llm-cost repositories
Trending repositories tagged llm-cost, ranked by trending score. Updated daily.
-
1
maximhq/bifrost
Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.
GitHub · Go · 9,898 stars · 1,641 forks · +98 stars in 24 hours · Trending score 3.89
-
2
localixai/tokendoctor
tokendoctor: the same Claude Code for up to 38% less. Replays your own past sessions to show what each change would have saved, then changes only what you pick
GitHub · TypeScript · 171 stars · 12 forks · +17 stars in 24 hours · Trending score 2.58
-
3
Abdoul-sudo/worklog
Claude Code mod to automatically track time, tokens and API price for each project, with a yearly activity heatmap and 8 themes to choose from.
GitHub · TypeScript · 38 stars · 2 forks · +19 stars in 24 hours · Trending score 1.53
-
4
OptimNow/cloud-finops-skills
Cloud FinOps Skill & MCP by OptimNow. FinOps Foundation aligned knowledge for AI agents: cloud cost (AWS/Azure/GCP/OCI), AI inference economics, Kubernetes, data platforms, allocation, chargeback, anomaly management, waste detection, GreenOps. Installs into 12 AI tools, or connect the hosted MCP server by URL. Content refreshed weekly.
GitHub · Python · 75 stars · 20 forks · +2 stars in 24 hours · Trending score 1.01
-
5
kalibr-ai/kalibr-sdk-python
Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.
GitHub · Python · 34 stars · 3 forks · +3 stars in 24 hours · Trending score 0.91
-
6
nickelsec/bough
Claude Code, Codex and Pi write down everything you do. bough draws it and prices it: a day, the work inside it, every prompt, and what each piece cost. One Go binary, runs on your machine, sends nothing anywhere.
GitHub · Go · 133 stars · 15 forks · 0 stars in 24 hours · Trending score 0.77
-
7
ThinkWatchProject/ThinkWatch-Lite
Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request.
GitHub · TypeScript · 946 stars · 8 forks · −30 stars in 24 hours · Trending score 0.75
-
8
Shiye-10Pages/dsh-whale-meter
🐳 鲸鱼电表:你在 DeepSeek Harness 上烧了多少 token?消耗量段位、可晒的战绩卡、6 家厂商 46 个模型精准计价(含国内分档)、8·17 调价前后对比。零配置,数据全在本机 | Token usage tiers & cost dashboard for DSH
GitHub · TypeScript · 13 stars · 1 forks · +2 stars in 24 hours · Trending score 0.73
-
9
archid21/rightsize
Make every Claude token count. rightsize picks the right model and effort for each prompt, while keeping cache and context costs low. It learns how you work and gets better over time.
GitHub · TypeScript · 48 stars · 13 forks · +3 stars in 24 hours · Trending score 0.72
-
10
dspv/caprock
Agentic development environment: run Claude Code, Codex, OpenCode and Gemini CLI side by side, and follow every PR from agent to release with its cost. Desktop app for macOS, Windows and Linux, plus a Claude Code plugin. Local, free.
GitHub · Go · 50 stars · 3 forks · 0 stars in 24 hours · Trending score 0.47
-
11
ankitvirdi4/awesome-llm-cost
Tools, libraries, papers, and patterns for reducing the cost of running large language models in production.
GitHub · 14 stars · 15 forks · 0 stars in 24 hours · Trending score 0.46
-
12
superbasedapp/observer
Track what every AI coding agent costs and see the limit coming. Per-session, per-model cost for Claude Code, Codex, Cursor and 37 more tools from your provider's own token counts, plus limit gauges, a dangerous-command guard and dashboard terminals. Free, Apache-2.0, runs on your machine.
GitHub · Go · 61 stars · 6 forks · 0 stars in 24 hours · Trending score 0.41
-
13
ilien-dev/sharur
Cut Claude Code token usage and cost with a one-line output style. Shorter replies than Concise on every Claude model: 29% fewer output tokens and 23% lower cost on Opus 5.5. Benchmarked.
GitHub · Python · 11 stars · 0 forks · +1 stars in 24 hours · Trending score 0.40
-
14
ayagmar/llm-usage-metrics
Token and cost reports for 17 AI coding agents (Claude Code, Codex, Gemini CLI, OpenCode, Copilot, pi and more), read from local session logs across all your machines
GitHub · TypeScript · 36 stars · 6 forks · 0 stars in 24 hours · Trending score 0.32
-
15
andreisirbu91-lab/MCPSpend
Real-time cost observability for Model Context Protocol (MCP) tool calls. Wraps any MCP server, attributes spend per tool/project/customer. Free tier 25K calls/mo. EU-hosted
GitHub · TypeScript · 58 stars · 3 forks · 0 stars in 24 hours · Trending score 0.14
-
16
sshnaidm/spenda
Spenda - Local usage and cost tracking for coding agents. It is a local, privacy-first tracker for AI coding agents. It monitors token usage and API costs in real time. Get granular breakdowns by project, model, and task to spot inefficiencies, optimize your budget, and keep your data completely secure.
GitHub · Python · 8 stars · 7 forks · 0 stars in 24 hours · Trending score 0.14
-
17
KushagraKanaujia/throttle
Stop renting your AI. Throttle tests your AI calls against cheaper models on your own traffic and moves the ones that pass. Open source.
GitHub · Python · 7 stars · 6 forks · 0 stars in 24 hours · Trending score 0.10
-
18
aicostbudget/ai-api-pricing-data
LLM & AI API pricing data as JSON, CSV and a free static API: input, output, cached and batch prices for OpenAI, Claude, Gemini, Grok, DeepSeek, Mistral, Qwen, Kimi and more. Every price source-linked and dated, with history. npm package + MCP server.
GitHub · PLpgSQL · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.09
-
19
Lxiayu/DshCockpit
Desktop cockpit for DeepSeek Harness (dsh): token usage & cost tracking, budget alerts, runtime auto-update with rollback, Quick Ask hotkey, scheduled tasks, session search. Win+macOS. DeepSeek Harness 桌面驾驶舱:成本/用量监控 · 自动更新 · 定时任务
GitHub · JavaScript · 40 stars · 1 forks · 0 stars in 24 hours · Trending score 0.05
-
20
aunysillyme/lean-browser-use
Cut browser use cost by about 25% in Claude Code: fresh runner subagent, bulk reads, three guards and a token meter. One npx command
GitHub · JavaScript · 6 stars · 1 forks · 0 stars in 24 hours · Trending score 0.04
-
21
Helicone/helicone
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
GitHub · TypeScript · 6,278 stars · 704 forks · 0 stars in 24 hours · Trending score 0.04
-
22
atlasmarkz/LoopPrism
See what your coding agents actually do and spend: sessions, context and cost for Claude Code, Codex, OpenCode, DeepSeek Harness, WorkBuddy. Local-first.
GitHub · Python · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.03
-
23
QuesmaOrg/awesome-ai-tokenomics
A curated list on AI token economics: what tokens cost, where they get wasted, and how to cut the bill. Tools, benchmarks, papers, and copy-paste configs for the token economy of LLMs and coding agents.
GitHub · Python · 215 stars · 44 forks · 0 stars in 24 hours · Trending score 0.02
-
24
pleasedodisturb/awesome-llm-token-optimization
A curated list of strategies, tools, papers, and resources for reducing LLM token costs and improving efficiency in production.
GitHub · Shell · 119 stars · 39 forks · 0 stars in 24 hours · Trending score 0.01