
DeepSeek V4 Pro
DeepSeek
- Bağlam penceresi
- 1M 1.048.576 token
- Girdi / Çıktı
- metin → metin
API fiyatları
USD / 1 milyon token
| Girdi | Çıktı | Önbellekten girdi |
|---|---|---|
|
|
|
Zaman çizelgesi
- · Ağırlık sürümü · kanıt bağlantısı
Girdi / çıktı fiyatı · USD / 1 milyon token
| Model | Kanıt bağlantıları | Girdi / çıktı fiyatı |
|---|---|---|
deepseek-v4-prostandard | deepseek | $0,66 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $1,32 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) / $1,98 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $3,96 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) |
deepseek-v4-prostandard · metin | opencode-go | $0,66 (When not (UTC days: mon, tue, wed, thu, fri and ((UTC time >= 01:00 and UTC time < 04:00) or (UTC time >= 06:00 and UTC time < 10:00)))); $1,32 (UTC days: mon, tue, wed, thu, fri and ((UTC time >= 01:00 and UTC time < 04:00) or (UTC time >= 06:00 and UTC time < 10:00))) / $1,98 (When not (UTC days: mon, tue, wed, thu, fri and ((UTC time >= 01:00 and UTC time < 04:00) or (UTC time >= 06:00 and UTC time < 10:00)))); $3,96 (UTC days: mon, tue, wed, thu, fri and ((UTC time >= 01:00 and UTC time < 04:00) or (UTC time >= 06:00 and UTC time < 10:00))) |
deepseek/deepseek-v4-prostandard | openrouter | $0,90 / $1,50 |
deepseek/deepseek-v4-prostandard | vercel-gateway | $1,32 / $3,96 |
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · oxstack/ox-llm · @n0rpan
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · openJiuwen-ai/jiuwenswarm · @Gaohan123
Alıntı
Model: deepseek-v4-pro
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · huynhtandat223/firstmate · @huynhtandat223
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · aryangantenk-dev/ynx · @aryangantenk-dev
Alıntı
| `free/deepseek-v4-pro` | 502 — *key is not allowed to use model* |
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · NoFxAiOS/nofx · @deanokk
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · Codeseys-Labs/t3factory · @baladithyab
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · windless0530/super-agent · @windless0530
Alıntı
- gen_bot_settings: router model fallback deepseek-v4-pro committed
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · wyolet/relay-catalog · @aaliboyev
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · phanmi/tyler_agent · @phanmi
Alıntı
showed two suggested models were a poor choice: `deepseek-v4-pro` was worse than `deepseek-flash` at several times the cost, and `gpt-5.6` cost twice as much as
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · oxstack/ox-llm · @n0rpan
Alıntı
**Tier: T1.** Test-only change, done through oxa (model: openrouter/deepseek-v4-pro), verified from outside oxa.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · mdiri-ai/SoduWork · @hugengyong
Alıntı
Use DeepSeek’s documented context window for `deepseek-flash` and `deepseek-v4-pro` when the route lacks an explicit limit. See [DeepSeek model metadata](https://api-docs.deepseek.com/api/list-models/).
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · jgong5/ATOM · @Phi-C
Alıntı
128 and 256, made by: AITER_BF16_FP8_MOE_BOUND=0 ATOM_MOE_GU_ITLV=1 TRACES=traces.jsonl MODEL=DeepSeek-V4-Pro GPU=0,1,2,3,4,5,6,7 SERVER_ARGS='--tensor-parallel-size 8 --kv-cache-dtype fp8 --enable-prefix-caching --max-num-seqs 512 --index-cache-dtype fp4 --method mtp --num-speculative-tokens 3 --spec-decode-acceptance-length 2.49
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · Solizardking/clawdb0t · @Solizardking
Alıntı
The model defaults now match `pkg/config/config.go` (`grok-4.5`, with `deepseek-v4-pro` as fallback). Spawn inheritance now says that `.solana/` and `.grok/` are not checked in.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · SaikiK12/T · @SaikiK12
Alıntı
four independent reasoning workers on **different models** (qwen3.7-max, deepseek-v4-pro, qwen3.7-plus) over one shared evidence pack, with the coordinator recomputing every number from committed files.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · NVIDIA-NeMo/Megatron-Bridge · @cuichenx
Alıntı
- [x] DeepSeek V4 Pro BF16: full model, 256 GPUs, 50 updates, eager defaults and clean exit (`1079973`).
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · LavishSphere/faultline · @LavishSphere
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · wilsoncheryl06/wil · @wilsoncheryl06
Alıntı
本文实测DeepSeek-V4-Pro GA版(0813构建)的1M tokens上下文能力,验证其在42万token长文档跨章节问答中的实用性;重点介绍通过TaoToken统一Key实现OpenAI兼容API接入的方法,涵盖Base URL、Model ID配置规范及Codex/Claude Code/Cline/Python客户端的可复用配置;同步分析401、local proxy failed、reading choices等典型报错根因与修复方案,并强调MoE架构下的延迟波动、并发限流(500)与429重试策略。
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · HolmesGPT/holmesgpt · @github-actions[bot]
Alıntı
opus-5.5-medium,sonnet-5.5-medium,gpt-6.1-sol-high,haiku-4.5,gemini-3.1-pro-preview,deepseek-v4-pro,kimi-k3,glm-5.3
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · praveenchunduru/IntrinsicValue · @praveenchunduru
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · jpenilla/pi-cloudflare-ai-gateway-native · @renovate[bot]
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · deepseek-ai/awesome-deepseek-integration · @tokeny-ai
Alıntı
The preview screenshot shows the chat input with `deepseek-v4-pro` selected.
- · Alex'in gönderileri · model ailesi · GitHub search · DeepSeek · pulls · babyLegionite/ds4 · @babyLegionite
Alıntı
c35cf38 models: download the DeepSeek V4 Pro 0813 quant
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · CaffeeLake/Roo-Cline · @renovate[bot]
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · walshjessica859/wal · @walshjessica859
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · takeuchihomeys-svg/sumora-ai-ui · @takeuchihomeys-svg
Alıntı
| `app/lib/deepseek-models.ts` | モデル名を1か所で持つ(`deepseek-v4-pro` / `deepseek-flash`)・推論用の安全な max_tokens |
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · knoel99/frontier-one · @claude
Alıntı
through a gateway, the call was billed as deepseek-v4-pro. Kimi and ZCode ran
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · vllm-project/vllm · @ChengYM5685
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · thevibeworks/deepseek-docs · @github-actions[bot]
Alıntı
Alpha Search by default for both `deepseek-flash` and `deepseek-v4-pro` and requires Codex 0.164+; config keys change to `standalone_web_search` / `supports_standalone_web_search`, the old top-level `web_search =
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · stayboy/MemberRegistrations · @stayboy
Alıntı
(both skill files, `AGENTS.md`, the policy, `lessons.md`) from `deepseek-v4-pro` build `0813`, across two review rounds — the second confirming the three P2 fixes, including a
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · stablyai/orca · @dandaka
Alıntı
External contributor. AI coding agent (OMP harness, deepseek-v4-pro model) assisted with implementation, regression test authoring, and self-review.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · murmurwang/arcfold-dsh-public · @murmurwang
Alıntı
- Explain when first setup selects DeepSeek V4 Pro in the installed plugin description and correct the local release guide.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · lidge-jun/opencodex · @henrikdukefoss
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · docwilde/doxa · @docwilde
Alıntı
- **`deepseek-v4-pro`:** refused; the provider documents no vision support.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · bogheorghiu/shared-rules · @vasana-bot
Alıntı
- `council_hub.py`: several models (Fable 5.2, Kimi K3.1 Pro, DeepSeek V4 Pro) stream into one room.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · MYLEGND/masterapp · @MYLEGND
Alıntı
- regression now locks the exact five-model set: Qwen3-30B-A3B-FP8, GPT-OSS-120B, GLM-5.3 Flash, GLM-5.3, and DeepSeek V4 Pro, with GPT-OSS-120B as the general primary model;
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · deximple/model-tf · @github-actions[bot]
Alıntı
- Added entry: `deepseek/deepseek-v4-pro` (high) — tier `low`, rank `{'simpleCoding': 63, 'reasoning': 60}`
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · ZAF07/zeph · @ZAF07
Alıntı
Model Prices in SGD seeded for deepseek-flash and deepseek-v4-pro Merge eval dashboard issue 01 grilling: Admins run Evals from the Dashboard or make eval in
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · ZAF07/zeph · @ZAF07
Alıntı
a Model Prices tab, seeded deepseek-flash 0.38/1.54 and deepseek-v4-pro 1.69/5.07 SGD per 1M; estimate on New run from each case's last run or a rough
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · whutlichao/worksplice · @whutlichao
Alıntı
without loading extensions”; actual models include `deepseek-flash` and `deepseek-v4-pro`, expected `[]`.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · strikersam/autonomous-ai-agency · @strikersam
Alıntı
config/llm/models.yaml:127 and packages/ai/brain_config.py:376, plus the cost table (cost_tracker.py:87). deepseek-ai/deepseek-v4-pro appears in the touched non-test files only in comments, and in cost_tracker.py:45 as a (0,0) cost
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · kucingapi/final-portfolio · @kucingapi
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · jgong5/ATOM · @Phi-C
Alıntı
Model: /shared_nfs/huggingface_models/deepseek-ai/DeepSeek-V4-Pro, on MI355X nodes
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · jgong5/ATOM · @Phi-C
Alıntı
The template's reference layer, from the InferenceX API's `benchmarks?model=DeepSeek-V4-Pro` rows for ATOM on MI355X agentic traces: TP8 at 5 concurrencies, DPA8 EP8 at 4, DPA8
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · jgong5/ATOM · @Phi-C
Alıntı
S1 with `"model": "1498/model/DeepSeek-V4-Pro"` from `agent_scratch`: missing a law (1), as with the whole path.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · apache/maka · @M4n5ter
Alıntı
- Offer provider-native web search by default on supported routes. ChatGPT Subscription and DeepSeek V4 Pro use `web_search`. DeepSeek Flash uses `deepseek_web_search`.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · PrepLabsAI/Rovara · @abhishek255
Alıntı
- **Models (6):** Sonnet 4.6 (baseline), GLM 5.3, DeepSeek V4 Pro, Kimi K2.6, Qwen3 Coder Plus, MiniMax M3.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · Kreijstal/pi-managed-workflow · @renovate[bot]
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · HolmesGPT/holmesgpt · @github-actions[bot]
Alıntı
Command**: ./run_benchmarks_local.py --benchmark-type fast-benchmark --models opus-5.5-medium,sonnet-5.5-medium,gpt-6.1-sol-high,haiku-4.5,gemini-3.1-pro-preview,deepseek-v4-pro,kimi-k3,glm-5.3
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · Hathi-Labs/Metorite · @vjvarada
Alıntı
counts less.** Before, an unmapped call kept the `deepseek-v4-pro` card, whatever served it. Now the card of the served model prices it. So a call
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · Fosowl/agenticSeek · @Felixkw12
Alıntı
Model ids are pool names such as `deepseek-v4-pro` or `claude-sonnet-4-6`, and Opper picks the provider per request. A `provider/model` id such as `aws/claude-sonnet-4-6-eu` pins one
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · robinsonalexandra27/rob · @robinsonalexandra27
Alıntı
本教程详解如何通过CC-Switch工具将Claude Code的Base URL切换至TaoToken兼容端点,从而调用DeepSeek-V4-Pro模型。涵盖环境准备、CC-Switch配置(API Key、Base URL、Auth Type、Model ID)、配置验证、401等常见错误排查及IDEA中CC GUI插件联动方法。核心依赖信息技术要素包括Anthropic协议兼容、API网关路由、环境变量注入与CLI配置管理。
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · ortizmatthew30/ort · @ortizmatthew30
Alıntı
本教程详解在Windows环境下通过winget安装Claude Code,利用cc-switch工具管理多模型配置,并成功接入DeepSeek-V4-pro模型。内容涵盖TaoToken兼容接口配置(Base URL、API Key、Model ID)、settings.json配置要点、对话与skill验证方法,以及401认证失败、local proxy failed、reading choices等高频报错的精准排查方案,强调环境变量生效时机与配置文件路径等关键技术细节。
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · cruzjoshua138/cru · @cruzjoshua138
Alıntı
本文通过API实测分析DeepSeek V4 Pro在Codex与Claude Code两种coding agent框架下的兼容性差异。结果表明:该模型支持OpenAI-compatible chat completions接口,但无法通过Codex依赖的responses接口;而借助Claude Messages兼容层可实现工具调用闭环。核心问题在于协议语义不匹配——Codex要求结构化agent loop输出,而DeepSeek V4 Pro当前仅适配通用聊天协议。reasoning tokens占用输出预算亦影响实际可用性。
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · oxstack/ox-llm · @n0rpan
Alıntı
the unattended goal loop (O-238) on n0rpan, model `openrouter/deepseek-v4-pro`; outside checks: checks green.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · oxstack/ox-llm · @n0rpan
Alıntı
**oxa** in the unattended goal loop (O-238), model `openrouter/deepseek-v4-pro`; outside checks: checks green.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · oxstack/ox-llm · @n0rpan
Alıntı
**Written by oxa**, model `openrouter/deepseek-v4-pro` via oxc (cloud-only install), on `air` (aarch64 Linux, non-Snapdragon). A first attempt with `openai/gpt-6-luna` died on #64 (tool `s`, then
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · orioli/IM-LLM · @Mihawii
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · melsofany/Rfq-Manager · @melsofany
Alıntı
| صف الإعدادات في الإنتاج | `model = deepseek-v4-pro` |
- · Alex'in gönderileri · model ailesi · GitHub search · DeepSeek · pulls · darkdiamond/pi-jfrog-boost · @dependabot[bot]
Alıntı
thinking level controls after Together renamed it to <code>deepseek-ai/DeepSeek-V4-Pro-0813</code> (<a href="https://redirect.github.com/earendil-works/pi/pull/10336">#10336</a> by <a href="https://github.com/cv"><code>@cv</code></a>)</li>
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · br41s/hermes-sandbox · @br41s
Alıntı
Investigating the owl-alpha → paid `deepseek/deepseek-v4-pro` migration, production Langfuse traces showed the auditor's DeepSeek calls caching erratically (~56% hit / ~44% full-prefix re-bills). Root cause:
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · br41s/hermes-sandbox · @br41s
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · GoDanceAi/godance · @SummerTiger
Alıntı
-H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' -d '{"model":"deepseek-v4-pro","messages":[{"role":"user","content":[{"type":"image_url","image_url":{"url":"data:image/png;base64,'$B64'"}}]}]}'
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · puffdog-git/dsh-discord-cyberfriend · @puffdog-git
Alıntı
another platform. They now default to deepseek-account and deepseek-v4-pro, and an unknown service falls back to deepseek-account
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · kingithegreat/Sadie · @kingithegreat
Alıntı
* fix(models): use DeepSeek's current model IDs (deepseek-flash, deepseek-v4-pro)
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · openclaw/openclaw · @SlowikInspiruje
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · murmurwang/arcfold-dsh-public · @murmurwang
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · logicplanes/kaeso · @dvnold
Alıntı
the other makers' models TokenHub serves, such as `deepseek-v4-pro`, `glm-5.3` and `kimi-k3`, and the embeddings models `kinfra-text-embedding-0.6b` and `-4b`, from apps in any format. TokenHub
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · dietrichliko/vfgh-llm-bench · @dietrichliko
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · anomalyco/models.dev · @victor-zzh
Alıntı
- Text-only models (DeepSeek V4 Pro, GLM-5.3) return 400 `image_input_not_supported` on image input.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · ai-dynamo/dynamo · @galletas1712
Alıntı
GLM-5.2 and DeepSeek-V4-Pro, each serving correct inference after promotion.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · Conquest-of-AzerothCore/azerothcore-wotlk-coa · @dijikstraa
Alıntı
description were prepared with AI (DeepSeek Harness; models deepseek-v4-pro and deepseek-flash; no subagents; superpowers not used — unavailable, phases followed by hand).*
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · ChidiRnweke/FollowThrough.ai · @ChidiRnweke
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · zjunlp/HarnessGrad · @crepuscular-drizzle
Alıntı
- Allow `deepseek-v4-pro` as the task agent and as an explicit model override for the built-in `deepseek` endpoint improver. The improver still defaults to `deepseek-flash`.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · oxstack/ox-llm · @n0rpan
Alıntı
**Written by oxa itself (dogfood round 3), model `openrouter/deepseek-v4-pro` via oxc.** Committed and pushed by the driver. Fixes #75.
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · murmurwang/arcfold-dsh-public · @murmurwang
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · kingithegreat/Sadie · @kingithegreat
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · automagik-si/arca · @namastex888
Alıntı
(`working_directory`), `bash` was allowed, and the model stayed `deepseek-v4-pro`. Against the round-1 code, 9 unit tests failed on behaviour: the switch, the live failure, the
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · The-PR-Agent/pr-agent · @JRedOW
Alıntı
chars of reasoning over 616s with no answer. `deepseek-v4-pro` and `qwen3.8-flash` behaved the same, while `glm-5.3-flash` answered in 44s and `deepseek-v4.1-flash` with `reasoning_effort = "none"`
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · SillyTavern/SillyTavern · @Wolfsblvt
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · freemanshawna97/fre · @freemanshawna97
Alıntı
OpenAI API疑似泄露GPT-6 Sol模型,发布节奏或提前;马斯克确认Grok 4.7因强化学习调优问题延期;月之暗面全量开放Kimi K2.8-Preview,支持100万token上下文,编码能力逼近K3。DeepSeek V4 Pro API继续运营,Devin Fusion、Cursor Projects等智能体新工具涌现,AI模型竞争进入上下文与协作新阶段。
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · valentinyeo/calorie-mcp-proto · @valentinyeo
Alıntı
in the 1.5.2 tarball, which lists `deepseek-v4.1-flash` and `deepseek-v4-pro` |
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · RyanZhangNTU/codex-pacer · @RyanZhangNTU
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · yetone/magpie · @yetone
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · whistlegraph/aesthetic-computer · @whistlegraph
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · duketopceo/open-computer · @duketopceo
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · FrancisCrickInstitute/Data-Prospector · @djpbarry
- · Kanıt bağlantıları · GitHub search · DeepSeek · commits · Ayasesaki7/nai-relay · @Ayasesaki7
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · stSoftwareAU/VibeCoder · @VibeCoderST
Alıntı
C - ->|usage limit, or no credential| D["DeepSeek deepseek-v4-pro"]
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · razzant/ouroboros · @login4all
Alıntı
- Reviewer model and effort: `deepseek/deepseek-v4-pro`, high reasoning effort
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · maximhq/bifrost · @jimaldon
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · maximhq/bifrost · @neta79
Alıntı
- **`ui/lib/constants/config.ts`** — Model placeholder (`e.g. deepseek-chat, deepseek-v4-pro`) and key requirement entry
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · maximhq/bifrost · @truffle-dev
Alıntı
returns IDs with the inference-provider segment duplicated, e.g. `huggingface/cohere/featherless-ai/deepseek-ai/DeepSeek-V4-Pro`. Requests against those IDs fail because `splitIntoModelProvider` parses the first segment (`cohere`) as the inference provider
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · iv-org/invidious · @Fijxu
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · iv-org/invidious · @Fijxu
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · iv-org/invidious · @Fijxu
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · anomalyco/models.dev · @models-dev-automation[bot]
- · Kanıt bağlantıları · GitHub search · DeepSeek · pulls · JSchmid6/wireguard-ops-cockpit · @JSchmid6
Alıntı
- Der in das Release eingebaute Katalog kennt `deepseek/deepseek-v4-pro` und `opencode/big-pickle`. Ohne Netz läuft opencode genauso.
- · Kanıt bağlantıları · DeepSeek · Research & News articles
Alıntı
Starting at 04:00 UTC on Sept 14, 2026, all deepseek-v4-pro requests will route to V4.1-Flash at V4.1-Flash rates
- · Kanıt bağlantıları · DeepSeek · updates
Alıntı
The official release of DeepSeek-V4-Pro will follow soon
- · Alex'in gönderileri · Alex Getman
Alıntı
⚡️ OpenAI just slashed GPT 5.6 prices Luna is now 80% cheaper, while Terra dropped 20%. The cuts also apply to subscriptions, with both models now using less of your quota. Luna is now cheaper than DeepSeek V4 Pro on input. One million tokens cost $0.20 vs $0.435.
Sinyaller 2
DeepSeek V4 Pro tespit edildi: OpenRouter
Özellikler
DeepSeek V4 Pro, DeepSeek tarafından geliştirilen bir yapay zekâ modelidir. Modelin ağırlıkları kamuya açıktır. Yayın tarihi: 2026-04-24. Bağlam penceresi 1.048.576 token uzunluğundadır. Bir milyon token başına giriş ücreti $0,66 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $1,32 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.), çıkış ücreti $1,98 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $3,96 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) tutarındadır.
- Bağlam penceresi
- 1.048.576
- Girdi
- metin
- Çıktı
- metin
- Ağırlıklar
- Açık
- Girdi · USD / 1 milyon token
- $0,66 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $1,32 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.)
- Çıktı · USD / 1 milyon token
- $1,98 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $3,96 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.)
- Önbellekten girdi · USD / 1 milyon token
- $0,022 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $0,044 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.)
Sorular
DeepSeek V4 Pro modelinin bağlam penceresi ne kadar?
Bağlam penceresi 1.048.576 token uzunluğundadır.
DeepSeek V4 Pro modelinin fiyatı nedir?
Bir milyon token başına giriş ücreti $0,66 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $1,32 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.), çıkış ücreti $1,98 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $3,96 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) tutarındadır. Önbellekten girdi fiyatı milyon token başına $0,022 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $0,044 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.).
DeepSeek V4 Pro modelinin ağırlıkları kamuya açık mı?
Evet. DeepSeek model ağırlıklarını yayınlar.
DeepSeek V4 Pro ne zaman piyasaya sürüldü?
2026-04-24.