One table for every stored input, output, cache-read, and context-window value. Values are catalog snapshots, not live provider quotes. Use the JSON endpoint to build your own diff or alerting job.
All values in USD per 1,000,000 tokens unless noted. Cache read shows — when the model has no published cache rate.
| # | Model | Provider | Category | Input / 1M | Output / 1M | Cache / 1M | Context | Profile |
|---|---|---|---|---|---|---|---|---|
| 1 | GPT-6 Luna | OpenAI | Cost-Efficient | $0.100 | $0.500 | $0.010 | 1.1M | View |
| 2 | Claude Haiku 5.5 | Anthropic | Cost-Efficient | $0.100 | $0.500 | $0.010 | 1M | View |
| 3 | DeepSeek Flash | DeepSeek | Open-Weights | $0.150 | $0.600 | $0.003 | 1M | View |
| 4 | GPT-4o Mini | OpenAI | Cost-Efficient | $0.150 | $0.600 | $0.075 | 128k | View |
| 5 | Gemini 3.5 Flash-Lite | Cost-Efficient | $0.300 | $2.50 | $0.030 | 1M | View | |
| 6 | Qwen 2.5 72B | Alibaba | Open-Weights | $0.350 | $0.400 | $0.350 | 128k | View |
| 7 | Llama 3.3 70B (Groq/Together) | Meta | Open-Weights | $0.590 | $0.790 | $0.590 | 128k | View |
| 8 | DeepSeek V4 Pro | DeepSeek | Open-Weights | $0.660 | $1.98 | $0.022 | 1M | View |
| 9 | GPT-5.4 Mini | OpenAI | Cost-Efficient | $0.750 | $4.50 | $0.075 | 400k | View |
| 10 | Gemini 3.8 Flash | Cost-Efficient | $0.750 | $3.75 | $0.075 | 1M | View | |
| 11 | Grok 4.3 | xAI | Cost-Efficient | $1.25 | $2.50 | $0.200 | 1M | View |
| 12 | GPT-6.1 Sol | OpenAI | Flagship | $2.00 | $10.00 | $0.100 | 1.1M | View |
| 13 | Claude Sonnet 5.5 | Anthropic | Flagship | $2.00 | $10.00 | $0.100 | 1M | View |
| 14 | Gemini 3.1 Pro (Preview) | Reasoning | $2.00 | $12.00 | $0.200 | 1M | View | |
| 15 | Grok 4.7 | xAI | Flagship | $2.00 | $6.00 | $0.500 | 500k | View |
| 16 | Mistral Large 2 | Mistral | Flagship | $2.00 | $6.00 | $1.00 | 128k | View |
| 17 | GPT-4o (Omni) | OpenAI | Flagship | $2.50 | $10.00 | $1.25 | 128k | View |
| 18 | Command R+ (Cohere) | Cohere | Flagship | $2.50 | $10.00 | $1.25 | 128k | View |
| 19 | Claude Opus 5.5 | Anthropic | Flagship | $4.00 | $20.00 | $0.200 | 1M | View |
| 20 | Gemini 4 Argon | Reasoning | $4.00 | $20.00 | $0.200 | 1M | View | |
| 21 | GPT-5.5 | OpenAI | Flagship | $5.00 | $30.00 | $0.500 | 922k | View |
| 22 | GPT-6 Astra | OpenAI | Reasoning | $10.00 | $50.00 | $1.00 | 1.1M | View |
| 23 | Claude Fable 5.1 | Anthropic | Reasoning | $10.00 | $50.00 | $0.250 | 1M | View |
In this catalog, GPT-6 Luna has the lowest input price at $0.100 per 1M input tokens. The cheapest output price is Qwen 2.5 72B at $0.400 per 1M output tokens. "Cheapest" depends on your input/output mix, so check the workload rankings too.
No. Prices are stored catalog snapshots reviewed on the dates shown. Providers change prices frequently, so confirm current rates on the provider pricing page before budgeting.
GET /api/price-index returns the same rows as JSON, plus source URLs and review dates. It is cached for an hour and is safe to poll for diffs or alerting.
Only models with a published prompt-caching rate show a cache-read price. Models without one bill all input tokens at the standard input rate.
| Model | Provider | Input / 1M | Output / 1M | Successor | Profile |
|---|---|---|---|---|---|
| DeepSeek V3 | DeepSeek | $0.140 | $0.280 | deepseek-flash | Archive |
| DeepSeek R1 (Reasoning) | DeepSeek | $0.550 | $2.19 | deepseek-v4-pro | Archive |
| Gemini 2.0 Flash | $0.100 | $0.400 | gemini-3-5-flash-lite | Archive | |
| Claude 3.5 Sonnet | Anthropic | $3.00 | $15.00 | claude-sonnet-5-5 | Archive |
| Claude 3.5 Haiku | Anthropic | $0.800 | $4.00 | claude-haiku-5-5 | Archive |
| o1 (Reasoning) | OpenAI | $15.00 | $60.00 | gpt-6-astra | Archive |
| o3-mini (Reasoning) | OpenAI | $1.10 | $4.40 | gpt-6-1-sol | Archive |
| Gemini 1.5 Pro | $1.25 | $5.00 | gemini-3-1-pro-preview | Archive | |
| Gemini 1.5 Flash | $0.075 | $0.300 | gemini-3-5-flash-lite | Archive | |
| Grok 2 | xAI | $2.00 | $10.00 | grok-4-7 | Archive |
| Claude 3.7 Sonnet | Anthropic | $3.00 | $15.00 | claude-sonnet-5-5 | Archive |