Model comparison
DeepSeek V3.1 vs GPT-5.6 Luna
DeepSeek against OpenAI, compared on context, price, and verified benchmark results.
Catalog record checked September 3, 2026Individual provider fields may changeEvidence confidence: High — see receipts below
DeepSeek
DeepSeek V3.1
Budget · Open weights
OpenAI
GPT-5.6 Luna
Budget
| Specification | DeepSeek V3.1 | GPT-5.6 Luna |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Tier | Budget | Budget |
| Context window | 128K | Winner: 1.05M |
| Max output | 128K | 128K |
| Input / 1M tokens | $0.25 | Winner: $0.20 |
| Output / 1M tokens | Winner: $0.95 | $1.20 |
| Weights | Open | Closed |
| Parameters | 671B total / 37B active (MoE) | cheapest GPT-5.6 tier |
| Reasoning levels | low, high, max | none, low, medium, high |
| Modalities | text | text, image |
| License | MIT | Not disclosedUnverified |
| API model id | Not publishedUnverified | gpt-5.6-luna |
| Released | August 21, 2025 | July 9, 2026 |
| Artificial Analysis Intelligence Index (2026-08-14) | 44 | Not verifiedUnverified |
| Artificial Analysis Intelligence Index [high] (2026-08-14) | Not verifiedUnverified | 47 |
| SWE-bench Verified (2026-09-01) | Not verifiedUnverified | 93 |
| Terminal-Bench 2.1 (2026-07-09) | Not verifiedUnverified | 84.7 |
| LiveBench (2026-09-05) | Not verifiedUnverified | 73.6 |
Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.
Benchmark receipts
- 2026-09-05: LiveBench official leaderboard (benchmark-owned), max effortContamination-resistant general capability across reasoning, coding, math, data analysis, and language, with monthly question refreshes. Comparability: comparable with caveat — Rolling question set: observations months apart measure different question mixes. Record the measurement date and compare within ~1 month windows.
- 2026-09-01: vals.ai SWE-bench Verified leaderboard (independent, mini-swe-agent bash-only) (independent; OpenAI did not report SWE-bench Verified for the GPT-5.6 family)Real GitHub issue resolution: does the model's patch pass the hidden tests. Comparability: comparable with caveat — Post-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.
- 2026-08-14: Artificial AnalysisComposite index blending reasoning, knowledge, and coding evals into one 0–100 score. Comparability: directly comparable — AA occasionally rebaselines the index scale between snapshots — a score captured on one date is only comparable to same-snapshot scores (check measuredAt).
- 2026-07-09: OpenAI GPT-5.6 announcement (vendor; chart transcribed by Vellum)Agentic terminal work: multi-step tasks executed in a sandboxed shell environment. Comparability: comparable with caveat — Scores across Terminal-Bench major versions (v1 vs v2) are NOT comparable; harness configuration (container, time limits) also shifts results.
Pricing tiers: DeepSeek V3.1: Third-party hosted ~$0.25/$0.95 per MTok; first-party peak/off-peak rates vary — verify on api-docs.deepseek.com. · GPT-5.6 Luna: Launch list was $1/$6; cut to $0.20/$1.20 on 2026-07-30. Cached input $0.02/MTok; batch $0.10/$0.60.
DeepSeek V3.1
DeepSeek V3.1 is the open-weight (MIT) general model — 671B/37B MoE, 128K context, strong reasoning at low cost.
Best for
- Cost-sensitive hosted agents
- High-volume coding assist
- Open-weight deployments
Watch out
Self-hosting needs datacentre VRAM; hosted rates differ by provider.
GPT-5.6 Luna
GPT-5.6 Luna is OpenAI's cheapest tier — roughly 1/25 of Opus 5-class input cost, suitable where quality requirements are modest.
Best for
- Classification
- High-volume chat
- Latency-sensitive pipelines
Watch out
Smallest GPT-5.6 tier; verify quality holds before routing frontier work to it.
When the cheaper one wins
DeepSeek V3.1 is cheaper on output at $0.95 per million tokens against $1.20 for GPT-5.6 Luna — about 1.3×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. These are standard-tier API rates, excluding batch and cache discounts.
Run the model pickerEvidence confidence: High
How strong and complete the evidence behind this comparison is — not a prediction of which model is better.
- Pricing verified on both sides — Input and output rates are verified for both models.
- 5/5 core specs verified on both sides — All core specifications verified for both models.
- 1 shared named benchmark with differing scores — Measured on: Artificial Analysis Intelligence Index.
- Verified within the last 90 days — Newest catalog check was 8 days ago.
- Both models carry source citations — Each side has at least two catalog sources on record.
Source receipts
Each catalog figure was checked against the provider or an independent second source on the date shown.
- DeepSeek V3.1: DeepSeek — V3.1 (accessed 2026-08-29)
- DeepSeek V3.1: CloudPrice — DeepSeek V3.1 (accessed 2026-08-29)
- GPT-5.6 Luna: OpenAI — GPT-5.6 (accessed 2026-08-29)
- GPT-5.6 Luna: OpenAI API pricing (gpt-5.6-luna $0.20/$1.20) (accessed 2026-08-29)
Related comparisons
- Claude Opus 5 vs GPT-5.6 Luna
- DeepSeek V4 Flash vs GPT-5.6 Luna
- Gemini 3.6 Flash vs GPT-5.6 Luna
- Gemini 3.7 Flash vs GPT-5.6 Luna
- GPT-5.6 Luna vs Grok 4.6
- Claude Haiku 4.5 vs DeepSeek V3.1
Diving deeper on one model? DeepSeek V3.1 · GPT-5.6 Luna
Common questions
DeepSeek V3.1 vs GPT-5.6 Luna
Answered from the verified figures on this page rather than general guidance.
Is DeepSeek V3.1 or GPT-5.6 Luna cheaper for input?
GPT-5.6 Luna is cheaper at $0.20 per million input tokens, against $0.25 for DeepSeek V3.1 — roughly 1.3× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; DeepSeek V3.1 has tiered pricing: Third-party hosted ~$0.25/$0.95 per MTok; first-party peak/off-peak rates vary — verify on api-docs.deepseek.com. GPT-5.6 Luna has tiered pricing: Launch list was $1/$6; cut to $0.20/$1.20 on 2026-07-30. Cached input $0.02/MTok; batch $0.10/$0.60.
Is DeepSeek V3.1 or GPT-5.6 Luna cheaper for output?
DeepSeek V3.1 is cheaper at $0.95 per million output tokens, against $1.20 for GPT-5.6 Luna — roughly 1.3× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; DeepSeek V3.1 has tiered pricing: Third-party hosted ~$0.25/$0.95 per MTok; first-party peak/off-peak rates vary — verify on api-docs.deepseek.com. GPT-5.6 Luna has tiered pricing: Launch list was $1/$6; cut to $0.20/$1.20 on 2026-07-30. Cached input $0.02/MTok; batch $0.10/$0.60.
Which has the larger context window, DeepSeek V3.1 or GPT-5.6 Luna?
GPT-5.6 Luna accepts 1.05M tokens against 128K for DeepSeek V3.1. This only matters if you routinely send very long documents or large codebases.
Do DeepSeek V3.1 and GPT-5.6 Luna support the same reasoning levels?
DeepSeek V3.1 exposes low, high, max, while GPT-5.6 Luna exposes none, low, medium, high.
Should I use DeepSeek V3.1 or GPT-5.6 Luna?
Both sit in the budget tier, so the choice usually comes down to price and context rather than capability. DeepSeek V3.1 suits cost-sensitive hosted agents; GPT-5.6 Luna suits classification.
Can I self-host DeepSeek V3.1 or GPT-5.6 Luna?
DeepSeek V3.1 publishes open weights, but self-hosting and third-party provider access depend on the licence, hardware, serving support, and availability. GPT-5.6 Luna is a closed model whose supported access paths are controlled by its provider.
Next step
Choosing between them
The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.
- Input price: GPT-5.6 Luna costs $0.20 per 1M tokens versus $0.25 for DeepSeek V3.1 — a 1.3x difference at the headline tier.
- Context: GPT-5.6 Luna takes 1.05M against 128K for DeepSeek V3.1 — only decisive if your prompts approach the smaller window.
- Measured capability: GPT-5.6 Luna leads Artificial Analysis Intelligence Index 47 to 44 (measured 2026-08-14).
- Deployment: DeepSeek V3.1 publishes weights you can self-host; the other is API-only.
Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.