Get started

GLM 5.3 against GPT-6.1 Terra.

Two listings from the same committed catalog, side by side: the fields OpenRouter publishes, the boards two third parties scored, and a cost sheet that is arithmetic over the listed rates.

retrieved sha256 · 0bb53a77713f

Compare/GLM 5.3vsGPT-6.1 TerraUSD per 1M tokens · one scale
Listed
1,048,576 tokens
Context
1,050,000 tokens
943,718 tokens
Max output
128,000 tokens
text → text
Modalities
file, image, text → text
not stated
Knowledge cutoff
not stated
96.4 tok/s
Throughput
56.3 tok/s
513ms
First token
1.89s
230,032 requests · 46 endpoints
Timed over
61,935 requests · 7 endpoints

Listed price

USD per million tokens · one linear scale
GLM 5.3Z.ai · listed 18 Aug 2026
Input per M$0.0699
Cached input per M$0.0689
Output per M$1.40
Blended, 3 in to 1 out$0.402
GPT-6.1 TerraOpenAI · listed 26 Oct 2026
Input per M$1.00
Cached input per M$0.05
Output per M$5.00
Blended, 3 in to 1 out$2.00

Per million tokens, as OpenRouter listed them when the catalog was read: its routed rates, not a provider's own page. One linear scale across every row, so a bar twice as long is twice the price. The blended row is Vitna's arithmetic, three input tokens to one output.

Every board either stands on

15 boards
31.7 · 21 of 58
Intelligence Index
51.3 · 08 of 58
74.8 · 13 of 118
Coding Index
not scored
53.1 · 05 of 94
Agentic Index
not scored
1278 · 24 of 126
Websites · Models
not ranked
1282 · 21 of 120
Code · Models
not ranked
1287 · 21 of 120
Game development · Models
not ranked
1283 · 23 of 116
UI components · Models
not ranked
1293 · 19 of 113
3D scenes · Models
not ranked
1251 · 33 of 110
Data visualisation · Models
not ranked
1244 · 20 of 83
SVG · Models
not ranked
1184 · 29 of 67
ASCII art · Models
not ranked
1184 · 24 of 49
Mobile apps · Agents
not ranked
1270 · 10 of 47
Web apps · Agents
not ranked
1217 · 09 of 29
python-pptx slides · Agents
not ranked
1189 · 02 of 25
HTML slides · Agents
not ranked

Score and position on each board, from the board's own source as OpenRouter carries it. The heavier figure leads that board; a missing score is a fact about coverage, not a zero.

Vitna reads

from provider pages

Where the registry tracks a model, Vitna reads the rate from the provider page itself and keeps it as a dated record; the OpenRouter figures above are its routed rates.

Baseten · GLM-5.3 Fast$2.10 / $6.60Mistral AI · GLM-5.3$1.40 / $4.40Together AI · GLM-5.3$1.40 / $4.40Parasail · GLM-5.3$1.40 / $4.40Novita AI · GLM-5.3$1.40 / $4.40Baseten · GLM-5.3$1.40 / $4.40OpenAI · GPT-6.1 Terra$1.00 / $5.00

Cost sheet

800 in · 200 out per call

Arithmetic over the listed rates and nothing else: tokens in over one million times the input rate, plus tokens out over one million times the output rate. No cache, no retries and no failure rate assumed; the Decision Lab is where cost per successful unit lives.

ModelPer callPer 1,000 callsPer 100,000 calls
GLM 5.3$0.000336$0.3359$33.59
GPT-6.1 Terra$0.001800$1.80$180

GLM 5.3 costs 81% less per call at these token counts.

Other pairs with a page
For one of your workloads

The market on these two is here. The right one for your work is not.

What this page cannot say is which is right for a particular piece of your production work, because that depends on what the workload requires and what your own evaluations measured, neither of which is public. The register weighs a candidate against a workload's own thresholds and shows what the engine would decide before anything is filed.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Vitna ran none of these evaluations and adjusted none of these figures.