01 /TOOLS / cohere
Cohere
situationalEnterprise-focused models — Command generation plus best-in-class Rerank.
journal entry · observed by @whysanesanders · verified 2026-08-15
Rerank is the quietly essential product — it improves any RAG pipeline regardless of your LLM. The Command chat models are solid but not the reason to come.
Known limitations
- Chat models trail frontier quality.
- Enterprise-sales motion makes self-serve feel second-class.
- Pricing pages for newer models are confusing.
Facts
- pricing
- freemium
- price note
- free trial keys; pay-as-you-go from $0.50/1M input tokens
- free tier
- yes
- open source
- no
- api
- yes
- self-host
- no
- category
- models-api
Receipts
Same sector — models-api
Anthropic API
Claude models direct — the practitioner's pick for coding and long-form text.
models-api
paid · Sonnet $3/1M input, $15/1M output; Haiku from $0.80/1M input
API
DeepSeek API
Open-weights lab with frontier-ish reasoning at disruptive prices.
models-api
paid · deepseek-chat $0.27/1M input (cache miss), $1.10/1M output
API
Google AI Studio / Gemini API
Gemini API with a real free tier — huge context, multimodal, generous limits.
models-api
freemium · free tier; Gemini 2.5 Pro from $1.25/1M input
APIFREE TIER