Topic collection
Language Model APIs
Model reviews and comparisons covering context, tool use, coding workflows, pricing, and API access.
The language-model guides compare APIs by the work they need to perform, including structured output, tool use, coding, long-context processing, latency, and price. They avoid treating a single benchmark as a universal ranking. Use the articles to understand tradeoffs and the linked model pages to inspect current capabilities before selecting a model for an application or agent workflow.
11 articles
Articles about language models
Gemini API Pricing: Argon, Flash and TTS per 1M Tokens (2026)
Gemini API pricing per 1M tokens for Gemini 4 Argon and 3.8 Flash, Gemini TTS per second, Google's upcoming price changes, and what real requests cost.
OpenAI API Pricing: GPT 6 Astra, Sol, Luna per 1M Tokens (2026)
OpenAI API pricing per 1M tokens for GPT 6 Astra, Sol, Luna and GPT 5: input, output, cache and long-context rates, real request costs, and which to pick.
Claude API Pricing: Opus, Sonnet, Haiku per 1M Tokens (2026)
Claude API pricing per 1M tokens for Opus, Sonnet, Haiku and Fable: input, output and cache rates, real request costs, and the cheapest way to call Claude.
DeepSeek API Pricing & Cost: V4 Pro and V4 Flash (2026)
DeepSeek API pricing and cost per 1M tokens for V4 Pro and V4 Flash: peak and off-peak rates, cache-hit pricing, the August 2026 price rise, and API access.
Gemini 3.7 Flash API Pricing & Cost per 1M Tokens (2026)
Gemini 3.7 Flash API pricing and cost per 1M tokens, the launch rate through December 31, 2026, benchmarks against 3.6 Flash, and how to call it.
GPT-5.6 Sol Ultrafast API: 750 Tokens/sec on Cerebras (2026)
OpenAI's Ultrafast mode runs GPT-5.6 Sol at up to 750 output tokens per second on Cerebras hardware. How it works, who gets it, and what to call today.
Grok 4.6 API Pricing & Cost per 1M Tokens, Benchmarks (2026)
Grok 4.6 API pricing and cost per 1M tokens, plus the numbers behind it: 95.6% SWE-bench Verified, first on CursorBench 3.2, 500k context, and API access.
Qwen3.8 27B: Benchmarks, Specs, and How to Run It (2026)
Qwen3.8 27B is a 27B open-weight VL model under Apache 2.0: 61.7% SWE-bench Pro, 262K context, image and video input. Benchmarks, VRAM math, how to run it.
Claude Fable 5 vs Kimi K3: API Pricing and Benchmarks (2026)
Kimi K3 costs roughly a third of Claude Fable 5 per token, but Fable 5 leads Arena 1513 to 1494 and HLE 53.3 to 43.5. API pricing, benchmarks, and code.
GPT 5.6 Sol vs Kimi K3: API Pricing and Benchmarks (2026)
GPT 5.6 Sol costs less per token than Kimi K3 and scores 80 on the Coding Agent Index. API pricing, benchmarks, speed, and code to call both.
Kimi K3 API Pricing & Cost per 1M Tokens, Benchmarks (2026)
Kimi K3 API pricing and cost per 1M input and output tokens, what a long agent run costs, how K3 benchmarks against Claude and GPT, and how to call it.