Zhipu AI · Chat
GLM 5.3 Flash
Natively multimodal flash model with a 1M token context, image and video input, always-on reasoning, native web search, and tool calling.
- llminfo IQ
- 133.6
- Market median price
- $0.2375 blended / 1M
- Max context
- 1.3M
- Listings
- 308
Evidence and sources
Advantages and trade-offs
Compared with 10 chat models, picked mainly by popularity and IQ
Advantages
Costs less than most peers
Market median price: $0.2375 blended / 1M, cheaper than 9 of 9 priced peers.
More provider options
Trade-offs
Deprecated by its maker
The maker has already deprecated this model (7 Nov 2026).
Input & output
as stated by the model's providersCapabilities
Supported operations and provider-stated features
Listings
| 1M | $0.00 | $0.00 | — | — | |
| 1M | $0.00 | $0.00 | — | — | |
| 1M | $0.042 | $0.184 | — | — | |
| 1M | $0.042cache read $0.041 | $0.184 | 75 | 462ms | |
| —Not published by the provider | $0.0473cache read $0.0315 | $0.231 | 81 | 1,427ms | |
| 1M | $0.05cache read $0.025 | $0.45 | — | — | |
| 1M | $0.05cache read $0.03 | $0.20 | — | — | |
| 1M | $0.0519 | $0.1019 | — | — | |
| 1M | $0.06cache read $0.012 | $0.20 | — | — | |
| —Not published by the provider | $0.065cache read $0.012 | $0.18 | — | — |
Showing 10 of 287: the cheapest per 1M input tokens from each provider. 10 listings with suspiciously low prices are in the full list only.
Also sold by 302ai, Abliteratedllm, Above, Adaption, Adzuki, Aiand, Aimlapi, Apertus, Arcee, Atlascloud, Avian, Baidu, Baseten, Berget AI, Bothub, Boundless, BytePlus, Cheapaimodel, Cheapest Token, Cline Pass, Cloudcode, Cloudflare Workers AI, Cometapi, Commandcode, Cortecs AI, Crossmodel, Crusoe, Databricks, DeepInfra, Digitalocean, Doubleword, Eden AI, Empiriolabs, Engy, Entrim, Eurouter, Evolink, Ezkielyna, Fastrouter, Featherless AI, Fireworks AI, Flexai, Flowdot, Friendli AI, Frogbot, Geodd, Gmicloud, Greenpt, Hyper, Inceptron, Inco, Inferenceapis, Inferris, Ionet, Isoquant, Iteracompute, Joingonka, Keln, Kenari, Kilo, Kitani, Klavo, Korouter, Liquid, Llmgateway, Llmgateway Providers, Lyceum, Meganova, Melious, Merge Gateway, Microsoft Azure, Mistral AI, Modal, Moneo, Morph, Munito, Munito Eu, Nan, Near AI, Nebius AI Studio, Neon, Neosantara, Netmind, Neuralwatt, Nous Portal, Novita AI, Ofox, Ollama, Opencode Go, Openroute Cn, Opper, Parasail, Particle AI, Perplexity, Perplexity Agent, Phala, Powerspring, Ppio, Privatemode AI, Proxystacks, Qiniu, Redpill, Runcrate, Runinfra, Sandbase, Scx AI, Sference, SiliconFlow, Siliconflow Cn, Sparrowcodes, Standardcompute, Stepping Stone, Streamlake, Synthetic, T Systems, Tencent, Tensorix, Tensorx, Tenstorrent, Thalam, Together AI, Tokengo, Tokenify, Umans AI, Uplinkswitch, Vancine, Venice, Vercel, Vivgrid, Volcano Engine, Vultr, Wally, Watt, Wavespeed, Weights & Biases, Z.ai, Zenmux, Zerogpu, Zhipu AI (Open Platform), Zro.
21 listings without a price are hidden.
Included in plans
Benchmarks
Named effort levels run from lowest to highest. Select a result to see its source details.
Agentic
Show results from 41 providers and OpenRouter's automatic routingHide results from 41 providers and OpenRouter's automatic routing
- Z.AI
- Relace
- Novita
- Wafer
- NextBit
- SiliconFlow
- InferenceNet
- Parasail
- OpenRouter's automatic routing
- DeepInfra
- Modal
- Venice
- Sail Research
- StreamLake
- AtlasCloud
- Near AI
- CoreWeave
- Fireworks
- BaseTen
- Inceptron
- Crusoe
- River
- Phala
- DekaLLM
- Io Net
- Cloudflare
- Friendli
- Nebius
- Together
- Reka
- Decart
- Makora
- Morph
- PrimeIntellect
- Mistral
- Cohere
- Tenstorrent
- DigitalOcean
- KT
- Particle AI
- OpenInference
- GMICloud
| Benchmark | Score |
|---|---|
| Tax Agent Bench | |
| Finance Agent (v2) | |
| Finance Agent v2.1 | |
| Harvey's Legal Agent Benchmark v1 |
Show 3 more benchmarksHide 3 benchmarks
| Benchmark | Score |
|---|---|
| Terminal-Bench 2.1 | |
| Terminal-Bench 4.0 | |
| Terminal-Bench-Science |
Human preference
| Benchmark | Score |
|---|---|
| Arena ELO | |
| Chinese | |
| Creative Writing | |
| English |
Show 58 more benchmarksHide 58 benchmarks
Science
Show results from 43 providers and OpenRouter's automatic routingHide results from 43 providers and OpenRouter's automatic routing
- Darkbloom
- DeepInfra
- Wafer
- Z.AI
- Venice
- InferenceNet
- Phala
- DigitalOcean
- PrimeIntellect
- Near AI
- GMICloud
- Novita
- DekaLLM
- Inceptron
- StreamLake
- Together
- AtlasCloud
- OpenRouter's automatic routing
- Fireworks
- Reka
- Cloudflare
- Relace
- SiliconFlow
- BaseTen
- Crusoe
- Parasail
- Decart
- CoreWeave
- NextBit
- Friendli
- Modal
- Cohere
- Morph
- Io Net
- Baidu
- Tenstorrent
- OpenInference
- KT
- River
- Mistral
- Particle AI
- Makora
- Sail Research
- Nebius
Coding
| Benchmark | Score |
|---|---|
| IOI | |
| Code Migration | |
| Code Migration v1.1 | |
| LiveCodeBench |
Show 5 more benchmarksHide 5 benchmarks
| Benchmark | Score |
|---|---|
| ProgramBench | |
| SkillsBench | |
| SWE-bench | |
| Vibe Code Bench 1-100 | |
| Vibe Code Bench v1.1 |
Multilingual
Show 11 more resultsHide 11 results
Reasoning
General
| Benchmark | Score |
|---|---|
| typos | |
| AMPS_Hard | |
| connections | |
| consecutive_events |
Show 15 more benchmarksHide 15 benchmarks
| Benchmark | Score |
|---|---|
| integrals_with_game | |
| javascript | |
| logic_with_navigation | |
| olympiad | |
| paraphrase | |
| plot_unscrambling | |
| python | |
| simplify | |
| spatial | |
| story_generation | |
| summarize | |
| tablejoin | |
| tablereformat | |
| theory_of_mind | |
| typescript |
Long context
Math
Vision
Instruction following
Knowledge
OCR
Other
Show 3 more resultsHide 3 results
Show 9 more resultsHide 9 results
Show 1 more resultHide 1 result
Show 9 more resultsHide 9 results
Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · Benchmark Nusantara, ibahasa (M. Khoirul Huda), doi:10.5281/zenodo.21970463. Test results CC BY 4.0, attribution to ibahasa; aggregate results CSV only. (licence) · Deep20Bench edition 1.1, Patrick Heusser. Results CC BY 4.0; native question scores and fraction-to-percent success rates. (licence) · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MineBench, MIT (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted. · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence)
Also known as: @cf/zai-org/glm-5.3-flash, accounts/fireworks/models/glm-5p3-flash, aihubmix/glm-5.3-flash, azure_ai/fw-glm-5.3-flash, baseten/zai-org/glm-5.3-flash, cline-pass/glm-5.3-flash, coding-glm-5.3-flash, coding-glm-5.3-flash-free, databricks/databricks-glm-5-3-flash, deepinfra/glm-5.3-flash, deepinfra/zai-org/glm-5.3-flash, e2ee-glm-5.3-flash, empiriolabs/glm-5-3-flash, fireworks/glm-5.3-flash, fireworks_ai/accounts/fireworks/models/glm-5p3-flash, fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us, fireworks_ai/glm-5p3-flash, fireworks_ai/glm-5p3-flash-us, flexai/glm-5.3-flash, glm 5.3 flash, glm-5-3-flash, glm-5-3-flash-260828, glm-5.3-flash-flex, glm-5.3-flash-free, glm-5.3-flash:fast, glm-5.3-flash@eu, glm5.3-flash, gmi/zai-org/glm-5.3-flash, greenference/glm-5.3-flash, hf:zai-org/glm-5.3-flash, mistral/glm-5.3-flash, mistral/zai-glm-5-3-flash, nebius/zai-org/glm-5.3-flash, novita/glm-5.3-flash, nvidia_nim/z-ai/glm-5.3-flash, opencode_go/glm-5.3-flash, parasail-glm-53-flash, perplexity/glm-5.3-flash, runware/glm-5.3-flash, scx-ai-gp/glm-5.3-flash, streamlake/glm-5.3-flash, tee/glm-5.3-flash, tencent/glm-5.3-flash, together-ai/glm-5.3-flash, together_ai/zai-org/glm-5.3-flash, umans-glm-5.3-flash, wandb/zai-org/glm-5.3-flash, z-ai-glm-5-3-flash, z-ai-glm-5.3-flash, z-ai/glm-5.3-flash, z-ai/glm-5.3-flash-free, z-ai/glm-5.3-flash:batch, zai-glm-5-3-flash, zai-org/glm-5.3-flash, zai-org/glm-5.3-flash-bf16, zai/glm-5.3-flash, zhipu/glm-5.3-flash
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works