Get started

GPT-5.6 Terra against Hy4.

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/GPT-5.6 TerravsHy4USD per 1M tokens · one scale
Listed
1,050,000 tokens
Context
1,048,576 tokens
128,000 tokens
Max output
65,536 tokens
file, image, text → text
Modalities
text, image → text
2026-02-16
Knowledge cutoff
not stated
65.2 tok/s
Throughput
84.2 tok/s
2.24s
First token
2.09s
14,473 requests · 6 endpoints
Timed over
3,573 requests · 2 endpoints

Listed price

USD per million tokens · one linear scale
GPT-5.6 TerraOpenAI · listed 9 Jul 2026
Input per M$2.00
Cached input per M$0.20
Output per M$12.00
Blended, 3 in to 1 out$4.50
Hy4Tencent · listed 4 Nov 2026
Input per M$0.417
Cached input per M$0.021
Output per M$1.25
Blended, 3 in to 1 out$0.625

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

8 boards
32.3 · 20 of 58
Intelligence Index
34.6 · 18 of 58
76.7 · 05 of 118
Coding Index
not scored
43.2 · 16 of 94
Agentic Index
not scored
not ranked
Websites · Models
1250 · 42 of 126
not ranked
Code · Models
1254 · 40 of 120
not ranked
Game development · Models
1278 · 24 of 120
not ranked
UI components · Models
1197 · 59 of 116
not ranked
3D scenes · Models
1251 · 28 of 113

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.

OpenAI · GPT-5.6 Terra$2.00 / $12.00Azure · GPT-5.6 Terra$2.00 / $12.00

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
GPT-5.6 Terra$0.004000$4.00$400
Hy4$0.000584$0.5837$58.37

Hy4 costs 85% 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.