MODEL PROOF
GPT-6 Luna
TRADE-OFF
A stored alternative has an equal-or-higher score and an equal-or-lower price, with capability losses.
Base context tier shown; inspect the complete context ladder below.
GLM 5.3 Flash · Δ score 81.2 points · 26% lower measured price
- 1.1M → 1M context
- no file input
- Independent LMArena score
- 1,390.2 ± 3.98 · 118,208 votes
- Context window
- 1.05M
- Maximum output
- 128K
- Input modalities
- file, image, text
- Output modalities
- text
- Published input price
- $0.100 / 1M tokens
- Published output price
- $0.500 / 1M tokens
- Pricing kind
- fixed
- Context tiers
- Tiered by context
Inspect complete billing conditions and endpoint terms below.
Price from OpenAI: 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: $0.100/M at OpenAI — delivery tier (flex) It does not pass the like-for-like test, so it never sets a rank.
Every price dimension · USD per million tokens
| Input | $0.100/M |
|---|---|
| Output | $0.500/M |
| Cached input | $0.010/M |
| Cache write | $0.125/M |
| Cache write 1h | Unknown/M |
| Reasoning | Unknown/M |
| Web search | $0.01/call |
The headline rate does not apply to a long-context workload.
Complete context ladder · 1 tier
| More than 272,000 tokens | $0.200/M in (2×) $0.750/M out $0.020/M cached input $0.250/M cache write |
|---|
Who sells it
The same weights, different shops. Cheapest is not like-for-like when serving precision differs.
5 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) |
|---|---|---|---|---|
| OpenAIopenai/flex Endpoint terms
| $0.050 | $0.250 | undeclared | 100.00% |
| Amazon Bedrockamazon-bedrock/global Endpoint terms
| $0.100 | $0.500 | undeclared | 100.00% |
| OpenAIopenai Endpoint terms
| $0.100 | $0.500 | undeclared | 100.00% |
| Azureazure Endpoint terms
| $0.100 | $0.500 | undeclared | 100.00% |
| OpenAIopenai/fast Endpoint terms
| $0.200 | $1.00 | undeclared | 100.00% |
Independent scores
| LMArena Elo | 1390.2max |
|---|---|
| LMArena row | gpt-6-luna-max |
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
Capability
| Context window | 1M |
|---|---|
| Max output | 128K |
| Input modes | file, image, text |
| Tool use | yes |
| Reasoning | optional |
| Open weights | no |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-11-22 |
| Quality data | verified |
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...
Questions this page answers
What does GPT-6 Luna cost?
$0.100/M in, $0.500/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does GPT-6 Luna have an independent quality score?
GPT-6 Luna has an LMArena score in this catalogue.
What beats GPT-6 Luna?
GLM 5.3 Flash 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 GPT-6 Luna?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
MODEL MONUMENT