Rate
DeepSeek guides
- PricingUpdated Nov 9, 2026
Batch API: when half price is worth the wait
What the Batch API saves on Claude, GPT-6, Gemini, Grok and Mistral for 100,000 summaries, from official prices, plus DeepSeek's off-peak.
- PricingUpdated Nov 5, 2026
What 1,000 AI API requests cost on 19 models (October 2026)
Dollar cost of 1,000 chat, coding-agent and summary requests on Claude, GPT-6, Gemini, Grok, DeepSeek and Mistral, from official list prices.
- BasicsUpdated Nov 5, 2026
What a context window is, and when you actually need 1M tokens
What counts toward an AI model's context window, how big it is on Claude, GPT-6, Gemini, Grok, DeepSeek and Mistral, and what a 1M-token request costs.
- PricingUpdated Nov 5, 2026
Prompt caching in practice: what it saves on Claude, GPT-6, Gemini and DeepSeek
How much prompt caching cuts your AI API bill, worked out from official prices for 14 models: cache read discounts, agent and document examples, write costs.
- Language modelsUpdated Nov 2, 2026
Claude Haiku 5.5 explained: price, the 100K-token cliff, and when to use it
Claude Haiku 5.5 costs $0.10 / $0.50 per million tokens up to 100K-token prompts, then 5x more. Costs vs Haiku 4.5, GPT-6 Luna and Gemini, worked out.
- Language modelsUpdated Nov 2, 2026
DeepSeek V4 Pro and V4.1 Flash explained: peak vs off-peak pricing
DeepSeek's two API models, their peak and off-peak prices, when the cheap hours are, and what 1,000 requests cost against Claude, GPT-6, Gemini and Grok.
- Language modelsUpdated Nov 2, 2026
GPT-6.1 Terra explained: price, context and where it fits
GPT-6.1 Terra costs $1 / $5 per million tokens with $0.05 cache reads and a 1.05M context. What it costs vs GPT-6.1 Sol, Claude, Gemini and DeepSeek.
- Language modelsUpdated Nov 2, 2026
Grok 4.7 explained: price, 500K context and where it fits
Grok 4.7 costs $2 / $6 per million tokens with $0.50 cache reads and a 500K context. Costs vs Claude, GPT-6.1 Sol and Gemini, worked out from list prices.
- PricingUpdated Sep 28, 2026
AI API pricing explained: tokens, input vs output, caching and batch
How AI API pricing works, with dollar examples: tokens, why output costs more, caching and batch discounts, and DeepSeek's peak hours.
