MODEL PROOF
GLM 5.2
BETTER VALUE OPTION
A stored alternative has an equal-or-higher measured score and an equal-or-lower price.
Price under confirmation since 2026-10-12. Upstream lists another price for this model now, or other prices from its sellers. What is shown is the last we published; the new figures are published once a second day shows the same values. · Serving precision differs between offers.
GLM 5.3 · Δ score 1.4 points · 11% lower measured price · $1.00 / 1M tokens (Price under confirmation since Oct 12, 2026)
MiMo-V2.6-Pro is a further stored option with these losses: 944K → 131K max output
- Independent LMArena score
- 1,470 ± 4.17 · 49,127 votes
- Context window
- 1.05M
- Maximum output
- 943.72K
- Input modalities
- text
- Output modalities
- text
- Published input price
- $0.309 / 1M tokens
- Published output price
- $3.55 / 1M tokens
- Pricing kind
- fixed
Inspect complete billing conditions and endpoint terms below.
Price from Morph: the cheapest offer that is serving, at standard delivery, with at least 90% of the reference context and at the maker’s precision or better, at its standard rate.
Price under confirmation since 2026-10-12 Upstream lists another price for this model now, or other prices from its sellers. What is shown is the last we published; the new figures are published once a second day shows the same values.
Cheaper right now: $0.872/M at DeepInfra — promotion 25% · 4-bit It does not pass the like-for-like test, so it never sets a rank.
Every price dimension · USD per million tokens
| Input | $0.309/M |
|---|---|
| Output | $3.55/M |
| Cached input | $0.137/M |
| Cache write | Unknown/M |
| Cache write 1h | Unknown/M |
| Reasoning | Unknown/M |
Who sells it
The same weights, different shops. Cheapest is not like-for-like when serving precision differs.
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.309/M from Morph.
33 provider offers · rates, limits and conditions
Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test.
| Seller | Input | Output | Precision | Uptime (1d) |
|---|---|---|---|---|
| Relacerelace Endpoint terms
| $0.152 | $12.00 | undeclared | 99.95% |
| Waferwafer Endpoint terms
| $0.190 | $8.00 | undeclared | 99.47% |
| InferenceNetinference-net Endpoint terms
| $0.200 | $4.40 | undeclared | 99.42% |
| Morphmorph/fp8 Endpoint terms
| $0.309 | $3.55 | fp8 | 99.40% |
| DeepInfradeepinfra/fp4 Endpoint terms
| $0.563 | $1.80 | fp4 | 99.48% |
| Decartdecart/mxfp4 Endpoint terms
| $0.605 | $3.72 | mxfp4 | 99.98% |
| StreamLakestreamlake/fp8 Endpoint terms
| $0.643 | $2.02 | fp8 | 99.84% |
| Novitanovita/fp8 Endpoint terms
| $0.650 | $2.04 | fp8 | 99.77% |
| SiliconFlowsiliconflow/fp8 Endpoint terms
| $0.700 | $2.20 | fp8 | 99.05% |
| DigitalOceandigitalocean Endpoint terms
| $0.700 | $2.20 | undeclared | 99.69% |
| CoreWeavecoreweave/fp4 Endpoint terms
| $0.760 | $2.42 | fp4 | 99.96% |
| AtlasCloudatlas-cloud/fp8 Endpoint terms
| $0.938 | $2.95 | fp8 | 98.29% |
| Alibabaalibaba/fp8 Endpoint terms
| $0.966 | $3.04 | fp8 | 98.46% |
| Cloudflarecloudflare Endpoint terms
| $1.18 | $4.40 | undeclared | 99.89% |
| Phalaphala/fp8 Endpoint terms
| $1.26 | $3.00 | fp8 | 99.94% |
| Inceptroninceptron/fp4 Endpoint terms
| $1.39 | $4.39 | fp4 | 98.35% |
| BaseTenbaseten/fp8 Endpoint terms
| $1.40 | $4.40 | fp8 | 99.68% |
| Baidubaidu/fp8 Endpoint terms
| $1.40 | $4.40 | fp8 | 99.88% |
| BaseTenbaseten/fp8 Endpoint terms
| $1.40 | $4.40 | fp8 | 99.73% |
| Venicevenice/fp8 Endpoint terms
| $1.40 | $4.40 | fp8 | 99.52% |
| GMICloudgmicloud/fp8 Endpoint terms
| $1.40 | $4.40 | fp8 | 99.10% |
| Z.AIz-ai/fp8 Endpoint terms
| $1.40 | $4.40 | fp8 | 99.85% |
| Nebiusnebius/fp4 Endpoint terms
| $1.40 | $4.40 | fp4 | 70.81% |
| Parasailparasail/fp4 Endpoint terms
| $1.40 | $4.40 | fp4 | 96.51% |
| Mistralmistral/zdr Endpoint terms
| $1.40 | $4.40 | nvfp4 | 99.96% |
| Togethertogether Endpoint terms
| $1.40 | $4.40 | undeclared | 99.21% |
| Friendlifriendli Endpoint terms
| $1.40 | $4.40 | undeclared | 99.83% |
| Mistralmistral/eu Endpoint terms
| $1.54 | $4.84 | undeclared | 100.00% |
| BaseTenbaseten/fast Endpoint terms
| $2.10 | $6.60 | fp8 | 99.49% |
| BaseTenbaseten/fast Endpoint terms
| $2.10 | $6.60 | fp8 | 99.22% |
| Baidubaidu/fast Endpoint terms
| $2.25 | $7.88 | fp4 | 100.00% |
| Decartdecart/fast Endpoint terms
| $2.25 | $8.00 | fp4 | 99.97% |
| Alibabaalibaba/fast Endpoint terms
| $2.31 | $7.26 | fp8 | 98.96% |
Independent scores
| LMArena Elo | 1470max |
|---|---|
| LMArena row | glm-5.2-max |
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
Best rankings by task
- Agenticgamedev #10 1206
- Full-stack apps #12 1241
- Htmlslides #13 1175
- Web apps #16 1222
- Data visualisation #17 1285
- Python pptxslides #17 1195
- Native Android apps #18 1184
- UI components #20 1296
Per-task Elo and rank from Design Arena, via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list.
Capability
| Context window | 1M |
|---|---|
| Max output | 943K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |
| Open weights | yes |
Provenance
| Price source | Published record of 2026-10-06, under confirmation since 2026-10-12 |
|---|---|
| Fetched | 2026-10-21 |
| Held | Price and provider offers kept at the published record of 2026-10-06 until a second day confirms the newer upstream value, or after 3 days until one day’s two readings agree. |
| Quality data | verified |
| Cross-checked | vendor page |
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
Questions this page answers
What does GLM 5.2 cost?
$0.309/M in, $3.55/M out: the published record of 2026-10-06, under confirmation since 2026-10-12. That is the API row, not a subscription.
Does GLM 5.2 have an independent quality score?
GLM 5.2 has an LMArena score in this catalogue.
What beats GLM 5.2?
GLM 5.3 has an equal-or-higher measured score and an equal-or-lower price.
Does this page use Artificial Analysis scores for GLM 5.2?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
Is the cheapest GLM 5.2 endpoint the same product?
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.309/M from Morph.
MODEL MONUMENT
Save or share this proof
Badge
The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not.
[](https://undominated.ai/models/z-ai__glm-5.2/)<a href="https://undominated.ai/models/z-ai__glm-5.2/"><img src="https://undominated.ai/badge/z-ai__glm-5.2.svg" alt="GLM 5.2 — Undominated.ai dominance verdict" height="36"></a>Direct file: https://undominated.ai/badge/z-ai__glm-5.2.svg — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never
older than the last deploy.
