GPT-4o mini
LLM APIs, with the math.
Compare token pricing, prompt caching savings, and inference costs across foundation models.
Bring your shortlist.
Choose up to four products for a closer look. The full cost ranking stays below.
Showing 4 of 4 supported products. Find products for this comparison
Your workload
Monthly usage. Adjust the assumptions to match your product.
Uncached input prompt tokens processed by the model API.
Maximum 10,000,000,000 tokens / monthGenerated completion and reasoning tokens returned by the model API.
Maximum 2,000,000,000 tokens / monthPrompt tokens read from context cache (system prompts, docs).
Maximum 10,000,000,000 tokens / month| Decision guideOne shared workload. Different trade-offs. | |||
|---|---|---|---|
| Monthly equivalentUSD · before tax | $3.08Lowest in your shortlistGPT-4o mini | $10.43Llama 3.3 70B (Groq) | Not availableDeepSeek-R1 |
| Payment commitment | Monthly | Monthly | Monthly |
| Fits this workload? | Within modeled limits | Within modeled limits | Outside modeled limits |
| What to know | Automatic 50% prompt caching discount applies to prompts with 1,024+ identical leading tokens. | Industry-leading 250+ tokens per second inference speeds on dedicated LPU hardware. | Current DeepSeek pricing lists V4 models. This legacy R1 model and its historical token rates are not supported by the current pricing source. 1 more conditions
|
| Outside the estimate | Fine-tuning, Batch API discounts, audio/realtime APIs, and image generation. | Context prompt caching discounts, vision inputs on this model. | This pricing model is not supported. |
| Evidence | Official pricing ↗Checked 2026-10-06 | Official pricing ↗Checked 2026-10-06 | Official pricing ↗Checked 2026-10-08 |
Look ahead, before you commit.
Vary standard input tokens. Keep all other inputs fixed.
View exact values and assumptions
Each point follows your selected plan. Automatic choices use the lowest eligible supported plan per product. Missing values mean no supported plan fits. This varies one input, not all costs with customer count. Lines connect sampled estimates; prices between those points can change in steps or at plan limits.
| Standard input tokens | OpenAI API | Groq Cloud |
|---|---|---|
| 1,000,000 tokens / month | $1.73 | $5.12 |
| 1,000,001 tokens / month | $1.73 | $5.12 |
| 4,500,000 tokens / month | $2.25 | $7.19 |
| 8,000,000 tokens / month | $2.78 | $9.25 |
| 10,000,000 tokens / month | $3.08 | $10.43 |
| 11,500,000 tokens / month | $3.30 | $11.32 |
| 15,000,000 tokens / month | $3.83 | $13.38 |
| 18,500,000 tokens / month | $4.35 | $15.45 |
| 22,000,000 tokens / month | $4.88 | $17.51 |
| 25,500,000 tokens / month | $5.40 | $19.58 |
| 29,000,000 tokens / month | $5.93 | $21.64 |
| 32,500,000 tokens / month | $6.45 | $23.71 |
| 36,000,000 tokens / month | $6.98 | $25.77 |
| 39,500,000 tokens / month | $7.50 | $27.84 |
| 43,000,000 tokens / month | $8.03 | $29.90 |
| 46,500,000 tokens / month | $8.55 | $31.97 |
| 50,000,000 tokens / month | $9.07 | $34.03 |
| 53,500,000 tokens / month | $9.60 | $36.10 |
| 60,500,000 tokens / month | $10.65 | $40.23 |
| 64,000,000 tokens / month | $11.18 | $42.29 |
| 67,500,000 tokens / month | $11.70 | $44.36 |
| 71,000,000 tokens / month | $12.23 | $46.42 |
| 74,500,000 tokens / month | $12.75 | $48.49 |
| 78,000,000 tokens / month | $13.28 | $50.55 |
| 81,500,000 tokens / month | $13.80 | $52.62 |
| 85,000,000 tokens / month | $14.33 | $54.68 |
| 88,500,000 tokens / month | $14.85 | $56.75 |
| 92,000,000 tokens / month | $15.38 | $58.81 |
| 95,500,000 tokens / month | $15.90 | $60.88 |
| 99,000,000 tokens / month | $16.43 | $62.94 |
| 102,500,000 tokens / month | $16.95 | $65.01 |
| 106,000,000 tokens / month | $17.48 | $67.07 |
| 109,500,000 tokens / month | $18.00 | $69.14 |
| 113,000,000 tokens / month | $18.52 | $71.20 |
| 120,000,000 tokens / month | $19.58 | $75.33 |
Your monthly comparison
2 eligible products in this loaded set · Lowest modeled cost first
Llama 3.3 70B (Groq)
2 plans outside this workload
Claude 3.5 Haiku retired on February 19, 2026. This model is unavailable on the Claude API. Claude 3.5 Sonnet retired on October 28, 2025. This model is unavailable on the Claude API.
Current DeepSeek pricing lists V4 models. This legacy R1 model and its historical token rates are not supported by the current pricing source. Current DeepSeek pricing lists V4 models. This legacy V3 model and its historical token rates are not supported by the current pricing source.
Prices reflect dated, supported plans. Matching a category does not mean matching features. How estimates work
LLM APIs Decision Guides
Compare modeled costs, documented plan features, and limitations before choosing a provider.
Explore best picks ↗Eligible monthly estimates at a stated reference workload, with sourced charges and exclusions you can inspect.
View cost leaderboard ↗Popular LLM APIs Comparisons
Compare OpenAI API and Anthropic Claude pricing, limits, and capabilities.
Compare head-to-head ↗Compare OpenAI API and DeepSeek API pricing, limits, and capabilities.
Compare head-to-head ↗Compare OpenAI API and Groq Cloud pricing, limits, and capabilities.
Compare head-to-head ↗Compare Anthropic Claude and DeepSeek API pricing, limits, and capabilities.
Compare head-to-head ↗Compare Anthropic Claude and Groq Cloud pricing, limits, and capabilities.
Compare head-to-head ↗Compare DeepSeek API and Groq Cloud pricing, limits, and capabilities.
Compare head-to-head ↗