Support chat is input-heavy: long help-center context plus short answers. Prompt caching and low input pricing dominate the monthly bill.
| # | Model | Provider | Input / 1M | Output / 1M | Context | Score | Profile |
|---|---|---|---|---|---|---|---|
| 1 | Claude Haiku 5.5 | Anthropic | $0.100 | $0.500 | 1.0M | 0.82 | View |
| 2 | Gemini 3.5 Flash-Lite | $0.300 | $2.500 | 1.0M | 0.81 | View | |
| 3 | DeepSeek Flash | DeepSeek | $0.150 | $0.600 | 1.0M | 0.76 | View |
| 4 | GPT-6 Luna | OpenAI | $0.100 | $0.500 | 1.1M | 0.72 | View |
| 5 | Claude Sonnet 5.5 | Anthropic | $2.000 | $10.000 | 1.0M | 0.72 | View |
| 6 | Gemini 3.8 Flash | $0.750 | $3.750 | 1.0M | 0.70 | View | |
| 7 | Grok 4.3 | xAI | $1.250 | $2.500 | 1.0M | 0.69 | View |
| 8 | Gemini 3.1 Pro (Preview) | $2.000 | $12.000 | 1.0M | 0.69 | View | |
| 9 | GPT-6.1 Sol | OpenAI | $2.000 | $10.000 | 1.1M | 0.67 | View |
| 10 | GPT-5.4 Mini | OpenAI | $0.750 | $4.500 | 400k | 0.67 | View |
| 11 | DeepSeek V4 Pro | DeepSeek | $0.660 | $1.980 | 1.0M | 0.66 | View |
| 12 | Claude Opus 5.5 | Anthropic | $4.000 | $20.000 | 1.0M | 0.62 | View |
| 13 | Gemini 4 Argon | $4.000 | $20.000 | 1.0M | 0.57 | View | |
| 14 | GPT-5.5 | OpenAI | $5.000 | $30.000 | 922k | 0.52 | View |
| 15 | Grok 4.7 | xAI | $2.000 | $6.000 | 500k | 0.52 | View |
Composite score = 0.4×cost + 0.2×context + 0.2×intelligence + 0.2×speed, where each factor is normalized 0–1 across the active catalog. Cost is inverted (lower price = higher score). Weights reflect the priorities of this use case. Scores are a starting point — always test on your own workload.
DeepSeek Flash and Gemini 3.5 Flash-Lite lead on input price. Test answer quality on your transcripts first.
Yes — support bots resend the same system prompt and context, so caching can cut input cost substantially.