DeepSeek V4 Flash 0731 vs Inkling Small vs GPT-6 Luna
GPT-6 Luna comes out ahead, 78 to 69 and 62 on our weighted score, though DeepSeek V4 Flash 0731 is 13% cheaper per token.
DeepSeekDeepSeek V4 Flash 0731
69/100- ECI154.5
- Price$0.14 / $0.28
- Context1M
Thinking MachinesInkling Small
62/100- ECI150.2
- Price$0.50 / $1.20
- Context1.05M
- Our pick
OpenAIGPT-6 Luna
78/100- ECI—
- Price$0.10 / $0.50
- Context1.05M
GPT-6 Luna is our pick
GPT-6 Luna is the better all-round choice, scoring 78/100 against DeepSeek V4 Flash 0731 (69) and Inkling Small (62). It leads on capability and inputs & features. DeepSeek V4 Flash 0731 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond, FrontierMath Tiers 1–3, OTIS Mock AIME 2024–2025 and SimpleQA Verified), because GPT-6 Luna has no Capabilities Index score yet.
- CapabilityGPT-6 LunaShared benchmarks: GPT-6 Luna 77.4% · DeepSeek V4 Flash 0731 69.2% · Inkling Small 61.0%
- Lowest priceDeepSeek V4 Flash 0731DeepSeek V4 Flash 0731 $0.175 · GPT-6 Luna $0.20 · Inkling Small $0.675 per 1M tokens (3:1 blend)
- Longest contextGPT-6 Luna and Inkling SmallGPT-6 Luna 1,050,000 · Inkling Small 1,048,576 · DeepSeek V4 Flash 0731 1,000,000 tokens
- Widest inputsInkling Small and GPT-6 LunaDeepSeek V4 Flash 0731: Text · Inkling Small: Text, Images, Audio · GPT-6 Luna: Text, Images, PDFs
- Self-hostingDeepSeek V4 Flash 0731 and Inkling SmallPublishes downloadable weights (MIT and Apache-2.0)
| Measure | Weight | DeepSeek V4 Flash 0731 | Inkling Small | GPT-6 Luna |
|---|---|---|---|---|
| CapabilityShared benchmarks | 50% | 69 | 61 | 77 |
| Price | 25% | 86 | 58 | 83 |
| Inputs & features | 15% | 45 | 70 | 80 |
| Context window | 10% | 60 | 61 | 61 |
| Overall | 100% | 69/100 | 62/100 | 78/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | DeepSeek V4 Flash 0731DeepSeek | Inkling SmallThinking Machines | GPT-6 LunaOpenAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 154.5 (best) | 150.2 | — |
| ECI rank | #32 of 148 (best) | #47 of 148 | — |
| GPQA DiamondGraduate-level science questions | 91.0% (best) | 88.5% | 90.5% |
| FrontierMath Tiers 1–3Research-level mathematics | 57.5% | 46.3% | 79.0% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 94.4% | 90.0% | 98.9% (best) |
| SimpleQA VerifiedShort factual questions | 33.6% | 19.1% | 41.4% (best) |
| Price per million tokens | |||
| Input | $0.14 | $0.50 | $0.10 (best) |
| Output | $0.28 (best) | $1.20 | $0.50 |
| Cached input | — | — | $0.01 |
| Blended (3:1) | $0.175 (best) | $0.675 | $0.20 |
| Long-context rate | Same rate | Same rate | Over 272K: $0.20 / $0.75 |
| Price source | Median of 48 providers | Median of 11 providers | Official OpenAI API |
| Limits | |||
| Context window | 1,000,000 tokens | 1,048,576 tokens | 1,050,000 tokens (best) |
| Max output | 384,000 tokens | 1,048,576 tokens (best) | 128,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | Yes |
| Audio | No | Yes | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | Yeslow · medium · high · xhigh · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | OpenMIT | OpenApache-2.0 | Proprietary |
| API model ID | — | — | gpt-6-luna |
| API providers | 49 (best) | 11 | 24 |
| Released | Jul 31, 2026 | Jul 30, 2026 | Sep 22, 2026 |
| Knowledge cutoff | May 2025 | — | May 18, 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- DeepSeek V4 Flash 0731$1.96
- Inkling Small$7.40
- GPT-6 Luna$2.00
Which should you choose?
Which is better: DeepSeek V4 Flash 0731, Inkling Small or GPT-6 Luna?
GPT-6 Luna is the better all-round choice, scoring 78/100 against DeepSeek V4 Flash 0731 (69) and Inkling Small (62). It leads on capability and inputs & features. DeepSeek V4 Flash 0731 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond, FrontierMath Tiers 1–3, OTIS Mock AIME 2024–2025 and SimpleQA Verified), because GPT-6 Luna has no Capabilities Index score yet.
Which is cheaper, DeepSeek V4 Flash 0731, Inkling Small or GPT-6 Luna?
DeepSeek V4 Flash 0731 is cheaper at $0.14 input / $0.28 output per million tokens (median across 48 API providers). GPT-6 Luna costs $0.10 input / $0.50 output per million tokens (official OpenAI API price); Inkling Small costs $0.50 input / $1.20 output per million tokens (median across 11 API providers). At a typical mix of three input tokens to one output token, that is $0.175 per million tokens for DeepSeek V4 Flash 0731 versus $0.20 for GPT-6 Luna (1.1× as much) and $0.675 for Inkling Small (3.9× as much).
Which scores higher on benchmarks?
Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond, FrontierMath Tiers 1–3, OTIS Mock AIME 2024–2025 and SimpleQA Verified): GPT-6 Luna 77.4%, DeepSeek V4 Flash 0731 69.2% and Inkling Small 61.0%. On individual benchmarks: GPQA Diamond — DeepSeek V4 Flash 0731 91.0%, GPT-6 Luna 90.5%, Inkling Small 88.5%; FrontierMath Tiers 1–3 — GPT-6 Luna 79.0%, DeepSeek V4 Flash 0731 57.5%, Inkling Small 46.3%; OTIS Mock AIME 2024–2025 — GPT-6 Luna 98.9%, DeepSeek V4 Flash 0731 94.4%, Inkling Small 90.0%; SimpleQA Verified — GPT-6 Luna 41.4%, DeepSeek V4 Flash 0731 33.6%, Inkling Small 19.1%.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek V4 Flash 0731, Inkling Small and GPT-6 Luna yet, so there is no like-for-like coding score. On overall capability, GPT-6 Luna leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
GPT-6 Luna and Inkling Small have the largest context windows (1,050,000 and 1,048,576 tokens), against 1,000,000 for DeepSeek V4 Flash 0731. Maximum output per response: DeepSeek V4 Flash 0731 up to 384,000, Inkling Small up to 1,048,576, GPT-6 Luna up to 128,000 tokens.
Which can read images, PDFs, audio or video?
DeepSeek V4 Flash 0731 accepts text; Inkling Small accepts text, images and audio; GPT-6 Luna accepts text, images and PDFs. Inkling Small handles the widest range of inputs.
Are any of these open source?
DeepSeek V4 Flash 0731 and Inkling Small publishes its weights (MIT and Apache-2.0) and can be self-hosted; GPT-6 Luna is proprietary.
Which is newer?
GPT-6 Luna is the newest, released Sep 22, 2026. DeepSeek V4 Flash 0731 came out Jul 31, 2026; Inkling Small came out Jul 30, 2026. Knowledge cutoff: DeepSeek V4 Flash 0731 May 2025, GPT-6 Luna May 18, 2026.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
Related comparisons
- DeepSeek V4 Flash 0731 vs GLM-5.3-FlashZ.ai (Zhipu) · ECI 151.9
- DeepSeek V4 Flash 0731 vs Gemini 3.6 FlashGoogle · ECI 154.3
- Inkling Small vs Qwen3.8 27BAlibaba (Qwen) · ECI 149.4
- Inkling Small vs MiniMax-M3MiniMax · ECI 147.0
- Inkling Small vs Kimi K2.7 CodeMoonshot AI · ECI 150.0
- Inkling Small vs Gemini 3.5 Flash LiteGoogle · ECI 145.1
