From 11a1641a438ba4c19a45e915756cccc5a6f76642 Mon Sep 17 00:00:00 2001 From: pdparchitect Date: Thu, 10 Sep 2026 11:58:38 +0000 Subject: [PATCH] chore(release): prepare platform 0.3.1 (+1 more) - chore(release): prepare platform 0.3.1 - feat: add DeepSeek V4.1 Flash model configurations for multiple providers --- CHANGELOG.md | 8 +++ package.json | 2 +- platform/config/models.ts | 146 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 155 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 44c49b7..2b4b4ce 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,6 +5,14 @@ here. The release version is defined in the workspace root `package.json`. ## [Unreleased] +## [0.3.1] - 2026-09-10 + +### Added + +- Support DeepSeek V4.1 Flash through Vercel AI Gateway, DeepSeek, and + OpenRouter, with image input, reasoning, tool calls, provider-specific model + identifiers, token limits, and usage pricing. + ## [0.3.0] - 2026-09-10 ### Added diff --git a/package.json b/package.json index fbd3244..00cb134 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "platform", - "version": "0.3.0", + "version": "0.3.1", "private": true, "license": "Apache-2.0", "packageManager": "pnpm@11.24.0", diff --git a/platform/config/models.ts b/platform/config/models.ts index ffc064d..36cc2ab 100644 --- a/platform/config/models.ts +++ b/platform/config/models.ts @@ -2096,6 +2096,52 @@ export const openrouterLanguageModels: Record< // deepseek + 'deepseek-v4.1-flash': { + description: `DeepSeek V4.1 Flash combines fast reasoning, coding, tool use, and native image understanding with a million-token context window.`, + + provider: 'openrouter', + + providerModel: 'deepseek/deepseek-v4.1-flash', + + family: 'deepseek', + + features: ['chat', 'functions', 'image', 'reasoning'], + + region: 'us', + availableRegions: ['us'], + + featured: true, + + maxTokens: 1_048_576, + maxInputTokens: 1_048_576 - 384_000, + maxOutputTokens: 384_000, + + // @note published off-peak pricing; provider peak-hour rates may be higher + pricing: { + tokenRatio: 0.0333, + inputTokenRatio: 0.0107, + outputTokenRatio: 0.0333, + inputPrice: 0.15, + outputPrice: 0.6, + }, + + interactionMaxMessages: DEFAULT_INTERACTION_MAX_MESSAGES, + + thresholdStrategy: 'truncate', + + visible: true, + deprecated: false, + + temperature: DEFAULT_TEMPERATURE, + + frequencyPenalty: 0, + presencePenalty: 0, + + tags: [], + + addedDate: '2026-09-10', + }, + 'deepseek-v4-pro': { description: `Top-tier DeepSeek reasoning and coding for the most demanding production workloads. Built for high-context tasks that benefit from deeper deliberation.`, @@ -4312,6 +4358,58 @@ export const vercelLanguageModels: Record< addedDate: '2026-04-24', }, + 'deepseek-v4.1-flash': { + description: `DeepSeek V4.1 Flash combines fast reasoning, coding, tool use, and native image understanding with a million-token context window.`, + + provider: 'vercel', + + providerModel: 'deepseek/deepseek-v4.1-flash', + + providerOptions: { + gateway: { + zeroDataRetention: false, + }, + }, + + family: 'deepseek', + + features: ['chat', 'functions', 'image', 'reasoning'], + + region: 'us', + availableRegions: ['us'], + + featured: true, + + maxTokens: 1_000_000, + maxInputTokens: 1_000_000 - 384_000, + maxOutputTokens: 384_000, + + // @note published off-peak pricing; provider peak-hour rates may be higher + pricing: { + tokenRatio: 0.0333, + inputTokenRatio: 0.0107, + outputTokenRatio: 0.0333, + inputPrice: 0.15, + outputPrice: 0.6, + }, + + interactionMaxMessages: DEFAULT_INTERACTION_MAX_MESSAGES, + + thresholdStrategy: 'truncate', + + visible: true, + deprecated: false, + + temperature: DEFAULT_TEMPERATURE, + + frequencyPenalty: 0, + presencePenalty: 0, + + tags: [], + + addedDate: '2026-09-10', + }, + 'deepseek-v4-flash': { description: `Fast, cost-efficient DeepSeek reasoning for latency-sensitive workloads that still need a massive context window and strong tool use.`, @@ -6686,6 +6784,54 @@ export const deepseekLanguageModels: Record< addedDate: '2026-04-24', }, + 'deepseek-v4.1-flash': { + description: `DeepSeek V4.1 Flash combines fast reasoning, coding, tool use, and native image understanding with a million-token context window.`, + + provider: 'deepseek', + + // @note the direct API serves v4.1 flash under the deepseek-flash identifier + // https://api-docs.deepseek.com/quick_start/pricing/ + providerModel: 'deepseek-flash', + + family: 'deepseek', + + features: ['chat', 'functions', 'image', 'reasoning'], + + region: 'us', + availableRegions: ['us'], + + featured: true, + + maxTokens: 1_000_000, + maxInputTokens: 1_000_000 - 384_000, + maxOutputTokens: 384_000, + + // @note published off-peak pricing; provider peak-hour rates may be higher + pricing: { + tokenRatio: 0.0333, + inputTokenRatio: 0.0107, + outputTokenRatio: 0.0333, + inputPrice: 0.15, + outputPrice: 0.6, + }, + + interactionMaxMessages: DEFAULT_INTERACTION_MAX_MESSAGES, + + thresholdStrategy: 'truncate', + + visible: true, + deprecated: false, + + temperature: DEFAULT_TEMPERATURE, + + frequencyPenalty: 0, + presencePenalty: 0, + + tags: [], + + addedDate: '2026-09-10', + }, + 'deepseek-v4-flash': { description: `Fast, cost-efficient DeepSeek reasoning for latency-sensitive workloads that still need a massive context window and strong tool use.`,