One dimension is not a complete decision
Cost, token volume, capacity, and evidence coverage answer different questions. Compare them with a representative prompt, actual output length, retry behavior, and your quality bar.
Find a model for a taskFixed billing scenario
AI API cost rankings by model
Compare the tracked token charge for one repeatable monthly workload. Use this as a starting point for budgeting, not as a claim about model quality or completed-task cost.
Fixed billing scenario
1M input + 300K output tokens per month
This board uses default source-tracked input and output rates. It excludes retries, caching discounts, tool calls, storage, and quality differences. Recalculate with your workload before routing traffic.
| Rank | Model | Input / 1M | Output / 1M | Monthly reference | Checked |
|---|---|---|---|---|---|
| 1 | GPT-OSS 20B on GroqGroq | $0.07 | $0.30 | $0.16 | 2026-07-15 |
| 2 | Llama 4 Scout on GroqGroq | $0.11 | $0.34 | $0.21 | 2026-07-15 |
| 3 | Gemini 2.5 Flash-LiteGoogle | $0.10 | $0.40 | $0.22 | 2026-08-26 |
| 4 | DeepSeek V4 Flash non-thinkingDeepSeek | $0.14 | $0.28 | $0.22 | 2026-08-16 |
| 5 | Command R 08-2024Cohere | $0.15 | $0.60 | $0.33 | 2026-07-17 |
| 6 | GPT-4o miniOpenAI | $0.15 | $0.60 | $0.33 | 2026-09-08 |
| 7 | GPT-OSS 120B on GroqGroq | $0.15 | $0.60 | $0.33 | 2026-07-15 |
| 8 | Qwen3-32B on GroqGroq | $0.29 | $0.59 | $0.47 | 2026-07-15 |
| 9 | GPT-5.6 LunaOpenAI | $0.20 | $1.20 | $0.56 | 2026-09-08 |
| 10 | gpt-5.4-nanoOpenAI | $0.20 | $1.25 | $0.57 | 2026-09-08 |
| 11 | DeepSeek V4 ProDeepSeek | $0.43 | $0.87 | $0.70 | 2026-08-16 |
| 12 | Gemini 3.1 Flash-LiteGoogle | $0.25 | $1.50 | $0.70 | 2026-08-26 |
| 13 | Gemini 3.5 Live Translate PreviewGoogle | $0.25 | $1.50 | $0.70 | 2026-08-26 |
| 14 | Gemini 2.5 FlashGoogle | $0.30 | $2.50 | $1.05 | 2026-08-26 |
| 15 | Gemini 3.5 Flash-LiteGoogle | $0.30 | $2.50 | $1.05 | 2026-08-26 |
| 16 | Gemini 3 Flash PreviewGoogle | $0.50 | $3.00 | $1.40 | 2026-08-26 |
| 17 | Gemini 3.6 FlashGoogle | $0.75 | $3.75 | $1.88 | 2026-09-03 |
| 18 | Gemini 3.7 FlashGoogle | $0.75 | $3.75 | $1.88 | 2026-09-03 |
| 19 | Gemini 3.8 FlashGoogle | $0.75 | $3.75 | $1.88 | 2026-09-03 |
| 20 | gpt-5.4-miniOpenAI | $0.75 | $4.50 | $2.10 | 2026-09-08 |
| 21 | Kimi K2.6Moonshot AI | $0.95 | $4.00 | $2.15 | 2026-07-17 |
| 22 | Kimi K2.7 CodeMoonshot AI | $0.95 | $4.00 | $2.15 | 2026-07-17 |
| 23 | Claude Haiku 4.5Anthropic | $1.00 | $5.00 | $2.50 | 2026-09-08 |
| 24 | Mistral Medium 3.5Mistral | $1.50 | $7.50 | $3.75 | 2026-07-17 |
| 25 | Grok 4.5xAI | $2.00 | $6.00 | $3.80 | 2026-07-17 |
| 26 | Gemini 3.5 FlashGoogle | $1.50 | $9.00 | $4.20 | 2026-08-26 |
| 27 | Gemini 2.5 ProGoogle | $1.25 | $10.00 | $4.25 | 2026-08-26 |
| 28 | Kimi K2.7 Code High-SpeedMoonshot AI | $1.90 | $8.00 | $4.30 | 2026-07-17 |
| 29 | Claude Sonnet 5Anthropic | $2.00 | $10.00 | $5.00 | 2026-09-08 |
| 30 | Command ACohere | $2.50 | $10.00 | $5.50 | 2026-07-17 |
| 31 | Command R+ 08-2024Cohere | $2.50 | $10.00 | $5.50 | 2026-07-17 |
| 32 | GPT-4oOpenAI | $2.50 | $10.00 | $5.50 | 2026-09-08 |
| 33 | Gemini 3.1 Pro PreviewGoogle | $2.00 | $12.00 | $5.60 | 2026-08-26 |
| 34 | GPT-5.6 TerraOpenAI | $2.00 | $12.00 | $5.60 | 2026-09-08 |
| 35 | Claude Sonnet 4.6Anthropic | $3.00 | $15.00 | $7.50 | 2026-09-08 |
| 36 | Kimi K3Moonshot AI | $3.00 | $15.00 | $7.50 | 2026-07-17 |
| 37 | GPT-5.6 SolOpenAI | $4.00 | $20.00 | $10.00 | 2026-09-08 |
| 38 | Claude Opus 4.8Anthropic | $5.00 | $25.00 | $12.50 | 2026-09-08 |
| 39 | Claude Opus 5Anthropic | $5.00 | $25.00 | $12.50 | 2026-09-08 |
| 40 | Claude Fable 5Anthropic | $10.00 | $50.00 | $25.00 | 2026-09-08 |
Rates are source-tracked. Model a different workload in the LLM API cost calculator and review the provider pricing pages.
Turn a ranking into a test
FAQ
Ranking methodology questions
Does a higher ranking mean a better model?
No. Each board measures one defined dimension. Token count, price, context capacity, and evidence coverage do not substitute for testing your own completed tasks.