Claude Fable Price: Fable 5.1 at $10/$50 per 1M Tokens
Claude Fable price as of Sept 4, 2026: Fable 5.1 bills $10/$50 per 1M tokens at Anthropic, $9/$45 on Modellix (10% OFF); cache reads cost $0.225 per million.
Modellix
LLM API | Tags | Modellix | Page 2
LLM API — Find Modellix Blog articles by topic and tag. Page 2.
LLM API
Claude API Pricing (2026): Opus 5, Sonnet 5, Haiku 4.5 Costs
Claude API pricing as of Sept 3, 2026: per-million-token rates for Opus 5, Sonnet 5, and Haiku 4.5, plus flat-rate billing, cache pricing, and context windows.
LLM API Pricing Comparison: 28 Models at 1M-Token Rates
28 text models compared on per-million-token API costs as of Sep 3, 2026: input, output, cache rates, Input Context tiers, and what one agent run bills.
Anthropic Base URL: Claude Code and Harness, No /v1
Set ANTHROPIC_BASE_URL to https://llm.modellix.ai, never /v1: Claude Code settings.json and the harness anthropic-messages provider, plus the 401 auth traps.
OpenAI Compatible API: What 'openai-completions' Means
What 'openai-completions' means: an OpenAI compatible API is a protocol contract, not a switch. Changing only the URL breaks; the cheat sheet shows why.
Claude Fable 5.1 vs Opus 5: Run Cost, Not Benchmarks
Fable 5.1 output is ~2x Opus 5 ($45 vs $22.50/1M, Sep 4, 2026); cache reads are half. Cheaper depends on workload shape; decide by scenario, verify on bills.
Gemini 3.8 Flash Pricing: $0.75 Rate Ends January 1, 2027
Gemini 3.8 Flash API pricing, captured Sept 4, 2026: Google's $0.75/$3.75 per-1M-token rates expire Dec 31, 2026 and double to $1.50/$7.50 on January 1, 2027.
MiniMax 2.5 API: Integration Guide, Pricing & Code
MiniMax 2.5 API guide: legacy status, current per-million pricing, both base URLs, working curl and SDK code, error handling, and M2.5 vs M2.7 vs M3 guidance.