Classification and routing cost drivers
Classification usually has short output but high volume, making per-request overhead and lower-cost model routing important budget variables.
Workload cost scenario
LLM Classification and Routing Cost Calculator
Compare API spend for short classification, moderation-routing, and intent-detection requests at high volume.
Platform teams routing requests before a larger model or human workflow.
Lowest tracked estimate
$38.25
GPT-OSS 20B on Groq for the current assumptions
Lowest cost does not mean best model. Test output quality, latency, retries, and reliability on your own workload.
Cost comparison
Estimated monthly cost by model
Comparing 45 models that fit the initial input length.
| Model | Provider | Input cost | Output cost | Monthly estimate | Context usage |
|---|---|---|---|---|---|
| GPT-OSS 20B on Groq | Groq | $26.25 | $12.00 | $38.25 | 0.5% |
| Gemini 1.5 Flash | $26.25 | $12.00 | $38.25 | 0.1% | |
| Gemini 2.5 Flash-Lite | $35.00 | $16.00 | $51.00 | 0.1% | |
| Llama 4 Scout on Groq | Groq | $38.50 | $13.60 | $52.10 | 0.5% |
| DeepSeek V4 Flash non-thinking | DeepSeek | $49.00 | $11.20 | $60.20 | 0.1% |
| GPT-4o mini | OpenAI | $52.50 | $24.00 | $76.50 | 0.5% |
| GPT-OSS 120B on Groq | Groq | $52.50 | $24.00 | $76.50 | 0.5% |
| Command R 08-2024 | Cohere | $52.50 | $24.00 | $76.50 | 0.5% |
| GPT-5.6 Luna | OpenAI | $70.00 | $48.00 | $118.00 | 0.1% |
| gpt-5.4-nano | OpenAI | $70.00 | $50.00 | $120.00 | 0.2% |
| Qwen3-32B on Groq | Groq | $101.50 | $23.60 | $125.10 | 0.5% |
| Gemini 3.5 Live Translate Preview | $87.50 | $60.00 | $147.50 | 0.5% | |
| Gemini 3.1 Flash-Lite | $87.50 | $60.00 | $147.50 | 0.1% | |
| DeepSeek V4 Pro | DeepSeek | $152.25 | $34.80 | $187.05 | 0.1% |
| Gemini 2.5 Flash | $105.00 | $100.00 | $205.00 | 0.1% | |
| Gemini 3.5 Flash-Lite | $105.00 | $100.00 | $205.00 | 0.1% | |
| Gemini 3 Flash Preview | $175.00 | $120.00 | $295.00 | 0.1% | |
| Gemini 3.6 Flash | $262.50 | $150.00 | $412.50 | 0.1% | |
| Gemini 3.7 Flash | $262.50 | $150.00 | $412.50 | 0.1% | |
| Gemini 3.8 Flash | $262.50 | $150.00 | $412.50 | 0.1% | |
| gpt-5.4-mini | OpenAI | $262.50 | $180.00 | $442.50 | 0.2% |
| Kimi K2.7 Code | Moonshot AI | $332.50 | $160.00 | $492.50 | 0.3% |
| Kimi K2.6 | Moonshot AI | $332.50 | $160.00 | $492.50 | 0.3% |
| Claude Haiku 4.5 | Anthropic | $350.00 | $200.00 | $550.00 | 0.4% |
| Gemini 1.5 Pro | $437.50 | $200.00 | $637.50 | 0.0% | |
| Mistral Medium 3.5 | Mistral | $525.00 | $300.00 | $825.00 | 0.3% |
| Gemini 2.5 Pro | $437.50 | $400.00 | $837.50 | 0.1% | |
| Gemini 3.5 Flash | $525.00 | $360.00 | $885.00 | 0.1% | |
| Grok 4.5 | xAI | $700.00 | $240.00 | $940.00 | 0.1% |
| Kimi K2.7 Code High-Speed | Moonshot AI | $665.00 | $320.00 | $985.00 | 0.3% |
| Claude Sonnet 5 | Anthropic | $700.00 | $400.00 | $1,100.00 | 0.1% |
| GPT-5.6 Terra | OpenAI | $700.00 | $480.00 | $1,180.00 | 0.1% |
| Gemini 3.1 Pro Preview | $700.00 | $480.00 | $1,180.00 | 0.1% | |
| GPT-4o | OpenAI | $875.00 | $400.00 | $1,275.00 | 0.5% |
| Command R+ 08-2024 | Cohere | $875.00 | $400.00 | $1,275.00 | 0.5% |
| Command A | Cohere | $875.00 | $400.00 | $1,275.00 | 0.3% |
| Claude Sonnet 4.6 | Anthropic | $1,050.00 | $600.00 | $1,650.00 | 0.1% |
| Kimi K3 | Moonshot AI | $1,050.00 | $600.00 | $1,650.00 | 0.1% |
| GPT-5.6 Sol | OpenAI | $1,400.00 | $800.00 | $2,200.00 | 0.1% |
| Claude Opus 4.8 | Anthropic | $1,750.00 | $1,000.00 | $2,750.00 | 0.1% |
| Claude Opus 5 | Anthropic | $1,750.00 | $1,000.00 | $2,750.00 | 0.1% |
| Claude Fable 5 | Anthropic | $3,500.00 | $2,000.00 | $5,500.00 | 0.1% |
| Claude Mythos 5 | Anthropic | $3,500.00 | $2,000.00 | $5,500.00 | 0.1% |
| GPT-6 Astra | OpenAI | $3,500.00 | $2,000.00 | $5,500.00 | 0.1% |
| GPT-5.6 Cyber | OpenAI | $4,375.00 | $3,000.00 | $7,375.00 | 0.2% |
What to measure
- Use a compact response schema.
- Measure fallback rates to larger models.
- Test whether deterministic rules can handle obvious cases before an LLM call.
Estimate boundary: Quality and latency are not assumed equal across models; validate labels on a representative evaluation set.
View pricing sources
How StackLens verifies data and calculates cost
OpenAI model pricingHigh confidenceChecked 2026-09-08
Tracked prices for included OpenAI models are checked against official provider documentation.
Anthropic model pricingHigh confidenceChecked 2026-09-08
Tracked prices for included Anthropic models are checked against official provider documentation.
Google model pricingHigh confidenceChecked 2026-09-03
Tracked prices for included Google models are checked against official provider documentation.
DeepSeek model pricingHigh confidenceChecked 2026-08-16
Tracked prices for included DeepSeek models are checked against official provider documentation.
Groq model pricingHigh confidenceChecked 2026-07-15
Tracked prices for included Groq models are checked against official provider documentation.
Groq model pricingHigh confidenceChecked 2026-07-15
Tracked prices for included Groq models are checked against official provider documentation.
Groq model pricingHigh confidenceChecked 2026-07-15
Tracked prices for included Groq models are checked against official provider documentation.
Groq model pricingHigh confidenceChecked 2026-07-15
Tracked prices for included Groq models are checked against official provider documentation.
Google model pricingHigh confidenceChecked 2026-07-17
Tracked prices for included Google models are checked against official provider documentation.
Google model pricingHigh confidenceChecked 2026-07-17
Tracked prices for included Google models are checked against official provider documentation.
Cohere model pricingHigh confidenceChecked 2026-07-17
Tracked prices for included Cohere models are checked against official provider documentation.
Cohere model pricingHigh confidenceChecked 2026-07-17
Tracked prices for included Cohere models are checked against official provider documentation.
Cohere model pricingHigh confidenceChecked 2026-07-17
Tracked prices for included Cohere models are checked against official provider documentation.
Mistral model pricingHigh confidenceChecked 2026-07-17
Tracked prices for included Mistral models are checked against official provider documentation.
Moonshot AI model pricingHigh confidenceChecked 2026-07-17
Tracked prices for included Moonshot AI models are checked against official provider documentation.
Moonshot AI model pricingHigh confidenceChecked 2026-07-17
Tracked prices for included Moonshot AI models are checked against official provider documentation.
Moonshot AI model pricingHigh confidenceChecked 2026-07-17
Tracked prices for included Moonshot AI models are checked against official provider documentation.
xAI model pricingHigh confidenceChecked 2026-07-17
Tracked prices for included xAI models are checked against official provider documentation.
Anthropic model pricingHigh confidenceChecked 2026-09-08
Tracked prices for included Anthropic models are checked against official provider documentation.
Provider pricing used in this comparison
Review the source-tracked provider pages before using this workload estimate in a budget.