DeepSeek V4 Pro vs GPT-5.6 Luna
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by DeepSeek
3 providers:
DeepSeek $0.435/$0.870
Fireworks $1.74/$3.48
Together $1.74/$3.48
|
by OpenAI
|
|---|---|---|
| Overview | ||
| Status | Current mid tier | Current mid tier |
| Released | Apr 24, 2026 | Jul 9, 2026 |
| Pricing per million tokens | ||
| Input | $0.435/Mtok | $0.200/Mtok |
| Output | $0.870/Mtok | $1.20/Mtok |
| Blended avg | $0.652/Mtok | $0.700/Mtok |
| Cached input | $0.004/Mtok | $0.020/Mtok |
| Specifications | ||
| Context window | 1M tokens | 1M tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
textimage
|
| Benchmarks source: Vellum LLM Leaderboard | ||
| Avg benchmark score | 71.5 | 90.7 |
| Perf / dollar | 109.6 | 25.9 |
| GPQA Diamond | 90.1 | 92.3 |
| SWE-Bench Verified | 50 | 93 |
| HumanEval | 80.6 | 93 |
| Terminal-Bench 2.1 | — | 84.3 |
| LiveCodeBench | 93.5 | — |
| MCP Atlas | 73.6 | — |
| BrowseComp | 83.4 | — |
| Humanity's Last Exam | 48.2 | — |
| ARC-AGI 2 | 30 | — |
| AIME 2025 | 75 | — |
| MMMLU | 82 | — |
| BFCL | 72 | — |
| MATH 500 | 80 | — |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 44.3 | 51.2 |
| AA Agentic Index | 36.4 | 45.6 |
| AA-Omniscience Index (−100–100) | -10 | -11.2 |
| GDPval-AA v2 | 1304.5 ELO | 1581.9 ELO |
| LMSYS Chatbot Arena | 1457.9 ELO | — |
| Providers | ||
| Available from |
DeepSeek — $0.435/$0.870/Mtok
Fireworks — $1.74/$3.48/Mtok
Together — $1.74/$3.48/Mtok
|
OpenAI — $0.200/$1.20/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | DeepSeek V4 Pro | GPT-5.6 Luna | Savings |
|---|---|---|---|
| 1M tokens | $0.65 | $0.7 | $0.05 (7.1%) |
| 10M tokens | $6.53 | $7 | $0.48 (6.9%) |
| 100M tokens | $65.25 | $70 | $4.75 (6.8%) |
| 1000M tokens | $652.5 | $700 | $47.5 (6.8%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.652/Mtok blended vs $0.700 — 6.8% less on the same 50/50 token mix
- your workload re-reads context (agents, RAG, long chats): cached input costs $0.004/Mtok — 99% off its list input price
- provider flexibility: available from 3 providers, so you can price-shop hosts or fail over
- raw capability matters more than price: 90.7 vs 71.5 average benchmark score
Price movement
recorded changes since we began tracking each model · last checked Aug 1, 2026| Model | Changes | Latest move | Old → new $/M |
|---|---|---|---|
| DeepSeek V4 Pro | 0 | — no move | Stable since we began tracking — no change recorded |
| GPT-5.6 Luna | 1 | price cut on Aug 1, 2026 | $1/$6 → $0.2/$1.2/Mtok |
The cheaper option here — DeepSeek V4 Pro costs $0.652/Mtok blended on DeepSeek.
Summary
DeepSeek V4 Pro by DeepSeek costs $0.435/Mtok input and $0.870/Mtok output, with a 1M-token context window. It supports text input and is available from 3 providers.
GPT-5.6 Luna by OpenAI costs $0.200/Mtok input and $1.20/Mtok output, with a 1M-token context window. It supports text, image input.
On a blended cost basis, DeepSeek V4 Pro is 6.8% cheaper than GPT-5.6 Luna.
On benchmarks, GPT-5.6 Luna scores higher (90.7 vs 71.5) on average. In terms of value, DeepSeek V4 Pro has better performance per dollar (109.6 vs 25.9).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.