Side-by-side comparison · models
GLM 4.5 Air (Thinking) vs GLM-5.2
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Models
GLM 4.5 Air (Thinking)
Efficient GLM model for fast reasoning, coding, and agent workflows.
Models
GLM-5.2
Open flagship GLM for long-horizon coding agents and million-token context work.
Checked facts
Line by line
| Measure | GLM 4.5 Air (Thinking) | GLM-5.2 |
|---|---|---|
| Input price | Not checked yet | $0.0060 per million tokens |
| Output price | Not checked yet | $6.80 per million tokens |
| Price on ambient | Not checked yet | $0.150 per million cached input tokens |
| Price on ambient | Not checked yet | $0.600 per million input tokens |
| Price on ambient | Not checked yet | $2.00 per million output tokens |
| Price on atlas-cloud | Not checked yet | $0.174 per million cached input tokens |
| Price on atlas-cloud | Not checked yet | $0.938 per million input tokens |
| Price on atlas-cloud | Not checked yet | $2.95 per million output tokens |
| Price on baidu | Not checked yet | $0.260 per million cached input tokens |
| Price on baidu | Not checked yet | $1.40 per million input tokens |
| Price on baidu | Not checked yet | $4.40 per million output tokens |
| Price on baseten | Not checked yet | $0.140 per million cached input tokens |
| Price on baseten | Not checked yet | $1.40 per million input tokens |
| Price on baseten | Not checked yet | $4.40 per million output tokens |
| Price on cloudflare | Not checked yet | $0.190 per million cached input tokens |
| Price on cloudflare | Not checked yet | $0.190 per million input tokens |
| Price on cloudflare | Not checked yet | $8.00 per million output tokens |
| Price on coreweave | Not checked yet | $0.140 per million cached input tokens |
| Price on coreweave | Not checked yet | $0.620 per million input tokens |
| Price on coreweave | Not checked yet | $2.42 per million output tokens |
| Price on decart | Not checked yet | $0.480 per million cached input tokens |
| Price on decart | Not checked yet | $1.20 per million input tokens |
| Price on decart | Not checked yet | $8.00 per million output tokens |
| Price on deepinfra | Not checked yet | $0.084 per million cached input tokens |
| Price on deepinfra | Not checked yet | $0.450 per million input tokens |
| Price on deepinfra | Not checked yet | $1.44 per million output tokens |
| Price on digitalocean | Not checked yet | $0.105 per million cached input tokens |
| Price on digitalocean | Not checked yet | $0.700 per million input tokens |
| Price on digitalocean | Not checked yet | $2.20 per million output tokens |
| Price on friendli | Not checked yet | $0.260 per million cached input tokens |
| Price on friendli | Not checked yet | $1.40 per million input tokens |
| Price on friendli | Not checked yet | $4.40 per million output tokens |
| Price on gmicloud | Not checked yet | $0.260 per million cached input tokens |
| Price on gmicloud | Not checked yet | $1.40 per million input tokens |
| Price on gmicloud | Not checked yet | $4.40 per million output tokens |
| Price on inceptron | Not checked yet | $0.190 per million cached input tokens |
| Price on inceptron | Not checked yet | $1.40 per million input tokens |
| Price on inceptron | Not checked yet | $4.40 per million output tokens |
| Price on mistralai | Not checked yet | $0.140 per million cached input tokens |
| Price on mistralai | Not checked yet | $1.40 per million input tokens |
| Price on mistralai | Not checked yet | $4.40 per million output tokens |
| Price on morph | Not checked yet | $0.250 per million cached input tokens |
| Price on morph | Not checked yet | $0.740 per million input tokens |
| Price on morph | Not checked yet | $3.00 per million output tokens |
| Price on nebius | Not checked yet | $0.140 per million cached input tokens |
| Price on nebius | Not checked yet | $1.40 per million input tokens |
| Price on nebius | Not checked yet | $4.40 per million output tokens |
| Price on novita | Not checked yet | $0.121 per million cached input tokens |
| Price on novita | Not checked yet | $0.650 per million input tokens |
| Price on novita | Not checked yet | $2.04 per million output tokens |
| Price on parasail | Not checked yet | $0.260 per million cached input tokens |
| Price on parasail | Not checked yet | $1.40 per million input tokens |
| Latest version | Not checked yet | z-ai/glm-5.2-20260616 |
| Time to first token (ms) | 2,430 | 1,150 |
| Output speed (tokens a second) | 86.5 | 191.2 |
| Time to first token (ms) on ambient | Not checked yet | 1,939 |
| Time to first token (ms) on atlas-cloud | Not checked yet | 956 |
| Time to first token (ms) on baidu | Not checked yet | 795 |
| Time to first token (ms) on baseten | Not checked yet | 1,483 |
| Time to first token (ms) on cloudflare | Not checked yet | 613 |
| Time to first token (ms) on coreweave | Not checked yet | 455 |
| Time to first token (ms) on decart | Not checked yet | 1,204 |
| Time to first token (ms) on deepinfra | Not checked yet | 2,888 |
| Time to first token (ms) on digitalocean | Not checked yet | 731 |
| Time to first token (ms) on friendli | Not checked yet | 347 |
| Time to first token (ms) on gmicloud | Not checked yet | 2,544 |
| Time to first token (ms) on inceptron | Not checked yet | 316 |
| Time to first token (ms) on mistralai | Not checked yet | 1,124 |
| Time to first token (ms) on morph | Not checked yet | 711 |
| Time to first token (ms) on nebius | Not checked yet | 990 |
| Time to first token (ms) on novita | Not checked yet | 3,255 |
| Time to first token (ms) on parasail | Not checked yet | 1,127 |
| Time to first token (ms) on phala | Not checked yet | 2,618 |
| Time to first token (ms) on qwen | Not checked yet | 889 |
| Time to first token (ms) on relace | Not checked yet | 750 |
| Time to first token (ms) on siliconflow | Not checked yet | 1,186 |
| Time to first token (ms) on streamlake | Not checked yet | 1,943 |
| Time to first token (ms) on together | Not checked yet | 4,945 |
| Time to first token (ms) on venice | Not checked yet | 2,023 |
| Time to first token (ms) on wafer | Not checked yet | 343 |
| Time to first token (ms) on z-ai | Not checked yet | 1,365 |
| Output speed (tokens a second) on ambient | Not checked yet | 83 |
| Output speed (tokens a second) on atlas-cloud | Not checked yet | 52 |
| Output speed (tokens a second) on baidu | Not checked yet | 82 |
| Output speed (tokens a second) on baseten | Not checked yet | 80 |
| Output speed (tokens a second) on cloudflare | Not checked yet | 90 |
| Output speed (tokens a second) on coreweave | Not checked yet | 193 |
| Output speed (tokens a second) on decart | Not checked yet | 277 |
| Output speed (tokens a second) on deepinfra | Not checked yet | 33 |
| Output speed (tokens a second) on digitalocean | Not checked yet | 74 |
| Output speed (tokens a second) on friendli | Not checked yet | 94 |
| Output speed (tokens a second) on gmicloud | Not checked yet | 28 |
| Output speed (tokens a second) on inceptron | Not checked yet | 114 |
| Tokens served on OpenRouter in a day | Not checked yet | 94.9B (for 7 Nov 2026) |
| Tool calls on OpenRouter in a day | Not checked yet | 806.1K (for 7 Nov 2026) |
| Artificial Analysis Intelligence Index | Not checked yet | 33.7 |
| Artificial Analysis Coding Index | Not checked yet | 68.8 |
| Artificial Analysis Agentic Index | Not checked yet | 38.4 |
| LMArena text rating (Elo) | Not checked yet | 1,469 |
| LMArena web development rating (Elo) | Not checked yet | 1,606 |
| Design Arena rating (Elo) | Not checked yet | 1,291 |
| Gpqa diamond | Not checked yet | 91.9% (for 16 June 2026) |
| Swe bench verified | Not checked yet | 78.7% (for 16 June 2026) |
| Frontiermath tiers 1 3 v2 private | Not checked yet | 59.2% (for 16 June 2026) |
| Simpleqa verified | Not checked yet | 34.2% (for 16 June 2026) |
| Arc agi 2 | Not checked yet | 22.8% (for 16 June 2026) |
| Apex agents | Not checked yet | 45.2% (for 16 June 2026) |
| Arc agi | Not checked yet | 77% (for 16 June 2026) |
| Chess puzzles | Not checked yet | 22% (for 16 June 2026) |
| Dtbench | Not checked yet | 93.6% (for 16 June 2026) |
| Ebr bench | Not checked yet | 9.5% (for 16 June 2026) |
| Frontiercode | Not checked yet | 24.5% (for 16 June 2026) |
| Frontiermath tier 4 v2 private | Not checked yet | 29.3% (for 16 June 2026) |
| Lmca | Not checked yet | 45.8% (for 16 June 2026) |
| Mystery game puzzles | Not checked yet | 19% (for 16 June 2026) |
| Posttrainbench | Not checked yet | 31.7% (for 16 June 2026) |
| Proofbench | Not checked yet | 35% (for 16 June 2026) |
| Simplebench | Not checked yet | 58.8% (for 16 June 2026) |
| Surface evolver bench | Not checked yet | 55.6% (for 16 June 2026) |
| Weirdml | Not checked yet | 70.1% (for 16 June 2026) |
| Otis mock aime 2024 2025 | Not checked yet | 86.4% (saturated benchmark: the top models all score near the ceiling) (for 16 June 2026) |
A line appears only when at least one record has a value we confirmed from a source. Values we have not confirmed are left out, never guessed. Records of different types share fewer lines.
Add a third
Compare with one more record
How this works
Share it, or build your own
This page works for any two or three records in the directory, of any type. The link stays the same whichever order you name them in, so you can share it as it is. Change the records in the address, for example /directories/vs/claude-code-vs-cursor, or start from our editorial comparisons.