tokenstat
tokenstat
Mistral

Mistral: GLM-5.3-Flash

mistral/zai-glm-5-3-flash · rates as of · How this catalog is built · Benchmarks

Native multimodal GLM model for efficient coding and long-horizon agent tasks

Cheapest input
$0.0298
$/MTok · OpenRouter
Cheapest output
$0.0846
$/MTok
Context
1.0M
tokens
Sources
3
106 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ lowerInput $0.0313 → $0.0298
  • ↓ lowerOutput $0.0923 → $0.0846
  • ↑ higherInput $0.0285 → $0.0313
  • ↓ lowerOutput $0.1479 → $0.0923
  • ↑ higherInput $0.0163 → $0.0285
  • ↑ higherOutput $0.1402 → $0.1479
  • ↓ lowerInput $0.018 → $0.0163
  • ↓ lowerInput $0.0457 → $0.018

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (9 omitted). Show free/$0 listings.

SourceProviderInputOutputCache readContext
OpenRoutercheapestz-ai/glm-5.3-flashOpenRouter$0.0298$0.0846$0.02981.0M
models.devz-ai/glm-5.3-flashOpenRouter$0.0313$0.0846$0.031.0M
OpenRouterz-ai/glm-5.3-flash:batchOpenRouter$0.05$0.18$0.011.0M
models.devz-ai/glm-5.3-flashPareto Inference$0.06$0.2$0.0121M
LiteLLMclf_ai_gateway/glm-5.3-flashN/A$0.06$0.2$0.012N/A
models.devglm-5.3-flash302.AI$0.075$0.25$0.0151M
models.devglm-5-3-flashEmpirioLabs AI$0.075$0.25$0.0751.0M
models.devz-ai/glm-5.3-flashZenMux$0.075$0.25$0.0151M
models.devz-ai/glm-5.3-flashIteraCompute$0.08$0.28$0.0231.0M
models.devz-ai/glm-5.3-flashNEAR AI Cloud$0.08$0.5$0.0121M
models.devz-ai/glm-5.3-flashStandard Compute$0.08$0.5$0.0121M
models.devglm-5.3-flashDevPass (LLM Gateway)$0.088$0.25$0.0251.0M
models.devscx-ai-gp/glm-5.3-flashLLM Gateway$0.088$0.25$0.0251.0M
models.devinference.net/glm-5.3-flashLLM Gateway$0.09$0.28$0.021.0M
models.devconsensusprotocol/glm-5.3-flashLLM Gateway$0.1$0.25$0.011.0M
models.devz-ai/glm-5.3-flashNanoGPT$0.1$0.3$0.0251.0M
models.devglm-5.3-flashCortecs$0.1$0.35$0.0181.0M
models.devglm-5.3-flashVultr$0.1$0.35$01.0M
models.deventrim/glm-5.3-flashLLM Gateway$0.1$0.35$0.01751.0M
LiteLLMzerogpu/glm-5.3-flashN/A$0.1$0.35$0.015N/A
models.devzai-org/GLM-5.3-FlashRunInfra$0.11$0.45$0.031.0M
LiteLLMzai-org/GLM-5.3-FlashN/A$0.11$0.35$0.02N/A
LiteLLMGLM-5.3-FlashN/A$0.11$0.35$0.02N/A
LiteLLMsail/zai-org/GLM-5.3-FlashN/A$0.11$0.35$0.02N/A
models.devglm-5.3-flashMelious$0.1115$0.446$0.02231M
models.devglm-5.3-flashAIHubMix$0.1127$0.3944$0.02821M
models.devglm-5-3-flashKenari$0.1143$0.3429$0.02291M
LiteLLMbigmodel/glm-5.3-flashN/A$0.1143$0.4$0.0329N/A
models.devglm-5.3-flashZhipu / Z.ai$0.1195$0.4183$0.03441M
models.devzai-org/GLM-5.3-FlashSiliconFlow (China)$0.1199$0.4198$0.03451.0M
models.devzai-org/GLM-5.3-FlashCoreWeave$0.12$0.38$0.021.0M
models.devglm-5.3-flashBoundless$0.12$0.4$0.0241.0M
models.devglm-5.3-flashVancine$0.12$0.4$0.0241M
models.devglm-5.3-flashGreenPT$0.1278$0.511$0.02561M
models.devzai-org/glm-5.3-flashMunito AI$0.13$0.45$0.0271.0M
models.devglm-5.3-flashEngy$0.135$0.45$0.027328K
models.devgreenference/glm-5.3-flashLLM Gateway$0.14$0.49$0.0281.0M
models.devzai-glm-5-3-flashMistral$0.15$0.5$0.031.0M
models.devzai-org/glm-5.3-flashAi&$0.15$0.5$0.031.0M
models.devzai-org/glm-5.3-flashArcee$0.15$0.5$0.031M
models.devzai-org/GLM-5.3-FlashBaseten$0.15$0.5$0.031.0M
models.devzai-org/GLM-5.3-FlashDeepInfra$0.15$0.5$0.031.0M
models.devzai-org/GLM-5.3-FlashFriendli$0.15$0.5$0.031.0M
models.devzai-org/GLM-5.3-FlashHugging Face$0.15$0.5$01.0M
models.devzai-org/glm-5.3-flashMunito AI (EU)$0.15$0.5$0.031.0M
models.devzai-org/GLM-5.3-FlashNebius$0.15$0.5$0.031.0M
models.devzai-org/glm-5.3-flashNovita AI$0.15$0.5$0.031.0M
models.devzai-org/GLM-5.3-FlashSiliconFlow$0.15$0.5$0.031.0M
models.devzai-org/GLM-5.3-FlashTogether AI$0.15$0.5$0.031.0M
models.devglm-5.3-flashDigitalOcean$0.15$0.5$0.031.0M
models.devglm-5-3-flashNeon$0.15$0.5$0.031.0M
models.devglm-5.3-flashNeuralwatt$0.15$0.5$0.031.0M
models.devglm-5.3-flashOllama Cloud$0.15$0.5$0.031M
models.devglm-5.3-flashOpenCode Go$0.15$0.5$0.031M
models.devglm-5.3-flashOpenCode$0.15$0.5$0.031M
models.devglm-5.3-flashVivgrid$0.15$0.5$0.041M
models.devz-ai/glm-5.3-flashAI/ML API$0.15$0.5$0.031.0M
models.devz-ai/glm-5.3-flashCommandCode$0.15$0.5$0.031M
models.devz-ai/glm-5.3-flashCrossModel$0.15$0.5$0.031M
models.devz-ai/glm-5.3-flashKilo Gateway$0.15$0.5$0.031.0M
models.devz-ai/glm-5.3-flashOfox$0.15$0.5$0.031M
models.devz-ai/glm-5.3-flashOrcaRouter$0.15$0.5$0.031M
models.devz-ai/glm-5.3-flashPrime Inference$0.15$0.5$0.031.0M
models.devz-ai/glm-5.3-flashTokenGo$0.15$0.5$0.031M
models.devcline-pass/glm-5.3-flashClinePass$0.15$0.5$0.031M
models.dev@cf/zai-org/glm-5.3-flashCloudflare$0.15$0.5$0.031.0M
models.devzai/glm-5.3-flashEden AI$0.15$0.5$0.031.0M
models.devtogether-ai/glm-5.3-flashLLM Gateway$0.15$0.5$0.031.0M
models.devzai/glm-5.3-flashMerge Gateway$0.15$0.5$0.031M
models.devzai/glm-5.3-flashTempr Gateway$0.15$0.5$0.031M
models.devzai/glm-5.3-flashVercel AI Gateway$0.15$0.5$0.031M
models.devglm-5.3-flashZhipu / Z.ai$0.15$0.5$0.031M
models.devaccounts/fireworks/models/glm-5p3-flashFireworks AI$0.15$0.5$0.031.0M
models.devTEE/glm-5.3-flashNanoGPT$0.15$0.5$0.031.0M
models.devperplexity/glm-5.3-flashPerplexity$0.15$0.5$0.031M
models.devhf:zai-org/GLM-5.3-FlashSynthetic$0.15$0.5$0.04524K
models.devumans-glm-5.3-flashUmans AI$0.15$0.5$0.031.0M
models.devz-ai-glm-5-3-flashVenice AI$0.15$0.5$0.031.0M
LiteLLMzai-glm-5-3-flashN/A$0.15$0.5$0.03N/A
LiteLLMwandb/zai-org/GLM-5.3-FlashN/A$0.15$0.5$0.05N/A
LiteLLMzai-org/glm-5.3-flashN/A$0.15$0.5$0.03N/A
LiteLLMaccounts/fireworks/models/glm-5p3-flashN/A$0.15$0.5$0.03N/A
LiteLLMtencent/glm-5.3-flashN/A$0.15$0.5$0.03N/A
LiteLLMperplexity/perplexity/glm-5.3-flashN/A$0.15$0.5$0.03N/A
LiteLLMfriendliai/zai-org/GLM-5.3-FlashN/A$0.15$0.5$0.03N/A
LiteLLMglm-5p3-flashN/A$0.15$0.5$0.03N/A
LiteLLMstreamlake/GLM-5.3-FlashN/A$0.15$0.5$0.03N/A
LiteLLMdatabricks-glm-5-3-flashN/A$0.15$0.5$0.03N/A
LiteLLMdatabricks/databricks-glm-5-3-flashN/A$0.15$0.5$0.03N/A
models.devglm-5.3-flashBothub$0.1566$0.522$01M
models.devzai-org/GLM-5.3-FlashInceptron$0.16$0.6$0.041.0M
models.devglm-5.3-flashCharm Hyper$0.1633$0.5444$0.03161.0M
models.devglm-5.3-flashAbove.Dev$0.165$0.55$0.03191M
LiteLLMkyma/glm-5.3-flashN/A$0.172$0.5733$0.0172N/A
models.devreka-ai/glm-5.3-flashLLM Gateway$0.18$0.6$0.0281.0M
LiteLLM@oi/GLM-5.3-FlashN/A$0.195$1.56$0.0195N/A
LiteLLMopeninfer/@oi/GLM-5.3-FlashN/A$0.195$1.56$0.0195N/A
models.devglm-5.3-flashOpper$0.2$0.5$0.071M
models.devz-ai/glm-5.3-flashTensorX$0.2$0.5$0.051.0M
models.devglm-5.3-flashRequesty$0.2$0.6$0.071M
LiteLLMglm-5.3-flashN/A$0.2$0.66$0.04N/A
LiteLLMinferenceapis/zai-org/GLM-5.3-FlashN/A$0.2$0.66$0.04N/A
models.devglm-5.3-flashPrivatemode AI$0.2311$0.7511$0.05781M
models.devglm-5.3-flashWally$0.272$0.65$0.0761.0M
models.devzai-org/GLM-5.3-FlashBerget.AI$0.29$0.58$01.0M
models.devzai-org/GLM-5.3-FlashModal$0.45$1.50$0.091M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: image
  • In: video
  • In: pdf
  • Out: text
Released: 2026-08-26Output limit: 131K tokensFamily: glm-flash

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

See what this model costs you

The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.

macOSDownloadWindowsPreviewCLImacOS · Linux · WindowsApp StoreDownloadGoogle PlayDownload