WWhichAITry via Vercel AI Gateway

Best AI models for chat

Chat prioritizes latency, personality, and cost per million tokens — not benchmark max scores.

The podium

Top 3 picks

🥇Anthropic
Claude Haiku 4.5

Fast, cheap, surprisingly smart.

speed
10.0
writing
8.0
value
10.0
200K context$1.00 / $5.00
🥈Google
Gemini 3 Flash

Cheap, fast, 2M-token context.

speed
10.0
writing
7.0
value
10.0
2M context$0.30 / $1.20
🥉Google
Gemini Nano 2

On-device first. Free inference, private by default.

speed
10.0
writing
6.0
value
10.0
32K contextFree / Free
Full ranking

Runners-up

#ModelContextPrice /M
4GPT-5 Mini OpenAI200K$0.40 / $1.60View →
5Mistral Small 3 Mistral128K$0.20 / $0.60View →
6GPT-OSS 20B OpenAI128K$0.15 / $0.60View →
7Claude Sonnet 4.6 Anthropic1M$3.00 / $15.00View →
8Qwen 3 Coder Alibaba128K$0.50 / $1.50View →
Keep learning

Related guides