Source-tracked API prices
Compare LLM input and output prices on one map.
See how tracked token rates cluster across providers, then inspect context windows, cached-input prices, model pages, and direct comparisons.
Showing 27 models.
Input price / 1M tokensOutput price / 1M tokens
AnthropicDeepSeekGoogleGroqOpenAI
Direct comparison
Compare costsCompare two models with the same workload
Static price reference
Tracked model prices behind the chart
Default profiles only. Threshold, batch, cache-write, and long-context tiers remain on model and provider pages.
| Model | Provider | Input / 1M | Cached input / 1M | Output / 1M | Context | Status | Checked |
|---|---|---|---|---|---|---|---|
| GPT-4o mini | OpenAI | $0.15 | $0.075 | $0.60 | 128,000 | Stable | 2026-07-13 |
| GPT-4o | OpenAI | $2.50 | $1.25 | $10.00 | 128,000 | Stable | 2026-07-13 |
| gpt-5.6-sol | OpenAI | $5.00 | $0.50 | $30.00 | 1,050,000 | Stable | 2026-07-13 |
| gpt-5.6-terra | OpenAI | $2.50 | $0.25 | $15.00 | 1,050,000 | Stable | 2026-07-13 |
| gpt-5.6-luna | OpenAI | $1.00 | $0.10 | $6.00 | 1,050,000 | Stable | 2026-07-13 |
| gpt-5.4-mini | OpenAI | $0.75 | $0.075 | $4.50 | 400,000 | Stable | 2026-07-13 |
| gpt-5.4-nano | OpenAI | $0.20 | $0.02 | $1.25 | 400,000 | Stable | 2026-07-13 |
| Claude Sonnet 5 | Anthropic | $2.00 | $0.20 | $10.00 | 1,000,000 | Stable | 2026-07-12 |
| Claude Opus 4.8 | Anthropic | $5.00 | $0.50 | $25.00 | 1,000,000 | Stable | 2026-07-12 |
| Claude Sonnet 4.6 | Anthropic | $3.00 | $0.30 | $15.00 | 1,000,000 | Stable | 2026-07-12 |
| Claude Haiku 4.5 | Anthropic | $1.00 | $0.10 | $5.00 | 200,000 | Stable | 2026-07-12 |
| Gemini 2.5 Pro | $1.25 | $0.125 | $10.00 | 1,048,576 | Stable | 2026-07-12 | |
| Gemini 2.5 Flash | $0.30 | $0.03 | $2.50 | 1,048,576 | Stable | 2026-07-12 | |
| Gemini 2.5 Flash-Lite | $0.10 | $0.01 | $0.40 | 1,048,576 | Stable | 2026-07-12 | |
| deepseek-v4-pro | DeepSeek | $0.435 | $0.0036 | $0.87 | 1,000,000 | Stable | 2026-07-12 |
| DeepSeek V4 Flash non-thinking | DeepSeek | $0.14 | $0.0028 | $0.28 | 1,000,000 | Stable | 2026-07-12 |
| Claude Fable 5 | Anthropic | $10.00 | $1.00 | $50.00 | 1,000,000 | Stable | 2026-07-14 |
| Claude Mythos 5 | Anthropic | $10.00 | $1.00 | $50.00 | 1,000,000 | Limited availability | 2026-07-14 |
| Gemini 3.5 Flash | $1.50 | $0.15 | $9.00 | 1,048,576 | Stable | 2026-07-14 | |
| Gemini 3.5 Live Translate Preview | $0.25 | $0.025 | $1.50 | 131,072 | Preview | 2026-07-14 | |
| Gemini 3 Flash Preview | $0.50 | $0.05 | $3.00 | 1,048,576 | Preview | 2026-07-14 | |
| Gemini 3.1 Flash-Lite | $0.25 | $0.025 | $1.50 | 1,048,576 | Stable | 2026-07-14 | |
| Gemini 3.1 Pro Preview | $2.00 | $0.20 | $12.00 | 1,048,576 | Preview | 2026-07-14 | |
| GPT-OSS 20B on Groq | Groq | $0.075 | $0.037 | $0.30 | 131,072 | Stable | 2026-07-15 |
| GPT-OSS 120B on Groq | Groq | $0.15 | $0.075 | $0.60 | 131,072 | Stable | 2026-07-15 |
| Llama 4 Scout on Groq | Groq | $0.11 | Unavailable | $0.34 | 131,072 | Preview | 2026-07-15 |
| Qwen3-32B on Groq | Groq | $0.29 | Unavailable | $0.59 | 131,072 | Preview | 2026-07-15 |
Lower left means lower tracked token rates
The chart uses logarithmic axes because model prices span more than two orders of magnitude. Bubble size reflects tracked context-window capacity, not quality or popularity.
Token price is not total application cost
Quality, retries, latency, output length, caching, routing, and failed agent loops can change cost per completed task.