Data
10,000 rows pasted in whole, answered with findings rather than a formula.
Pricing verified:
Between $0.0018 and $0.480 per run, depending on the model. That is a 261× spread for the same job.
10,000 rows across ten short columns ≈ 9 tokens per row ≈ 90,000 input tokens. A written analysis with findings ≈ 900 words ≈ 1,200 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 20 analyses a month | Context |
|---|---|---|---|---|
| Mistral: Mistral Nemo | Mistral | $0.0018 | $0.037 | 131k tokens |
| OpenAI: GPT-5 Nano | OpenAI | $0.0025 | $0.050 | 400k tokens |
| Meta: Llama 3.2 1B Instructneeds chunking | Meta | $0.0027 | $0.053 | 60k tokens |
| Google: Gemma 2 9Bneeds chunking | $0.0028 | $0.056 | 8k tokens | |
| Meta: Llama 3.1 8B Instructneeds chunking | Meta | $0.0046 | $0.092 | 16k tokens |
| OpenAI: GPT-4.1 Nano | OpenAI | $0.0047 | $0.095 | 1.0M tokens |
| Mistral: Mistral Small 3.2 24B | Mistral | $0.0070 | $0.140 | 128k tokens |
| GPT-4o | OpenAI | $0.0071 | $0.142 | 128k tokens |
| Google: Gemini 2.0 Flash Lite | $0.0071 | $0.142 | 1.0M tokens | |
| OpenAI: gpt-oss-safeguard-20b | OpenAI | $0.0071 | $0.142 | 131k tokens |
| Mistral: Ministral 3 3B 2512 | Mistral | $0.0091 | $0.182 | 131k tokens |
| Llama 4 Scout | Meta | $0.0094 | $0.187 | 512k tokens |
| Mistral: Devstral Small 1.1 | Mistral | $0.0094 | $0.187 | 131k tokens |
| Mistral: Mistral Small Creativeneeds chunking | Mistral | $0.0094 | $0.187 | 33k tokens |
| Mistral: Voxtral Small 24B 2507needs chunking | Mistral | $0.0094 | $0.187 | 32k tokens |
| Google: Gemini 2.0 Flash | $0.0095 | $0.190 | 1.0M tokens | |
| Google: Gemini 2.5 Flash Lite | $0.0095 | $0.190 | 1.0M tokens | |
| Google: Gemini 2.5 Flash Lite Preview 09-2025 | $0.0095 | $0.190 | 1.0M tokens | |
| GPT-5.6 Luna | OpenAI | $0.0097 | $0.194 | 1.1M tokens |
| Mistral: Mistral 7B Instruct v0.1needs chunking | Mistral | $0.010 | $0.203 | 3k tokens |
| Gemma 4 26B A4B | $0.012 | $0.244 | 262k tokens | |
| Meta: Llama 3 8B Instructneeds chunking | Meta | $0.013 | $0.255 | 8k tokens |
| DeepSeek V4-Flash | DeepSeek | $0.013 | $0.259 | 1M tokens |
| Gemma 4 31B | $0.013 | $0.262 | 262k tokens | |
| Mistral: Ministral 3 8B 2512 | Mistral | $0.014 | $0.274 | 262k tokens |
| GPT-4o Mini | OpenAI | $0.014 | $0.284 | 128k tokens |
| Mistral: Mistral Small 4 | Mistral | $0.014 | $0.284 | 262k tokens |
| Google: Gemini 2.5 Flash | $0.015 | $0.300 | 1.0M tokens | |
| Meta: Llama Guard 4 12B | Meta | $0.016 | $0.328 | 164k tokens |
| Mistral: Ministral 3 14B 2512 | Mistral | $0.018 | $0.365 | 262k tokens |
| Mistral: Sabaneeds chunking | Mistral | $0.019 | $0.374 | 33k tokens |
| Llama 4 Maverick | Meta | $0.019 | $0.379 | 256k tokens |
| OpenAI: GPT-4.1 Mini | OpenAI | $0.019 | $0.379 | 1.0M tokens |
| xAI: Grok Code Fast 1 | xAI | $0.020 | $0.396 | 256k tokens |
| OpenAI: GPT-3.5 Turboneeds chunking | OpenAI | $0.023 | $0.468 | 16k tokens |
| Anthropic: Claude 3 Haiku | Anthropic | $0.024 | $0.480 | 200k tokens |
| Google: Gemini 3 Flash Preview | $0.024 | $0.486 | 1.0M tokens | |
| OpenAI: GPT-5 Mini | OpenAI | $0.025 | $0.498 | 400k tokens |
| OpenAI: GPT-5.1-Codex-Mini | OpenAI | $0.025 | $0.498 | 400k tokens |
| DeepSeek V3 | DeepSeek | $0.026 | $0.512 | 128k tokens |
| xAI: Grok 3 Mini | xAI | $0.028 | $0.552 | 131k tokens |
| xAI: Grok 3 Mini Beta | xAI | $0.028 | $0.552 | 131k tokens |
| Mistral: Codestral 2508 | Mistral | $0.028 | $0.562 | 256k tokens |
| Gemini 3.5 Flash-Lite | $0.030 | $0.600 | 1.0M tokens | |
| Google: Nano Banana (Gemini 2.5 Flash Image)needs chunking | $0.030 | $0.600 | 33k tokens | |
| Meta: Llama 3.2 11B Vision Instruct | Meta | $0.031 | $0.629 | 131k tokens |
| Mistral Small 3.1 | Mistral | $0.032 | $0.645 | 128k tokens |
| Mistral: Mistral Small 3needs chunking | Mistral | $0.032 | $0.645 | 33k tokens |
| Gemini 3.6 Flash | $0.036 | $0.720 | 1.0M tokens | |
| Meta: Llama 3.1 70B Instruct | Meta | $0.036 | $0.730 | 131k tokens |
| Mistral: Devstral 2 2512 | Mistral | $0.038 | $0.768 | 262k tokens |
| Mistral: Devstral Medium | Mistral | $0.038 | $0.768 | 131k tokens |
| Mistral: Mistral Medium 3 | Mistral | $0.038 | $0.768 | 131k tokens |
| Mistral: Mistral Medium 3.1 | Mistral | $0.038 | $0.768 | 131k tokens |
| DeepSeek V4-Pro | DeepSeek | $0.040 | $0.804 | 1M tokens |
| Llama Guard 3 8B | Meta | $0.043 | $0.865 | 131k tokens |
| Meta: Llama 3 70B Instructneeds chunking | Meta | $0.047 | $0.936 | 8k tokens |
| Mistral: Mistral Large 3 2512 | Mistral | $0.047 | $0.936 | 262k tokens |
| Anthropic: Claude Haiku 4.5 | Anthropic | $0.048 | $0.960 | 200k tokens |
| Gemini 3.1 Flash | $0.049 | $0.972 | 1M tokens | |
| Mistral: Mixtral 8x7B Instructneeds chunking | Mistral | $0.049 | $0.985 | 33k tokens |
| DeepSeek R1 | DeepSeek | $0.052 | $1.04 | 128k tokens |
| OpenAI: o3 Mini | OpenAI | $0.052 | $1.04 | 200k tokens |
| OpenAI: o3 Mini High | OpenAI | $0.052 | $1.04 | 200k tokens |
| OpenAI: o4 Mini | OpenAI | $0.052 | $1.04 | 200k tokens |
| OpenAI: o4 Mini High | OpenAI | $0.052 | $1.04 | 200k tokens |
| OpenAI: GPT Audio Mini | OpenAI | $0.057 | $1.14 | 128k tokens |
| Google: Gemma 2 27Bneeds chunking | $0.059 | $1.19 | 8k tokens | |
| Google: Gemini 2.5 Pro | $0.062 | $1.24 | 1.0M tokens | |
| OpenAI: GPT-5 Codex | OpenAI | $0.062 | $1.24 | 400k tokens |
| Gemini 3.5 Flash | $0.073 | $1.46 | 1.0M tokens | |
| Anthropic: Claude 3.5 Haiku | Anthropic | $0.077 | $1.54 | 200k tokens |
| Claude 4 Haiku | Anthropic | $0.077 | $1.54 | 200k tokens |
| Codestral 25.01 | Mistral | $0.084 | $1.68 | 256k tokens |
| Kimi K2.7 Code | Moonshot | $0.090 | $1.81 | 256k tokens |
| OpenAI: GPT-3.5 Turbo (older v0613)needs chunking | OpenAI | $0.092 | $1.85 | 4k tokens |
| OpenAI: GPT-4.1 | OpenAI | $0.095 | $1.90 | 1.0M tokens |
| OpenAI: o3 | OpenAI | $0.095 | $1.90 | 200k tokens |
| Claude Sonnet 5 | Anthropic | $0.096 | $1.92 | 1M tokens |
| GPT-5.6 Sol | OpenAI | $0.096 | $1.92 | 1.1M tokens |
| GPT-5.6 Terra | OpenAI | $0.097 | $1.94 | 1.1M tokens |
| OpenAI: GPT-5 | OpenAI | $0.097 | $1.94 | 400k tokens |
| GPT-5.2 Mini | OpenAI | $0.114 | $2.28 | 128k tokens |
| Muse Spark | Meta | $0.118 | $2.35 | 1.0M tokens |
| Google: Gemini 2.5 Pro Preview 05-06 | $0.124 | $2.49 | 1.0M tokens | |
| Google: Gemini 2.5 Pro Preview 06-05 | $0.124 | $2.49 | 1.0M tokens | |
| OpenAI: GPT-5 Chat | OpenAI | $0.124 | $2.49 | 128k tokens |
| OpenAI: GPT-5.1 | OpenAI | $0.124 | $2.49 | 400k tokens |
| OpenAI: GPT-5.1 Chat | OpenAI | $0.124 | $2.49 | 128k tokens |
| OpenAI: GPT-5.1-Codex | OpenAI | $0.124 | $2.49 | 400k tokens |
| OpenAI: GPT-5.1-Codex-Max | OpenAI | $0.124 | $2.49 | 400k tokens |
| GLM-5.2 | Z.ai | $0.131 | $2.63 | 1M tokens |
| OpenAI: GPT-3.5 Turbo Instructneeds chunking | OpenAI | $0.137 | $2.75 | 4k tokens |
| Anthropic: Claude Sonnet 4.5 | Anthropic | $0.144 | $2.88 | 1M tokens |
| Claude Sonnet 4.6 | Anthropic | $0.144 | $2.88 | 1M tokens |
| Mistral Medium 3.5 | Mistral | $0.144 | $2.88 | 256k tokens |
| OpenAI: GPT-5.3 Chat | OpenAI | $0.174 | $3.49 | 128k tokens |
| OpenAI: GPT-5.3-Codex | OpenAI | $0.174 | $3.49 | 400k tokens |
| Grok 4 | xAI | $0.187 | $3.74 | 2M tokens |
| Grok 4.5 | xAI | $0.187 | $3.74 | 500k tokens |
| Mistral Large 2 | Mistral | $0.187 | $3.74 | 128k tokens |
| Mistral: Mixtral 8x22B Instructneeds chunking | Mistral | $0.187 | $3.74 | 66k tokens |
| Mistral: Pixtral Large 2411 | Mistral | $0.187 | $3.74 | 131k tokens |
| Qwen 3.8 Max | Alibaba | $0.187 | $3.74 | 1M tokens |
| OpenAI: o4 Mini Deep Research | OpenAI | $0.190 | $3.79 | 200k tokens |
| Gemini 3.1 Pro | $0.194 | $3.89 | 2M tokens | |
| Google: Nano Banana Pro (Gemini 3 Pro Image Preview)needs chunking | $0.194 | $3.89 | 66k tokens | |
| OpenAI: GPT-5 Image Mini | OpenAI | $0.227 | $4.55 | 400k tokens |
| Qwen 3.7 Max | Alibaba | $0.234 | $4.68 | 1M tokens |
| OpenAI: GPT Audio | OpenAI | $0.237 | $4.74 | 128k tokens |
| Claude Opus 5 | Anthropic | $0.240 | $4.80 | 1M tokens |
| GPT-5.4 | OpenAI | $0.243 | $4.86 | 272k tokens |
| OpenAI: GPT-3.5 Turbo 16kneeds chunking | OpenAI | $0.275 | $5.50 | 16k tokens |
| Anthropic: Claude 3.7 Sonnet (thinking) | Anthropic | $0.288 | $5.76 | 200k tokens |
| Anthropic: Claude Sonnet 4 | Anthropic | $0.288 | $5.76 | 200k tokens |
| Kimi K3 | Moonshot | $0.288 | $5.76 | 1M tokens |
| xAI: Grok 3 | xAI | $0.288 | $5.76 | 131k tokens |
| xAI: Grok 3 Beta | xAI | $0.288 | $5.76 | 131k tokens |
| OpenAI: GPT-4 Turbo | OpenAI | $0.468 | $9.36 | 128k tokens |
| Anthropic: Claude Opus 4.5 | Anthropic | $0.480 | $9.60 | 200k tokens |
| Claude Fable 5 | Anthropic | $0.480 | $9.60 | 1M tokens |
| Claude Opus 4.7 | Anthropic | $0.480 | $9.60 | 1M tokens |
| Claude Opus 4.8 | Anthropic | $0.480 | $9.60 | 1M tokens |
| GPT-5.5 | OpenAI | $0.486 | $9.72 | 1M tokens |
| Anthropic: Claude 3.5 Sonnet | Anthropic | $0.576 | $11.52 | 200k tokens |
| OpenAI: o1 | OpenAI | $0.711 | $14.22 | 200k tokens |
| OpenAI: GPT-5 Pro | OpenAI | $0.747 | $14.94 | 400k tokens |
| OpenAI: GPT-5 Image | OpenAI | $0.912 | $18.24 | 400k tokens |
| OpenAI: GPT-4 Turbo (older v1106) | OpenAI | $0.936 | $18.72 | 128k tokens |
| OpenAI: GPT-4 Turbo Preview | OpenAI | $0.936 | $18.72 | 128k tokens |
| OpenAI: o3 Deep Research | OpenAI | $0.948 | $18.96 | 200k tokens |
| OpenAI: o3 Pro | OpenAI | $0.948 | $18.96 | 200k tokens |
| Claude Mythos 5 | Anthropic | $0.960 | $19.20 | 1M tokens |
| GPT-5.2 | OpenAI | $1.13 | $22.51 | 200k tokens |
| Anthropic: Claude Opus 4 | Anthropic | $1.44 | $28.80 | 200k tokens |
| Anthropic: Claude Opus 4.1 | Anthropic | $1.44 | $28.80 | 200k tokens |
| Claude Opus 4.6 | Anthropic | $1.44 | $28.80 | 1M tokens |
| OpenAI: GPT-4needs chunking | OpenAI | $2.77 | $55.44 | 8k tokens |
| OpenAI: GPT-4 (older v0314)needs chunking | OpenAI | $2.77 | $55.44 | 8k tokens |
| OpenAI: o1-pro | OpenAI | $7.11 | $142 | 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.
Sending raw rows is the expensive way to do this and it is what most people try first. If the same sheet gets queried repeatedly, having the model write code that runs over the file costs a few hundred tokens instead of ninety thousand — and it does arithmetic correctly.
$0.0018 on Mistral: Mistral Nemo, the cheapest capable option, rising to $0.480 on Claude Fable 5 at the top end. Llama 4 Scout is the value pick at $0.0094 per run. The job is priced at 90,000 input and 1,200 output tokens — see the working below.
10,000 rows across ten short columns ≈ 9 tokens per row ≈ 90,000 input tokens. A written analysis with findings ≈ 900 words ≈ 1,200 output tokens.
$0.037 a month on Mistral: Mistral Nemo, $0.187 on Llama 4 Scout, and $9.60 on Claude Fable 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.
Sending raw rows is the expensive way to do this and it is what most people try first. If the same sheet gets queried repeatedly, having the model write code that runs over the file costs a few hundred tokens instead of ninety thousand — and it does arithmetic correctly.
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.