Blog tag

#LLM costs

What AI usage costs, how to see it and how to keep it under control.

AI and development
Anthropic's Max and Team API credits: how they change agent experiments
Claude Max and Team plans now include monthly Claude Platform credits for building agents. What they cover, what they exclude, and what finance should track.
14 October 20265 min read
AI and development
Claude Sonnet 5.5: faster mid-tier coding without a list-price rise
Sonnet 5.5 kept Sonnet 5's $2 and $10 token prices, then had its cache-read price halved. What that does to coding costs, and where Opus 5.5 still leads.
14 October 20265 min read
AI and development
Codex made GPT-6.1 Sol the default: what teams should change
Codex 0.161.0 switched its default model to GPT-6.1 Sol and made Daybreak cyber routing opt-in. What changed, what it costs, and what to pin in CI and config.
14 October 20265 min read
AI and development
Gemini 4 Argon is generally available: price, limits and the 1 December change
Gemini 4 Argon launched on 13 October 2026 at an introductory API price that doubles on 1 December. What it costs, what Google claims, and what to plan for.
14 October 20266 min read
AI and development
GPT-6.1 Sol: near-Astra coding performance at one-fifth the token price
OpenAI's GPT-6.1 Sol lists at $2/$10 per million tokens against Astra's $10/$50. What that changes for default coding models, caching and harness cost.
14 October 20264 min read
AI and development
Claude Haiku 5.5 for coding sub-agents: what the price cut changes
Anthropic's Haiku 5.5 makes high-volume subagent work cheap enough to measure. When to route there, and when Sonnet still leads.
14 October 20265 min read
AI and development
Subscription or metered: what new model pricing means for AI budgets
Muse Wonder launched with both API prices and subscription-only access. How the two pricing models differ, and what that means for controlling AI spend.
14 October 20263 min read
- #LLM costs
- #Model routing
AI and development
The harness sets the bill: why the same model costs more in some agents
New coding-agent benchmarks show one model scoring and costing very differently across agent harnesses. What that means for evaluating AI coding tools.
14 October 20263 min read
How-to
Keep AI spend in check with per-person budgets and SpanDock Mind
Turn on the SpanDock model proxy, give each person a budget, choose what happens at the limit, and see what was spent and saved.
14 October 20264 min read
AI and development
Small open-weight models as coding sub-agents: reading the Mellum2.1 release
JetBrains released Mellum2.1, a 12B open-weight model built for coding sub-agents. What it claims, what to verify, and where small models fit.
14 October 20265 min read
AI and development
Prompt caching: the AI cost control most teams don't measure
Cached input costs a tenth of the normal price on major APIs. How prompt caching works, why coding agents depend on it, and how to see whether yours hits.
14 October 20264 min read

#LLM costs

Browse by tag