The cheapest LLM API right now is Llama Prompt Guard 2 22M at $0.030 input /
$0.030 output per million tokens. The most expensive output tokens belong to
gpt-6-cyber at $100.00 per million. We track 76 models from 8 providers.
| # | Model | Provider | Input / 1M | Output / 1M | Cached / 1M | Blended / 1M |
|---|---|---|---|---|---|---|
| 1 | Llama Prompt Guard 2 22M | Groq | $0.030 | $0.030 | — | $0.030 |
| 2 | Prompt Guard 2 86M | Groq | $0.040 | $0.040 | — | $0.040 |
| 3 | Llama 3.1 8B Instant | Groq | $0.050 | $0.080 | — | $0.058 |
| 4 | Ministral 3 3B | Mistral AI | $0.10 | $0.10 | $0.010 | $0.10 |
| 5 | GPT OSS 20B | Groq | $0.075 | $0.30 | — | $0.13 |
| 6 | GPT OSS Safeguard 20B | Groq | $0.075 | $0.30 | — | $0.13 |
| 7 | Safety GPT OSS 20B | Groq | $0.075 | $0.30 | — | $0.13 |
| 8 | Ministral 3 8B | Mistral AI | $0.15 | $0.15 | $0.015 | $0.15 |
| 9 | Llama 4 Scout | Groq | $0.11 | $0.34 | — | $0.17 |
| 10 | gpt-6-luna | OpenAI | $0.10 | $0.50 | $0.010 | $0.20 |
| 11 | Claude Haiku 5.5 | Anthropic | $0.10 | $0.50 | $0.010 | $0.20 |
| 12 | Ministral 3 14B | Mistral AI | $0.20 | $0.20 | $0.020 | $0.20 |
| 13 | Z.ai GLM 5.3 Flash | Mistral AI | $0.15 | $0.50 | $0.030 | $0.24 |
| 14 | GLM-5.3-Flash | Together AI | $0.15 | $0.50 | $0.030 | $0.24 |
| 15 | deepseek-flash | DeepSeek | $0.15 | $0.60 | $0.003 | $0.26 |
| 16 | GPT OSS 120B | Groq | $0.15 | $0.60 | — | $0.26 |
| 17 | Mistral Small 4 | Mistral AI | $0.15 | $0.60 | $0.015 | $0.26 |
| 18 | Qwen3 32B | Groq | $0.29 | $0.59 | — | $0.36 |
| 19 | Codestral | Mistral AI | $0.30 | $0.90 | $0.030 | $0.45 |
| 20 | DeepSeek V4.1 Flash 1017 | Mistral AI | $0.30 | $1.20 | $0.007 | $0.52 |
| 21 | Qwen3.7-Plus | Together AI | $0.32 | $1.28 | — | $0.56 |
| 22 | Gemini 3.1 Flash-Lite | $0.25 | $1.50 | $0.025 | $0.56 | |
| 23 | Llama 3.3 70B Versatile | Groq | $0.59 | $0.79 | — | $0.64 |
| 24 | Gemini 3 Flash Lite | $0.38 | $1.88 | $0.037 | $0.75 | |
| 25 | Gemini 2.5 Flash Lite | $0.38 | $1.88 | $0.037 | $0.75 | |
| 26 | Mistral Large 3 | Mistral AI | $0.50 | $1.50 | $0.050 | $0.75 |
| 27 | Gemini 3 Nano | $0.30 | $2.50 | $0.030 | $0.85 | |
| 28 | Gemini 3.5 Flash | $0.30 | $2.50 | $0.030 | $0.85 | |
| 29 | Gemini 2 Flash | $0.30 | $2.50 | $0.030 | $0.85 | |
| 30 | Gemini 3.5 Flash-Lite | $0.30 | $2.50 | $0.030 | $0.85 | |
| 31 | deepseek-v4-pro | DeepSeek | $0.66 | $1.98 | $0.022 | $0.99 |
| 32 | Gemini 2.5 Flash | $0.075 | $3.75 | $0.075 | $0.99 | |
| 33 | gpt-realtime-2.1-mini | OpenAI | $0.60 | $2.40 | $0.060 | $1.05 |
| 34 | Mistral Large 4 | Mistral AI | $0.70 | $2.10 | $0.070 | $1.05 |
| 35 | Gemini 3 Flash Preview | $0.50 | $3.00 | $0.050 | $1.12 | |
| 36 | grok-build-0.1 | xAI | $1.00 | $2.00 | $0.20 | $1.25 |
| 37 | Gemini 3 Flash | $0.75 | $3.75 | $0.075 | $1.50 | |
| 38 | Gemini 2.0 Flash | $0.75 | $3.75 | $0.075 | $1.50 | |
| 39 | Gemini 1.5 Flash | $0.75 | $3.75 | $0.075 | $1.50 | |
| 40 | Gemini 3.8 Flash | $0.75 | $3.75 | $0.075 | $1.50 | |
| 41 | Gemini 3.6 Flash | $0.75 | $3.75 | $0.075 | $1.50 | |
| 42 | grok-4.3 | xAI | $1.25 | $2.50 | $0.20 | $1.56 |
| 43 | grok-4.20-0309-reasoning | xAI | $1.25 | $2.50 | $0.20 | $1.56 |
| 44 | grok-4.20-0309-non-reasoning | xAI | $1.25 | $2.50 | $0.20 | $1.56 |
| 45 | Qwen3.8-27B | Groq | $0.80 | $4.00 | — | $1.60 |
| 46 | Gemini 2.0 Live | $0.75 | $4.50 | — | $1.69 | |
| 47 | DeepSeek V4 Pro 0813 | Together AI | $1.32 | $3.96 | $0.13 | $1.98 |
| 48 | gpt-6.1-terra | OpenAI | $1.00 | $5.00 | $0.050 | $2.00 |
| 49 | Gemini 3 Pro Lite | $1.00 | $5.00 | $0.050 | $2.00 | |
| 50 | Gemini 3 Pro Flash | $1.00 | $5.00 | $0.050 | $2.00 | |
| 51 | Gemini 3 Pro Thinking | $1.00 | $5.00 | $0.050 | $2.00 | |
| 52 | Z.ai GLM 5.3 | Mistral AI | $1.40 | $4.40 | $0.14 | $2.15 |
| 53 | GLM-5.3 | Together AI | $1.40 | $4.40 | $0.26 | $2.15 |
| 54 | GLM-5.2 | Together AI | $1.40 | $4.40 | $0.26 | $2.15 |
| 55 | grok-4.7 | xAI | $2.00 | $6.00 | $0.50 | $3.00 |
| 56 | grok-4.6 | xAI | $2.00 | $6.00 | $0.50 | $3.00 |
| 57 | grok-4.5 | xAI | $2.00 | $6.00 | $0.30 | $3.00 |
| 58 | Mistral Medium 3.5 | Mistral AI | $1.50 | $7.50 | $0.15 | $3.00 |
| 59 | Gemini 2.5 Pro | $1.25 | $10.00 | $0.12 | $3.44 | |
| 60 | Qwen3.7-Max | Together AI | $2.50 | $7.50 | $0.50 | $3.75 |
| 61 | gpt-6.1-sol | OpenAI | $2.00 | $10.00 | $0.10 | $4.00 |
| 62 | Claude Sonnet 5.5 | Anthropic | $2.00 | $10.00 | $0.10 | $4.00 |
| 63 | Gemini 3 Pro | $2.00 | $10.00 | $0.10 | $4.00 | |
| 64 | Gemini 4 Argon | $2.00 | $10.00 | $0.10 | $4.00 | |
| 65 | Kimi K3.1 Pro | Together AI | $2.00 | $10.00 | $0.20 | $4.00 |
| 66 | Gemini 3.1 Pro Preview | $2.00 | $12.00 | $0.20 | $4.50 | |
| 67 | gpt-5.3-codex | OpenAI | $1.75 | $14.00 | $0.17 | $4.81 |
| 68 | Kimi K3 | Together AI | $3.00 | $15.00 | $0.30 | $6.00 |
| 69 | gpt-5.6-sol | OpenAI | $4.00 | $20.00 | $0.40 | $8.00 |
| 70 | Claude Opus 5.5 | Anthropic | $4.00 | $20.00 | $0.20 | $8.00 |
| 71 | gpt-realtime-2.1 | OpenAI | $4.00 | $24.00 | $0.40 | $9.00 |
| 72 | chat-latest | OpenAI | $5.00 | $30.00 | $0.50 | $11.25 |
| 73 | gpt-6-astra | OpenAI | $10.00 | $50.00 | $1.00 | $20.00 |
| 74 | Claude Fable 5.1 | Anthropic | $10.00 | $50.00 | $0.25 | $20.00 |
| 75 | gpt-5.6-cyber | OpenAI | $12.50 | $75.00 | $1.25 | $28.12 |
| 76 | gpt-6-cyber | OpenAI | $20.00 | $100.00 | $2.00 | $40.00 |
Blended = (3 × input + output) ÷ 4, a typical chat mix. For agents and long conversations, the cached column is what drives the bill.
Prices last checked November 8, 2026 · re-checked twice a week from official pricing pages and APIs · How we collect prices
Which model should you actually use?
Describe the feature you're building and the Planner estimates monthly token spend for the models that fit.