From 62ca24e92857a1a1042a6695b413656916011e3b Mon Sep 17 00:00:00 2001 From: Claude Date: Wed, 16 Sep 2026 15:18:05 +0000 Subject: [PATCH] chore: sync models with dashboard API - add deepseek-v4.1-flash ($0.30 in / $1.20 out, 1,048,576-token context): ZGPU_PRICING, test CATALOG, CHAT_MODELS (responses), README + DOCUMENTATION model tables, DOCUMENTATION section 1 bullet - ZGPU_FALLBACK unchanged: glm-5.2 still holds the highest input and output rate - version 3.9.0 -> 3.10.0 Source: https://api-dashboard.zerogpu.ai/api/models Co-Authored-By: Claude Opus 5 Claude-Session: https://claude.ai/code/session_01PX3a2wyDoH8pjweMjZuANg --- README.md | 1 + docs/DOCUMENTATION.md | 3 ++- package-lock.json | 4 ++-- package.json | 2 +- src/commands/chat.ts | 1 + src/lib/savings.ts | 1 + tests/savings.test.ts | 1 + 7 files changed, 9 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index d0e547c..eca8232 100644 --- a/README.md +++ b/README.md @@ -158,6 +158,7 @@ zerogpu chat "Port this helper to async/await." -m deepseek-v4-flash-0731 | `LFM2.5-1.2B-Thinking` | Compact reasoning model. | | `gpt-oss-120b` | 120B MoE, 131K context, reasoning + function calling. | | `llama-guard-4-12b` | 12B dense, 164K context, brand safety + text moderation. | +| `deepseek-v4.1-flash` | Sparse MoE (8B active on input, 16B on output), 1M context, long-context agentic work + function calling. | | `qwen3-30b-a3b-fp8` | 30B MoE, 100+ languages, reasoning + function calling. | | `glm-5.2` | 753B MoE, 262K context, reasoning + function calling. The platform's most capable model, and its priciest. | | `deepseek-v4-flash-0731` | 284B MoE (13B active), 1M context, coding and agentic workflows. | diff --git a/docs/DOCUMENTATION.md b/docs/DOCUMENTATION.md index 0145356..f529cc8 100644 --- a/docs/DOCUMENTATION.md +++ b/docs/DOCUMENTATION.md @@ -5,7 +5,7 @@ `zerogpu-cli` is the official command-line interface for [ZeroGPU](https://zerogpu.ai), a distributed / edge inference platform for small language models (SLMs) and nano language models. The CLI is a thin, OpenAI-compatible client around the ZeroGPU **Responses API** (`https://api.zerogpu.ai/v1/responses`) — and, for models served only there, the **Chat Completions API** (`https://api.zerogpu.ai/v1/chat/completions`) — that lets you call a curated set of edge-optimized models directly from your terminal for common NLP workloads: - Conversational chat (`LFM2.5-1.2B-Instruct`, `LFM2.5-1.2B-Thinking`) -- Reasoning and tool-use chat (`gpt-oss-120b`, `llama-guard-4-12b`, `qwen3-30b-a3b-fp8`, `glm-5.2`, `deepseek-v4-flash-0731`) +- Reasoning and tool-use chat (`gpt-oss-120b`, `llama-guard-4-12b`, `deepseek-v4.1-flash`, `qwen3-30b-a3b-fp8`, `glm-5.2`, `deepseek-v4-flash-0731`) - IAB content/audience classification (`zlm-v1-iab-classify-edge`, `zlm-v2-iab-classify-edge-enriched`) - Domain-level IAB classification (`zlm-v1-iab-domain-classifier`) - Zero-shot classification (`deberta-v3-small`) @@ -213,6 +213,7 @@ zerogpu chat [-i ] [-m ] [-r] | `LFM2.5-1.2B-Thinking` | Responses | Compact reasoning model. | | `gpt-oss-120b` | Responses | 120B MoE, 131K context, reasoning + function calling. | | `llama-guard-4-12b` | Responses | 12B dense, 163,840-token context, brand safety + text moderation. | +| `deepseek-v4.1-flash` | Responses | Sparse MoE (8B active on input, 16B on output), 1,048,576-token context, long-context agentic work + function calling. | | `qwen3-30b-a3b-fp8` | Chat Completions | 30B MoE, 100+ languages, reasoning + function calling. | | `glm-5.2` | Chat Completions | 753B MoE, 262,144-token context, reasoning + function calling. The most capable model on the platform, and the most expensive by an order of magnitude. | | `deepseek-v4-flash-0731` | Chat Completions | 284B MoE (13B active), 1,048,576-token context, coding and agentic workflows. | diff --git a/package-lock.json b/package-lock.json index d05ffd6..9b3c7d7 100644 --- a/package-lock.json +++ b/package-lock.json @@ -1,12 +1,12 @@ { "name": "zerogpu-cli", - "version": "3.9.0", + "version": "3.10.0", "lockfileVersion": 3, "requires": true, "packages": { "": { "name": "zerogpu-cli", - "version": "3.9.0", + "version": "3.10.0", "license": "MIT", "dependencies": { "commander": "^12.1.0", diff --git a/package.json b/package.json index 73c68c3..d40bda6 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "zerogpu-cli", - "version": "3.9.0", + "version": "3.10.0", "description": "Command-line interface for ZeroGPU.", "type": "module", "bin": { diff --git a/src/commands/chat.ts b/src/commands/chat.ts index 2322e53..fb7db56 100644 --- a/src/commands/chat.ts +++ b/src/commands/chat.ts @@ -25,6 +25,7 @@ const CHAT_MODELS: Record = { "LFM2.5-1.2B-Thinking": "responses", "gpt-oss-120b": "responses", "llama-guard-4-12b": "responses", + "deepseek-v4.1-flash": "responses", "qwen3-30b-a3b-fp8": "chat-completions", "glm-5.2": "chat-completions", "deepseek-v4-flash-0731": "chat-completions", diff --git a/src/lib/savings.ts b/src/lib/savings.ts index 9131df3..e2de728 100644 --- a/src/lib/savings.ts +++ b/src/lib/savings.ts @@ -23,6 +23,7 @@ export const ZGPU_PRICING: Record = { "gpt-oss-120b": { in: 0.15, out: 0.6 }, "qwen3-30b-a3b-fp8": { in: 0.05, out: 0.3 }, "glm-5.2": { in: 1.1, out: 3.5 }, + "deepseek-v4.1-flash": { in: 0.3, out: 1.2 }, "deepseek-v4-flash-0731": { in: 0.16, out: 0.38 }, "llama-guard-4-12b": { in: 0.18, out: 0.18 }, "llama-3.1-8b-instruct-fast": { in: 0.02, out: 0.05 }, diff --git a/tests/savings.test.ts b/tests/savings.test.ts index 9e6d792..6fb0e69 100644 --- a/tests/savings.test.ts +++ b/tests/savings.test.ts @@ -114,6 +114,7 @@ describe("ZGPU_PRICING tracks the published model catalog", () => { "gpt-oss-120b": { in: 0.15, out: 0.6 }, "qwen3-30b-a3b-fp8": { in: 0.05, out: 0.3 }, "glm-5.2": { in: 1.1, out: 3.5 }, + "deepseek-v4.1-flash": { in: 0.3, out: 1.2 }, "deepseek-v4-flash-0731": { in: 0.16, out: 0.38 }, "llama-guard-4-12b": { in: 0.18, out: 0.18 }, "llama-3.1-8b-instruct-fast": { in: 0.02, out: 0.05 },