Topic
Deepseek
Start here: How to Run DeepSeek V4 Pro via API in 2026 — Every Host Compared — DeAI's reference piece on this topic.
DeepInfra Pricing in 2026: Every Model Priced, Verified
DeepInfra prices 100+ open models per token as of 2026-10-13: DeepSeek V4 Flash $0.06/$0.18 per million, Kimi K3 $2.85/$14.25, Claude and Gemini also listed.
Price Index Delta: DeepSeek V4 Pro Snaps Back, GLM-5.3 Flash Scissors
OpenRouter list-price delta, 2026-10-12: DeepSeek V4 Pro snapped back 358% to $0.9553/$1.9105; GLM-5.3 Flash cut input 85% while output rose 140%.
Open-source ARTEX agent ran DeepSeek V4.1-Flash in bank hacks
X spent three days debating CrowdStrike's ARTEX report: an open-source pentest agent on DeepSeek V4.1-Flash hit South Korean banks, leaking 66,000 records.
Ecosia drops Mistral for Chinese open weights on EU-hosted Melious
Ecosia is dropping Mistral for Chinese open-weight models via EU-hosted Melious, as its CEO claims costs roughly halved and calls Mistral 'a year behind'.
Mistral Large 4 preview: 1T-param MoE, open weights due end of October
Mistral AI's Large 4 is in public preview: a 1T-parameter MoE with 49B active scoring 38 on the AA index, open weights promised by end of October.
SambaNova Cloud in 2026: RDU Inference Priced Across Its Whole Catalog
SambaNova Cloud runs open models on RDU silicon. We priced all 7 models as of 2026-10-06: $0.22/$0.59 on gpt-oss-120b up to $3/$4.50 on DeepSeek V3.1.
Price Index Delta: DeepSeek Doubles, Kimi K3 Splits, gpt-oss Reverts
OpenRouter list-price delta, 2026-10-05: DeepSeek V4.1 Flash doubled to $0.30/$1.20 per million tokens; Kimi K3 split its spread; gpt-oss-120b reverted.
How to Run DeepSeek V4 Flash via API in 2026 (Priced)
DeepSeek V4 Flash's official API is $0.14/$0.28 per million tokens; third-party hosts undercut it. How to run the $0.14/M workhorse, from keys to cutover.
Price Index Delta: Kimi K3 Cuts 36%, DeepSeek Reverts to Off-Peak
Week-over-week OpenRouter list-price delta, 2026-09-21: Kimi K3 down 36% to $1.70/$8.50 per million tokens; DeepSeek V4.1 Flash halved to $0.15/$0.60 off-peak.
Vercel gateway data shows open models at a record 78.4% of tokens
X is celebrating Vercel's claim that open-weight models hit 78.4% of AI Gateway token volume, with open-lab spend passing OpenAI. It is one gateway's sample.
Price Index Delta: DeepSeek V4.1 Flash Lands, GLM Flash Doubles
Week-over-week OpenRouter list-price delta, 2026-09-14 vs 2026-09-07: DeepSeek V4 Flash 0731 fell 57% to $0.06/$0.12 per million tokens; GLM-5.3 Flash doubled.
DeepSeek retires V4-Flash in a silent swap, spares V4-Pro
DeepSeek retired legacy V4-Flash IDs into V4.1-Flash ($0.30/$1.20 per M) and reversed its V4-Pro shutdown — two changes buried in pricing-page footnotes.
DeepSeek V4.1-Flash: builders argue over the 890-byte KV cache
DeepSeek's MIT-licensed V4.1-Flash drew 1.37M X views in five hours. Verified: 552B MoE weights on Hugging Face, 1M context, $0.003/M cached input.
Open-Model Inference Prices, September 2026
On 2026-09-07 OpenRouter listed gpt-oss-120b at $0.037/$0.17 per million tokens and DeepSeek V4 Flash 0731 at $0.14/$0.28, matching DeepSeek's official API.
The Cheapest LLM APIs in 2026 — 14 Providers Priced per Million Tokens
The cheapest LLM APIs in 2026 start at $0.14 per million input tokens (DeepSeek V4 Flash, as of 2026-08-20). Compare 14 providers and pricing models.
DeepSeek API: Official vs Third-Party Hosts (2026) — Privacy & Price
DeepSeek's official API stores data under Chinese jurisdiction; third-party hosts run the same open weights elsewhere. Compare 5 routes on privacy and price.
Does DeepSeek Store Your Data? Jurisdiction and the Policy (2026)
Yes — DeepSeek's apps store prompts on servers in China per its privacy policy. Here are the 3 data paths (app, API, self-hosted) and what each retains.
Leaving the Anthropic API: Open-Model Equivalents & the Switch (2026)
A practical guide to leaving the Anthropic API: map Claude workloads to open-weight models, choose a host, and swap one base URL. Code and checklist included.
Migrate Off the OpenAI API in an Afternoon (2026 — Code Included)
Migrate from the OpenAI API in one afternoon: swap the base URL (3 lines of code), remap model names to open weights, and canary 5% of traffic for 2 hours.
Open-Weight vs Open-Source AI Models: The Difference That Bites (2026)
Open-weight means you can download the weights; open-source means you get real rights. Why the gap matters in 2026, with 4 license traps to check first.
How to Run DeepSeek V4 Pro via API in 2026 — Every Host Compared
Every way to run DeepSeek V4 Pro via API in 2026 — official API, third-party hosts, aggregators, self-hosting — plus its self-reported 80.6% SWE-bench score.
