MODEL PROOF
GLM 4.5 Air
BETTER VALUE OPTION
A stored alternative has an equal-or-higher measured score and an equal-or-lower price.
Serving precision differs between offers.
GLM 5.3 Flash · Δ score 87.7 points · 52% lower measured price · $0.148 / 1M tokens
Gemma 4 31B is a further stored option with these losses: 98K → 16K max output
- Independent LMArena score
- 1,383.7 ± 4.23 · 30,588 votes
- Context window
- 131.07K
- Maximum output
- 98.3K
- Input modalities
- text
- Output modalities
- text
- Published input price
- $0.130 / 1M tokens
- Published output price
- $0.850 / 1M tokens
- Pricing kind
- fixed
Inspect complete billing conditions and endpoint terms below.
Price from Novita: 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.
Every price dimension · USD per million tokens
| Input | $0.130/M |
|---|---|
| Output | $0.850/M |
| Cached input | $0.025/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 $0.130/M from Novita.
3 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) |
|---|---|---|---|---|
| Novitanovita/bf16 Endpoint terms
| $0.130 | $0.850 | bf16 | 100.00% |
| SiliconFlowsiliconflow/fp8 Endpoint terms
| $0.140 | $0.860 | fp8 | 100.00% |
| Z.AIz-ai/fp8 Endpoint terms
| $0.200 | $1.10 | fp8 | 99.47% |
Independent scores
| LMArena Elo | 1383.7default |
|---|---|
| LMArena row | glm-4.5-air |
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
Best rankings by task
- Data visualisation #67 1181
- SVG #80 1055
- 3D #95 1089
- UI components #101 1107
- Websites #102 1134
- Code categories #104 1119
- Game development #109 1066
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 | 131K |
|---|---|
| Max output | 98K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |
| Knowledge cutoff | 2024-12-31 |
| Open weights | Unknown |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-11-22 |
| Quality data | verified |
GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...
Questions this page answers
What does GLM 4.5 Air cost?
$0.130/M in, $0.850/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does GLM 4.5 Air have an independent quality score?
GLM 4.5 Air has an LMArena score in this catalogue.
What beats GLM 4.5 Air?
GLM 5.3 Flash has an equal-or-higher measured score and an equal-or-lower price.
Does this page use Artificial Analysis scores for GLM 4.5 Air?
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 4.5 Air endpoint the same product?
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.130/M from Novita.
MODEL MONUMENT