Compare LLM API Prices
Compare published AI API prices, then open a model to check its region and context tiers. The workload examples below turn token rates into a concrete cost estimate.
Compare prices across 2521 models from 31 providers
| Compare | Provider | Model | Input Price | Output Price |
|---|---|---|---|---|
| AI21 Labs | $2 | $8 | ||
| AI21 Labs | $0.2 | $0.4 | ||
| Anthropic | $10 | $50 | ||
| Anthropic | $10 | $50 | ||
| Anthropic | $0.8 | $4 | ||
| Anthropic | $0.8 | $4 | ||
| Anthropic | $0.8 | $4 | ||
| Anthropic | $1 | $5 | ||
| Anthropic | ≤100K$0.1 $0.1 >100K$0.5 | $0.5 $0.5 $2.5 | ||
| Anthropic | $10 | $50 | ||
| Anthropic | $10 | $50 | ||
| Anthropic | $10 | $50 | ||
| Anthropic | $10 | $50 | ||
| Anthropic | $15 | $75 | ||
| Anthropic | $15 | $75 | ||
| Anthropic | $15 | $75 | ||
| Anthropic | $15 | $75 | ||
| Anthropic | $15 | $75 | ||
| Anthropic | $15 | $75 | ||
| Anthropic | $15 | $75 | ||
| Anthropic | $5 | $25 | ||
| Anthropic | $5 | $25 | ||
| Anthropic | $5 | $25 | ||
| Anthropic | $5 | $25 | ||
| Anthropic | $5 | $25 | ||
| Anthropic | $4 | $20 | ||
| Anthropic | $3 | $15 | ||
| Anthropic | $3 | $15 | ||
| Anthropic | $3 | $15 | ||
| Anthropic | $3 | $15 | ||
| Anthropic | $3 | $15 | ||
| Anthropic | $3 | $15 | ||
| Anthropic | $2 | $10 | ||
| Anthropic | $3 | $15 | ||
| Anthropic | $2 | $10 | ||
| AWS Bedrock | $0.3 | $2.5 | ||
| AWS Bedrock | $1 | $40 | ||
| AWS Bedrock | $1.25 Global cross-region$1.25 | — $10 | ||
| AWS Bedrock | $3 Global cross-region$3 | — $12 | ||
| AWS Bedrock | $0.3 Global cross-region$0.3 | — $2.5 | ||
| AWS Bedrock | $0.04/image | — | ||
| AWS Bedrock | $0.06 Global cross-region$0.06 | — $0.24 | ||
| AWS Bedrock | $0.035 Global cross-region$0.035 | — $0.14 | ||
| AWS Bedrock | $0.0675 {priceOf!bedrock/bedrock!fWTU_nxHvSmnGvjH1erX6tTZZ— | — | ||
| AWS Bedrock | $0.135 {priceOf!bedrock/bedrock!Zfo8texvBEL9ZYfvvuztxH_ja— | — | ||
| AWS Bedrock | $2.5 | $12.5 | ||
| AWS Bedrock | $0.8 Global cross-region$0.8 | — $3.2 | ||
| AWS Bedrock | $1 Global cross-region$1 | — $4 | ||
| AWS Bedrock | $0.08/sec | — | ||
| AWS Bedrock | $3.4 Global cross-region$3.4 | — $13.6 |
per 1M tokens · US Dollar · Source: Official pricing pages
LLM API cost examples
1,000 requests, each using 1,000 input tokens and 200 billed text output tokens: 1M input and 200K output tokens in total.
| Model | Input / 1M tokens | Output / 1M tokens | Estimated cost | Pricing conditions |
|---|---|---|---|---|
| Claude Haiku 5.5Anthropic | $0.1 | $0.5 | $0.2 | Region not specifiedInput tier up to 100K tokens per requestView official pricing |
| gpt-6-lunaOpenAI | $0.1 | $0.5 | $0.2 | Region not specifiedView official pricing |
| qwen3.8-flashQwen | $0.1196 | $0.4038 | $0.2004 | China MainlandInput tier up to 1M tokens per requestView official pricing |
| MiniMax-M2.7MiniMax | $0.3141 | $1.26 | $0.5653 | Region not specifiedView official pricing |
| deepseek-v4-flashDeepSeek | $0.44 | $1.32 | $0.704 | Region not specifiedView official pricing |
| GLM-5-TurboZhipu | $0.7478 | $3.29 | $1.41 | Region not specifiedInput tier up to 32K tokens per requestView official pricing |
Estimates in USD use standard processing, uncached input and the displayed base input tier. Regional rates, longer prompts, thinking tokens and other billable usage can change the final cost. Models can differ in capabilities.
Calculate costs for your workload →Frequently Asked Questions
What is the cheapest LLM API right now?▾
Mistral OCR (25.05) (Google Vertex AI) currently offers the lowest input price at $0.0005 per million tokens for text generation.
Which AI model has the largest context window?▾
Auto Router (OpenRouter) supports the largest context window among tracked models at 2M.
How is LLM API pricing structured?▾
Most LLM APIs charge separately for input tokens (your prompt and conversation history) and output tokens (the model's response). Output tokens typically cost 2–5× more than input tokens. Many providers also offer discounted batch pricing, prompt caching for repeated prefixes, and surcharges for long-context requests.
Which AI providers does LLMRates.ai track?▾
LLMRates.ai tracks models from Anthropic, Google, OpenAI, AI21 Labs, AWS Bedrock, Azure AI, Cloudflare Workers AI, Cohere, and more — covering both US and Chinese AI providers.
How often are prices updated?▾
Prices are scraped directly from official provider pricing pages and updated daily. Major price changes are typically reflected within 24 hours.
What is prompt caching and how does it reduce API costs?▾
Prompt caching stores a repeated prompt prefix — such as a system prompt or a large document — so the model doesn't re-process it on every request. Providers like Anthropic and Google offer cached input tokens at a 70–90% discount off the standard input price, making it a key cost-reduction lever for production applications.
What is the gpt-4-0613 API price?▾
gpt-4-0613 (OpenAI) costs $30 per million input tokens and $60 per million output tokens.
How much does Claude Sonnet 5.5 cost?▾
Claude Sonnet 5.5 (Anthropic) costs $2 per million input tokens and $10 per million output tokens.
What is Gemini Omni Flash Preview API pricing?▾
Gemini Omni Flash Preview (Google) costs $1.5 per million input tokens and $9 per million output tokens.
What are the most affordable models from top AI providers?▾
The most affordable popular models by input price (USD, standard tier, per million tokens):
- doubao-seed-2.0-mini (Volcano Ark) — $0.0299 input / $0.2991 output
- Claude Haiku 5.5 (Anthropic) — $0.1 input / $0.5 output
- gpt-6-luna (OpenAI) — $0.1 input / $0.5 output
- qwen3.8-flash (Qwen) — $0.1196 input / $0.4038 output
- qwen3.7-plus (Qwen) — $0.2991 input / $1.2 output
How do I control token costs when building AI agents?▾
AI agents run in multi-step loops — each iteration re-sends the accumulated conversation history, tool results, and plan, so token costs compound quickly. Prioritize models with low input pricing and strong tool/function-calling support. Prompt caching (Anthropic, Google) can cut costs by 70–90% on repeated context. Affordable models with solid tool support include:
What are reasoning models and how are they priced?▾
Reasoning models — such as glm-4.5, glm-4.5-air, glm-4.6, glm-4.7 — perform internal chain-of-thought reasoning before responding. They are typically priced 5–20× higher than standard models due to the extra compute for reasoning tokens. Some providers charge a separate rate for thinking tokens generated during the reasoning process.