MODEL PROOF

GLM 5.3

TRADE-OFF

A stored alternative has an equal-or-higher score and an equal-or-lower price, with capability losses.

$1.00 / 1M tokens Balanced · 3 tokens in per 1 out

Serving precision differs between offers.

MiMo-V2.6-Pro · Δ score 17.3 points · 46% lower measured price

  • 944K → 131K max output
Independent LMArena score
1,475.4 ± 4.56 · 34,708 votes
Context window
1.05M
Maximum output
943.72K
Input modalities
text
Output modalities
text
Published input price
$0.700 / 1M tokens
Published output price
$1.90 / 1M tokens
Pricing kind
fixed

Inspect complete billing conditions and endpoint terms below.

Price from SiliconFlow: 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.

Cheaper right now: $0.402/M at Wafer — 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$0.700/M
Output$1.90/M
Cached input$0.130/M
Cache writeUnknown/M
Cache write 1hUnknown/M
ReasoningUnknown/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 $0.600/M from Tenstorrent.

45 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.

SellerInputOutputPrecisionUptime (1d)
Waferwafer/us
Endpoint terms
Cached input /M
$0.069
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.070 $1.40 fp4 100.00%
Relacerelace/fp4
Endpoint terms
Cached input /M
$0.070
Context limit
1,048,576 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.070 $4.38 fp4 100.00%
InferenceNetinference-net/us
Endpoint terms
Cached input /M
$0.079
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.084 $3.60 fp4 100.00%
InferenceNetinference-net/fp4
Endpoint terms
Cached input /M
$0.079
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.084 $3.60 fp4 100.00%
Waferwafer/fp4
Endpoint terms
Cached input /M
$0.178
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.179 $1.40 fp4 100.00%
AkashMLakashml/fp4
Endpoint terms
Cached input /M
$0.190
Context limit
1,048,576 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.190 $4.40 fp4 100.00%
DeepInfradeepinfra/fp4/flex
Endpoint terms
Cached input /M
$0.100
Context limit
1,048,576 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
37.5% · already included in these rates
Uptime · last 30 minutes
Unknown
$0.450 $2.00 fp4 100.00%
Coherecohere/nvfp4
Endpoint terms
Cached input /M
$0.100
Context limit
1,048,576 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.500 $3.50 nvfp4 100.00%
Decartdecart/fp4
Endpoint terms
Cached input /M
$0.100
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.560 $1.81 fp4 100.00%
DeepInfradeepinfra/fp4
Endpoint terms
Cached input /M
$0.125
Context limit
1,048,576 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
37.5% · already included in these rates
Uptime · last 30 minutes
100.00%
$0.563 $2.50 fp4 99.22%
Tenstorrenttenstorrent/fp8
Endpoint terms
Cached input /M
$0.100
Context limit
1,044,480 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.600 $2.50 fp8 100.00%
Novitanovita/fp8
Endpoint terms
Cached input /M
$0.117
Context limit
1,048,576 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
55% · already included in these rates
Uptime · last 30 minutes
100.00%
$0.630 $1.98 fp8 100.00%
SiliconFlowsiliconflow/fp8
Endpoint terms
Cached input /M
$0.130
Context limit
1,048,576 tokens
Output limit
262,144 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.700 $1.90 fp8 99.36%
Doubleworddoubleword/nvfp4
Endpoint terms
Cached input /M
$0.140
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.700 $2.20 nvfp4 100.00%
Cloudflarecloudflare
Endpoint terms
Cached input /M
$0.130
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.700 $2.20 undeclared 100.00%
Sail Researchsail-research/us
Endpoint terms
Cached input /M
$0.120
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.750 $3.00 fp8 100.00%
CoreWeavecoreweave/nvfp4
Endpoint terms
Cached input /M
$0.190
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.750 $3.00 nvfp4 99.93%
Featherlessfeatherless
Endpoint terms
Cached input /M
$0.156
Context limit
262,144 tokens
Output limit
32,768 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
40% · already included in these rates
Uptime · last 30 minutes
100.00%
$0.840 $2.64 undeclared 98.46%
DigitalOceandigitalocean
Endpoint terms
Cached input /M
$0.169
Context limit
1,048,576 tokens
Output limit
128,000 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.910 $2.86 undeclared 100.00%
Morphmorph/fp8
Endpoint terms
Cached input /M
$0.204
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$1.01 $4.70 fp8 100.00%
Sail Researchsail-research/fp8
Endpoint terms
Cached input /M
$0.168
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$1.05 $4.20 fp8 100.00%
Inceptroninceptron/fp4
Endpoint terms
Cached input /M
$0.117
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$1.05 $3.50 fp4 100.00%
Alibabaalibaba
Endpoint terms
Cached input /M
$0.238
Context limit
1,000,000 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
Unknown
$1.19 $3.74 undeclared 100.00%
Friendlifriendli
Endpoint terms
Cached input /M
$0.234
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
10% · already included in these rates
Uptime · last 30 minutes
100.00%
$1.26 $3.96 undeclared 100.00%
Baidubaidu/fp8
Endpoint terms
Cached input /M
$0.260
Context limit
1,048,576 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
Unknown
$1.40 $4.40 fp8 —
Z.AIz-ai/fp8
Endpoint terms
Cached input /M
$0.260
Context limit
1,048,576 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$1.40 $4.40 fp8 99.58%
Nebiusnebius/fp4
Endpoint terms
Cached input /M
$0.260
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$1.40 $4.40 fp4 100.00%
BaseTenbaseten/fp4/us
Endpoint terms
Cached input /M
$0.140
Context limit
1,048,576 tokens
Output limit
262,144 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$1.40 $4.40 fp4 100.00%
Crusoecrusoe/fp4
Endpoint terms
Cached input /M
$0.260
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
Unknown
$1.40 $4.40 fp4 100.00%
Parasailparasail/fp4
Endpoint terms
Cached input /M
$0.260
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$1.40 $4.40 fp4 100.00%
BaseTenbaseten/fp4
Endpoint terms
Cached input /M
$0.140
Context limit
1,048,576 tokens
Output limit
262,144 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$1.40 $4.40 fp4 100.00%
SambaNovasambanova
Endpoint terms
Cached input /M
$0.070
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
50% · already included in these rates
Uptime · last 30 minutes
100.00%
$1.40 $4.40 undeclared 100.00%
Mistralmistral/zdr
Endpoint terms
Cached input /M
$0.140
Context limit
1,048,576 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$1.40 $4.40 nvfp4 100.00%
Venicevenice
Endpoint terms
Cached input /M
$0.260
Context limit
1,000,000 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
20% · already included in these rates
Uptime · last 30 minutes
Unknown
$1.40 $4.40 undeclared 99.33%
Togethertogether
Endpoint terms
Cached input /M
$0.260
Context limit
1,048,575 tokens
Output limit
943,717 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$1.40 $4.40 undeclared 100.00%
Modalmodal
Endpoint terms
Cached input /M
$0.260
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
Unknown
$1.40 $4.40 undeclared 100.00%
Fireworksfireworks
Endpoint terms
Cached input /M
$0.260
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$1.40 $4.40 undeclared 100.00%
Makoramakora/fp4
Endpoint terms
Cached input /M
$0.260
Context limit
1,048,576 tokens
Output limit
128,000 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$1.50 $4.40 fp4 99.06%
Mistralmistral/nvfp4/eu
Endpoint terms
Cached input /M
$0.154
Context limit
1,048,576 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$1.54 $4.84 nvfp4 98.94%
Amazon Bedrockamazon-bedrock/us-east-1
Endpoint terms
Cached input /M
$0.312
Context limit
1,048,576 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$1.68 $5.28 undeclared 99.84%
BaseTenbaseten/us/fast
Endpoint terms
Cached input /M
$0.210
Context limit
1,048,576 tokens
Output limit
262,144 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$2.10 $6.60 fp8 100.00%
BaseTenbaseten/fast
Endpoint terms
Cached input /M
$0.210
Context limit
1,048,576 tokens
Output limit
262,144 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$2.10 $6.60 fp8 100.00%
Parasailparasail/fast
Endpoint terms
Cached input /M
$0.260
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$2.10 $6.60 fp4 100.00%
ModelRunmodelrun/fp4
Endpoint terms
Cached input /M
$0.400
Context limit
1,048,576 tokens
Output limit
524,288 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$2.10 $6.60 fp4 100.00%
Fireworksfireworks/fast
Endpoint terms
Cached input /M
$0.390
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$2.10 $6.60 undeclared 100.00%

Independent scores

LMArena Elo1475.4max
LMArena rowglm-5.3-max

LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.

Best rankings by task

  • Htmlslides #2 1189
  • Web apps #8 1270
  • Python pptxslides #10 1217
  • SVG #21 1237
  • 3D #23 1277
  • Code categories #24 1275
  • Game development #24 1271
  • Websites #26 1273

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 window1M
Max output943K
Input modestext
Tool useyes
Reasoningalways on
Open weightsyes

Provenance

Price sourceopenrouter.ai
Fetched2026-11-22
Quality dataverified
Cross-checkedvendor page

Our take

editorial — not a measurement

GLM is a candidate for text-only workloads where selected-workload cost and task quality can be evaluated together. Use the current proof and benchmark evidence to judge measured price and capability. Do not infer downloadable weights or licence rights from the broader GLM family; verify the exact release and endpoint.

Strengths

  • Text input, tools and reasoning effort are listed
  • Cached-input pricing is recorded

Weaknesses

  • Family history does not establish this release’s weight or licence status
  • Text-only input is a migration constraint

Reach for it when

  • Text-only workload evaluations
  • Teams that compare cost per completed task

Avoid it if

  • You require multimodal input
  • Self-hosting is required but the exact weights and licence are not established

Sources: openrouter.ai

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...

Questions this page answers

What does GLM 5.3 cost?

$0.700/M in, $1.90/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.

Does GLM 5.3 have an independent quality score?

GLM 5.3 has an LMArena score in this catalogue.

What beats GLM 5.3?

MiMo-V2.6-Pro has an equal-or-higher measured score and an equal-or-lower price, with capability trade-offs.

Does this page use Artificial Analysis scores for GLM 5.3?

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 5.3 endpoint the same product?

Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.600/M from Tenstorrent.

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.

GLM 5.3 — Undominated.ai dominance verdict

Markdown
[![GLM 5.3 — Undominated.ai dominance verdict](https://undominated.ai/badge/z-ai__glm-5.3.svg)](https://undominated.ai/models/z-ai__glm-5.3/)
HTML
<a href="https://undominated.ai/models/z-ai__glm-5.3/"><img src="https://undominated.ai/badge/z-ai__glm-5.3.svg" alt="GLM 5.3 — Undominated.ai dominance verdict" height="36"></a>

Direct file: https://undominated.ai/badge/z-ai__glm-5.3.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.

Evidence & Ask