Support
The ticket, the customer's history and retrieved help-centre articles in; a drafted reply out.
Pricing verified:
Between $0.0001 and $0.011 per run, depending on the model. That is a 77× spread for the same job.
The ticket, prior thread history and three retrieved help-centre articles ≈ 2,600 words ≈ 3,500 input tokens. A 260-word reply ≈ 350 output tokens.
Cost = (input tokens ÷ 1M × input price) + (output tokens ÷ 1M × output price). Prices come from our daily-verified model data. Batch and cached-input discounts are not applied — they only ever make these numbers smaller.
| Model | Provider | Per run | At 5,000 tickets a month | Context |
|---|---|---|---|---|
| Gemma 2 9B | $0.0001 | $0.683 | 8k tokens | |
| Llama 3.2 1B Instruct | Meta | $0.0002 | $0.822 | 60k tokens |
| Llama 3.1 8B Instruct | Meta | $0.0002 | $1.01 | 16k tokens |
| GPT-5 Nano | OpenAI | $0.0003 | $1.58 | 400k tokens |
| gpt-oss-safeguard-20b | OpenAI | $0.0003 | $1.58 | 131k tokens |
| Mistral Small 3.2 24B | Mistral | $0.0003 | $1.66 | 128k tokens |
| Gemini 2.0 Flash Lite | $0.0004 | $1.84 | 1.0M tokens | |
| Ministral 3 3B 2512 | Mistral | $0.0004 | $1.92 | 131k tokens |
| Mistral 7B Instruct v0.1needs chunking | Mistral | $0.0005 | $2.26 | 3k tokens |
| Devstral Small 1.1 | Mistral | $0.0005 | $2.27 | 131k tokens |
| Mistral Small Creative | Mistral | $0.0005 | $2.27 | 33k tokens |
| Voxtral Small 24B 2507 | Mistral | $0.0005 | $2.27 | 32k tokens |
| Mistral Small 3.1 | Mistral | $0.0005 | $2.28 | 128k tokens |
| Gemini 2.0 Flash | $0.0005 | $2.45 | 1.0M tokens | |
| Gemini 2.5 Flash Lite | $0.0005 | $2.45 | 1.0M tokens | |
| Gemini 2.5 Flash Lite Preview 09-2025 | $0.0005 | $2.45 | 1.0M tokens | |
| GPT-4.1 Nano | OpenAI | $0.0005 | $2.45 | 1.0M tokens |
| Llama 3 8B Instruct | Meta | $0.0005 | $2.70 | 8k tokens |
| Ministral 3 8B 2512 | Mistral | $0.0006 | $2.89 | 262k tokens |
| Mistral Nemo | Mistral | $0.0006 | $2.89 | 131k tokens |
| DeepSeek V4-Flash | DeepSeek | $0.0006 | $2.94 | 1M tokens |
| Gemma 4 26B A4B | $0.0006 | $2.98 | 262k tokens | |
| Llama Guard 4 12B | Meta | $0.0007 | $3.47 | 164k tokens |
| GLM-5.3 Flash | Z.ai | $0.0007 | $3.50 | 1M tokens |
| Qwen 3.8 Flash | Alibaba | $0.0007 | $3.62 | 991k tokens |
| GPT-4o Mini | OpenAI | $0.0007 | $3.67 | 128k tokens |
| Mistral Small 4 | Mistral | $0.0007 | $3.67 | 262k tokens |
| Ministral 3 14B 2512 | Mistral | $0.0008 | $3.85 | 262k tokens |
| Saba | Mistral | $0.0009 | $4.55 | 33k tokens |
| GPT-5.6 Luna | OpenAI | $0.0011 | $5.60 | 1.1M tokens |
| Grok 3 Mini | xAI | $0.0012 | $6.13 | 131k tokens |
| Grok 3 Mini Beta | xAI | $0.0012 | $6.13 | 131k tokens |
| Grok Code Fast 1 | xAI | $0.0012 | $6.13 | 256k tokens |
| Claude 3 Haiku | Anthropic | $0.0013 | $6.56 | 200k tokens |
| Llama 3.2 11B Vision Instruct | Meta | $0.0013 | $6.64 | 131k tokens |
| DeepSeek V3 | DeepSeek | $0.0013 | $6.65 | 128k tokens |
| Codestral 2508 | Mistral | $0.0014 | $6.82 | 256k tokens |
| Gemini 3 Flash Preview | $0.0014 | $7.00 | 1.0M tokens | |
| Mistral Small 3 | Mistral | $0.0014 | $7.11 | 33k tokens |
| Llama 3.1 70B Instruct | Meta | $0.0015 | $7.70 | 131k tokens |
| GPT-5 Mini | OpenAI | $0.0016 | $7.88 | 400k tokens |
| GPT-5.1-Codex-Mini | OpenAI | $0.0016 | $7.88 | 400k tokens |
| Llama Guard 3 8B | Meta | $0.0017 | $8.45 | 131k tokens |
| Gemma 4 31B | $0.0017 | $8.52 | 262k tokens | |
| Muse Glimmer 30B | Meta | $0.0017 | $8.75 | 131k tokens |
| DeepSeek V4-Pro | DeepSeek | $0.0018 | $9.13 | 1M tokens |
| Gemini 2.5 Flash | $0.0019 | $9.63 | 1.0M tokens | |
| Gemini 3.5 Flash-Lite | $0.0019 | $9.63 | 1.0M tokens | |
| Nano Banana (Gemini 2.5 Flash Image) | $0.0019 | $9.63 | 33k tokens | |
| GPT-4.1 Mini | OpenAI | $0.0020 | $9.80 | 1.0M tokens |
| Llama 3 70B Instruct | Meta | $0.0020 | $10.22 | 8k tokens |
| Mixtral 8x7B Instruct | Mistral | $0.0021 | $10.40 | 33k tokens |
| Devstral 2 2512 | Mistral | $0.0021 | $10.50 | 262k tokens |
| Devstral Medium | Mistral | $0.0021 | $10.50 | 131k tokens |
| Mistral Medium 3 | Mistral | $0.0021 | $10.50 | 131k tokens |
| Mistral Medium 3.1 | Mistral | $0.0021 | $10.50 | 131k tokens |
| Llama 4 Scout | Meta | $0.0022 | $10.85 | 512k tokens |
| GPT-3.5 Turbo | OpenAI | $0.0023 | $11.38 | 16k tokens |
| Mistral Large 3 2512 | Mistral | $0.0023 | $11.38 | 262k tokens |
| Gemma 2 27B | $0.0025 | $12.51 | 8k tokens | |
| Llama 4 Maverick | Meta | $0.0027 | $13.30 | 256k tokens |
| DeepSeek R1 | DeepSeek | $0.0027 | $13.46 | 128k tokens |
| Gemini 3.1 Flash | $0.0028 | $14.00 | 1M tokens | |
| GPT Audio Mini | OpenAI | $0.0029 | $14.70 | 128k tokens |
| Gemini 3.6 Flash | $0.0039 | $19.69 | 1.0M tokens | |
| Gemini 3.7 Flash | $0.0039 | $19.69 | 1.0M tokens | |
| Codestral 25.01 | Mistral | $0.0041 | $20.47 | 256k tokens |
| Claude 3.5 Haiku | Anthropic | $0.0042 | $21.00 | 200k tokens |
| GPT-3.5 Turbo (older v0613) | OpenAI | $0.0042 | $21.00 | 4k tokens |
| Claude 4 Haiku | Anthropic | $0.0042 | $21.00 | 200k tokens |
| Kimi K2.7 Code | Moonshot | $0.0047 | $23.63 | 256k tokens |
| Claude Haiku 4.5 | Anthropic | $0.0053 | $26.25 | 200k tokens |
| o3 Mini | OpenAI | $0.0054 | $26.95 | 200k tokens |
| o3 Mini High | OpenAI | $0.0054 | $26.95 | 200k tokens |
| o4 Mini | OpenAI | $0.0054 | $26.95 | 200k tokens |
| o4 Mini High | OpenAI | $0.0054 | $26.95 | 200k tokens |
| Muse Spark | Meta | $0.0059 | $29.31 | 1.0M tokens |
| GPT-5.2 Mini | OpenAI | $0.0059 | $29.40 | 128k tokens |
| GPT-3.5 Turbo Instruct | OpenAI | $0.0060 | $29.75 | 4k tokens |
| GLM-5.2 | Z.ai | $0.0064 | $32.20 | 1M tokens |
| GLM-5.3 | Z.ai | $0.0064 | $32.20 | 1M tokens |
| GPT-5 | OpenAI | $0.0079 | $39.38 | 400k tokens |
| GPT-5 Chat | OpenAI | $0.0079 | $39.38 | 128k tokens |
| GPT-5 Codex | OpenAI | $0.0079 | $39.38 | 400k tokens |
| GPT-5.1 | OpenAI | $0.0079 | $39.38 | 400k tokens |
| GPT-5.1 Chat | OpenAI | $0.0079 | $39.38 | 128k tokens |
| GPT-5.1-Codex | OpenAI | $0.0079 | $39.38 | 400k tokens |
| GPT-5.1-Codex-Max | OpenAI | $0.0079 | $39.38 | 400k tokens |
| Gemini 2.5 Pro | $0.0079 | $39.38 | 1.0M tokens | |
| Gemini 2.5 Pro Preview 05-06 | $0.0079 | $39.38 | 1.0M tokens | |
| Gemini 2.5 Pro Preview 06-05 | $0.0079 | $39.38 | 1.0M tokens | |
| Mistral Medium 3.5 | Mistral | $0.0079 | $39.38 | 256k tokens |
| Gemini 3.5 Flash | $0.0084 | $42.00 | 1.0M tokens | |
| Grok 4 | xAI | $0.0091 | $45.50 | 2M tokens |
| Grok 4.5 | xAI | $0.0091 | $45.50 | 500k tokens |
| Grok 4.6 | xAI | $0.0091 | $45.50 | 500k tokens |
| Mixtral 8x22B Instruct | Mistral | $0.0091 | $45.50 | 66k tokens |
| Pixtral Large 2411 | Mistral | $0.0091 | $45.50 | 131k tokens |
| Qwen 3.8 Max | Alibaba | $0.0091 | $45.50 | 1M tokens |
| GPT-5 Image Mini | OpenAI | $0.0095 | $47.25 | 400k tokens |
| GPT-4.1 | OpenAI | $0.0098 | $49.00 | 1.0M tokens |
| o3 | OpenAI | $0.0098 | $49.00 | 200k tokens |
| o4 Mini Deep Research | OpenAI | $0.0098 | $49.00 | 200k tokens |
| Claude Sonnet 5 | Anthropic | $0.011 | $52.50 | 1M tokens |
| GPT-5.6 Sol | OpenAI | $0.011 | $52.50 | 1.1M tokens |
| GPT-5.2 | OpenAI | $0.011 | $55.13 | 200k tokens |
| GPT-5.3 Chat | OpenAI | $0.011 | $55.13 | 128k tokens |
| GPT-5.3-Codex | OpenAI | $0.011 | $55.13 | 400k tokens |
| GPT-5.6 Terra | OpenAI | $0.011 | $56.00 | 1.1M tokens |
| Gemini 3.1 Pro | $0.011 | $56.00 | 2M tokens | |
| Nano Banana Pro (Gemini 3 Pro Image Preview) | $0.011 | $56.00 | 66k tokens | |
| Qwen 3.7 Max | Alibaba | $0.011 | $56.88 | 1M tokens |
| GPT-3.5 Turbo 16k | OpenAI | $0.012 | $59.50 | 16k tokens |
| GPT Audio | OpenAI | $0.012 | $61.25 | 128k tokens |
| GPT-4o | OpenAI | $0.012 | $61.25 | 128k tokens |
| Mistral Large 2 | Mistral | $0.014 | $68.25 | 128k tokens |
| GPT-5.4 | OpenAI | $0.014 | $70.00 | 272k tokens |
| Claude 3.7 Sonnet (thinking) | Anthropic | $0.016 | $78.75 | 200k tokens |
| Claude Sonnet 4 | Anthropic | $0.016 | $78.75 | 200k tokens |
| Claude Sonnet 4.5 | Anthropic | $0.016 | $78.75 | 1M tokens |
| Claude Sonnet 4.6 | Anthropic | $0.016 | $78.75 | 1M tokens |
| Grok 3 | xAI | $0.016 | $78.75 | 131k tokens |
| Grok 3 Beta | xAI | $0.016 | $78.75 | 131k tokens |
| Kimi K3 | Moonshot | $0.016 | $78.75 | 1M tokens |
| Claude Opus 4.5 | Anthropic | $0.026 | $131 | 200k tokens |
| Claude Opus 4.6 | Anthropic | $0.026 | $131 | 1M tokens |
| Claude Opus 4.7 | Anthropic | $0.026 | $131 | 1M tokens |
| Claude Opus 4.8 | Anthropic | $0.026 | $131 | 1M tokens |
| Claude Opus 5 | Anthropic | $0.026 | $131 | 1M tokens |
| GPT-5.5 | OpenAI | $0.028 | $140 | 1M tokens |
| Claude 3.5 Sonnet | Anthropic | $0.032 | $158 | 200k tokens |
| GPT-5 Image | OpenAI | $0.039 | $193 | 400k tokens |
| GPT-4 Turbo | OpenAI | $0.046 | $228 | 128k tokens |
| GPT-4 Turbo (older v1106) | OpenAI | $0.046 | $228 | 128k tokens |
| GPT-4 Turbo Preview | OpenAI | $0.046 | $228 | 128k tokens |
| o3 Deep Research | OpenAI | $0.049 | $245 | 200k tokens |
| Claude Fable 5 | Anthropic | $0.053 | $263 | 1M tokens |
| Claude Fable 5.1 | Anthropic | $0.053 | $263 | 1M tokens |
| Claude Mythos 5 | Anthropic | $0.053 | $263 | 1M tokens |
| Claude Mythos 5.1 | Anthropic | $0.053 | $263 | 1M tokens |
| GPT-6 Astra | OpenAI | $0.053 | $263 | 1.1M tokens |
| o1 | OpenAI | $0.073 | $368 | 200k tokens |
| Claude Opus 4 | Anthropic | $0.079 | $394 | 200k tokens |
| Claude Opus 4.1 | Anthropic | $0.079 | $394 | 200k tokens |
| GPT-5 Pro | OpenAI | $0.095 | $473 | 400k tokens |
| o3 Pro | OpenAI | $0.098 | $490 | 200k tokens |
| GPT-4 | OpenAI | $0.126 | $630 | 8k tokens |
| GPT-4 (older v0314) | OpenAI | $0.126 | $630 | 8k tokens |
| o1-pro | OpenAI | $0.735 | $3,675 | 200k tokens |
“Needs chunking” means the model's context window can't hold this job in a single pass, so the real cost is higher than the figure shown and quality usually suffers.
At 5,000 tickets the gap between the cheapest and the most expensive model is real money, which makes this the classic case for routing: a budget model drafts, and tickets it flags as uncertain escalate to a premium model or a human.
$0.0001 on Gemma 2 9B, the cheapest capable option, rising to $0.011 on Claude Sonnet 5 at the top end. GPT-5.6 Luna is the value pick at $0.0011 per run. The job is priced at 3,500 input and 350 output tokens — see the working below.
The ticket, prior thread history and three retrieved help-centre articles ≈ 2,600 words ≈ 3,500 input tokens. A 260-word reply ≈ 350 output tokens.
$0.683 a month on Gemma 2 9B, $5.60 on GPT-5.6 Luna, and $52.50 on Claude Sonnet 5. Batch APIs typically halve these figures for work that can wait, and prompt caching cuts the input side further when the same context is reused.
At 5,000 tickets the gap between the cheapest and the most expensive model is real money, which makes this the classic case for routing: a budget model drafts, and tickets it flags as uncertain escalate to a premium model or a human.
Yes. Every figure on this page is computed from our model pricing data, which is checked daily against each provider's official pricing page. When a provider changes a price, these numbers change with it.
Newsletter
Pricing changes, new model releases, and updated recommendations — delivered when it matters.
No spam. Useful updates only. Affiliate disclosures always clearly labeled.