there a batch price for GLM-5.3?

No per-model batch price for GLM-5.3 is listed on the pages read. Fireworks AI says batch inference is billed at 50% of serverless pricing, with no per-model batch figure. Novita says batch inference is at an introductory 50% discount for supported models, with no per-model batch prices. Together AI shows a Batch API price toggle but lists no per-model batch figures. Amazon Bedrock says Flex tier and Batch pricing is at 50% discount to Standard tier pricing; per-model batch prices are listed only for gpt-oss, in the Asia Pacific (Sydney) table. Mistral AI keeps Batch and Priority prices on separate tabs; the default Standard tab lists no batch price.

Sources

Last verified from each provider's own pages (11 sites). This is a directory of listed prices and what each provider states about the model it serves, not a benchmark. Prices change often; check the provider's page before you commit. Speed figures appear only where a provider states them, labelled Vendor-stated.

Newsletter

Know when open-weight API prices move

One email per week. New model releases, price changes and where to run them, and what they mean for what you build.

Read more about GLM-5.3

Related

Run open-weight models locally

The self-host alternative: downloads, memory needs and commands for each model.

Open-weight model licenses

Which of these models you may use commercially, and on what terms.

LLM API cost levers

Prompt caching, batch discounts and service tiers by provider.

Free LLM API tiers

Which providers have a standing free tier or credits.

OpenAI-compatible endpoints

Base URLs and limits for switching providers without rewriting code.

LLM gateways and routers

Route one model across several of these providers with fallbacks.

Other open-weight models: DeepSeek V4 Pro, DeepSeek V4.1 Flash, Qwen3.8-27B, Kimi K3, MiniMax-M3, gpt-oss-120b, gpt-oss-20b, Llama 4 Maverick, Gemma 4 31B, Mistral Large 3, NVIDIA Nemotron 3.5 Super VL 120B-A12B.

Providers on this page: Together AI, Fireworks AI, DeepInfra, Baseten, Novita AI, Cloudflare Workers AI, Amazon Bedrock, Z.ai, Mistral AI.