DeepSWE
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
gpt-6-lunacodex -m gpt-6-luna. Continuum also serves it on the hosted lane. See Codex models.The API id is gpt-6-luna. Continuum uses the bare id at the gateway and continuum/gpt-6-luna in cross-provider pickers.
The input context is 1,050,000 tokens and maximum output is 128,000 tokens. Input is text and images; output is text. The knowledge cutoff is 18 May 2026.
Reasoning effort on the API is none, low, medium, high, xhigh, or max, with medium as the default. Continuum exposes low through max.
OpenAI positions it as: “Our most efficient model for focused, high-volume tasks.”
Use GPT-6 Luna for mechanical, well-specified work at volume: renames, formatting, extraction, and short focused edits.
No independent board lists this exact SKU as of 2026-08-19.
Closest benchmarked sibling: GPT-5.6 Sol, 73% ±3% Pass@1 at max on the DeepSWE official board. That is a score for the sibling, not for this SKU.
Boards checked: DeepSWE official (2026-08-13), Artificial Analysis Intelligence Index, vals.ai hero index. Every card that does carry a row is on the coding leaderboard.
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
No Intelligence Index integer fetched for this identity. Chip omitted.
We did not open a vals.ai card for this identity. Chip omitted.
Get Plus to use the Continuum-hosted GPT-6 Luna rail. Not a Mac download.
OpenAI does not publish GPT-6 Luna weights. No HF Files button. Get Plus is hosted inference.
Lab card and OpenRouter listing only. No Hugging Face Files button, because there is no official repo to point at.
Fetched OpenRouter catalog on 2026-08-19. hugging_face_id was empty.
Continuum hosts gpt-6-luna on the hosted lane, and it is available through your own Codex subscription (Codex CLI 0.155.0 or later on a ChatGPT account).
gpt-6-luna
click to select
We list first-party and OpenRouter, plus Continuum only when the live public allowlist named the id. This is not a 15-host routing table.
Official pricing per million tokens: $0.10 input, $0.50 output, $0.01 cached input, and $0.125 cache write.
| Claim | Source | As of |
|---|---|---|
| API id, $0.10 / $0.01 cached / $0.125 cache write / $0.50 out, 272K request-wide surcharge, 1.05M context, 128K output, effort levels, modalities, knowledge cutoff | OpenAI GPT-6 Luna model page | 2026-09-22 |
| No base OpenRouter slug on the 2026-08-19 catalog; Hugging Face unlisted | OpenRouter /api/v1/models | 2026-08-19 |
Same official DeepSWE harness (mini-swe-agent, public 113 tasks), fetched 2026-08-19. Different effort labels are the lab's own setting on that board, shown here rather than normalized.
Continue through OpenAI's model family with GPT-5.6 Luna.
No. They are separate ids with separate prices. gpt-6-luna and gpt-5.6-luna are both listed, and the bare luna shorthand on this site still means GPT-5.6 Luna.
Lab posts pick a harness, an effort, a split, and sometimes a private eval set. DeepSWE publishes the official mini-swe-agent row with cost, tokens, and steps. Scale SWE-bench Pro only counts when the public shared-harness board has a row we can fetch. A higher lab number is usually a different test, not a better one.
Verified against the live public allowlist on 2026-08-19. Base URL is https://continuumcode.ai/v1. Keys are cont_sk_ from Settings, Account, Inference API. Personal keys need Plus or above.
curl https://continuumcode.ai/v1/chat/completions \
-H "Authorization: Bearer $CONTINUUM_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-6-luna","messages":[{"role":"user","content":"Review this diff."}]}'