LLM Token Cost Calculator
Compare API pricing across 202+ language models from OpenAI, Anthropic, Google, Meta, Mistral, xAI, DeepSeek and Cohere. Includes cached-input pricing, batch-API discounts and reasoning-token math. Prices auto-refresh every 24 hours via OpenRouter.
Featured model pricing (per 1M tokens)
| Model | Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|---|
| Anthropic: Claude Haiku 4.5 | Anthropic | $1.00 | $5.00 | $0.10 | 200K |
| Anthropic: Claude Opus 4.7 | Anthropic | $5.00 | $25.00 | $0.50 | 1000K |
| Anthropic: Claude Sonnet 4.6 | Anthropic | $3.00 | $15.00 | $0.30 | 1000K |
| Cohere: Command R (08-2024) | Cohere | $0.15 | $0.60 | — | 128K |
| Cohere: Command R+ (08-2024) | Cohere | $2.50 | $10.00 | — | 128K |
| Cohere: Command R7B (12-2024) | Cohere | $0.04 | $0.15 | — | 128K |
| DeepSeek: DeepSeek V3.1 Terminus | DeepSeek | $0.21 | $0.79 | $0.13 | 164K |
| DeepSeek: DeepSeek V3.2 | DeepSeek | $0.25 | $0.38 | $0.03 | 131K |
| DeepSeek: DeepSeek V3.2 Exp | DeepSeek | $0.27 | $0.41 | — | 164K |
| DeepSeek: DeepSeek V3.2 Speciale | DeepSeek | $0.40 | $1.20 | $0.20 | 164K |
| DeepSeek: R1 | DeepSeek | $0.70 | $2.50 | — | 64K |
| DeepSeek: R1 0528 | DeepSeek | $0.50 | $2.15 | $0.35 | 164K |
| DeepSeek: R1 Distill Llama 70B | DeepSeek | $0.70 | $0.80 | — | 131K |
| DeepSeek: R1 Distill Qwen 32B | DeepSeek | $0.29 | $0.29 | — | 33K |
| Google: Gemini 2.5 Pro | $1.25 | $10.00 | $0.13 | 1049K | |
| Google: Gemini 2.5 Pro Preview 05-06 | $1.25 | $10.00 | $0.13 | 1049K | |
| Google: Gemini 2.5 Pro Preview 06-05 | $1.25 | $10.00 | $0.13 | 1049K | |
| Google: Gemini 3 Flash Preview | $0.50 | $3.00 | $0.05 | 1049K | |
| Google: Nano Banana Pro (Gemini 3 Pro Image Preview) | $2.00 | $12.00 | $0.20 | 66K | |
| Meta: Llama 3.3 70B Instruct | Meta | $0.12 | $0.38 | — | 131K |
| Meta: Llama 4 Maverick | Meta | $0.15 | $0.60 | — | 1049K |
| Meta: Llama 4 Scout | Meta | $0.08 | $0.30 | — | 328K |
| Mistral Large | Mistral | $2.00 | $6.00 | $0.20 | 128K |
| Mistral Large 2407 | Mistral | $2.00 | $6.00 | $0.20 | 131K |
| Mistral Large 2411 | Mistral | $2.00 | $6.00 | $0.20 | 131K |
| Mistral: Mistral Large 3 2512 | Mistral | $0.50 | $1.50 | $0.05 | 262K |
| OpenAI: GPT-4o | OpenAI | $2.50 | $10.00 | — | 128K |
| OpenAI: GPT-4o (2024-05-13) | OpenAI | $5.00 | $15.00 | — | 128K |
| OpenAI: GPT-4o (2024-08-06) | OpenAI | $2.50 | $10.00 | $1.25 | 128K |
| OpenAI: GPT-4o (2024-11-20) | OpenAI | $2.50 | $10.00 | $1.25 | 128K |
| OpenAI: GPT-4o Audio | OpenAI | $2.50 | $10.00 | — | 128K |
| OpenAI: GPT-4o Search Preview | OpenAI | $2.50 | $10.00 | — | 128K |
| OpenAI: GPT-4o-mini | OpenAI | $0.15 | $0.60 | $0.07 | 128K |
| OpenAI: GPT-4o-mini (2024-07-18) | OpenAI | $0.15 | $0.60 | $0.07 | 128K |
| OpenAI: GPT-4o-mini Search Preview | OpenAI | $0.15 | $0.60 | — | 128K |
| OpenAI: GPT-5 | OpenAI | $1.25 | $10.00 | $0.13 | 400K |
| OpenAI: GPT-5 Chat | OpenAI | $1.25 | $10.00 | $0.13 | 128K |
| OpenAI: GPT-5 Codex | OpenAI | $1.25 | $10.00 | $0.13 | 400K |
| OpenAI: GPT-5 Image | OpenAI | $10.00 | $10.00 | $1.25 | 400K |
| OpenAI: GPT-5 Image Mini | OpenAI | $2.50 | $2.00 | $0.25 | 400K |
| OpenAI: GPT-5 Mini | OpenAI | $0.25 | $2.00 | $0.02 | 400K |
| OpenAI: GPT-5 Nano | OpenAI | $0.05 | $0.40 | $0.01 | 400K |
| OpenAI: GPT-5 Pro | OpenAI | $15.00 | $120.00 | — | 400K |
| OpenAI: GPT-5.1 | OpenAI | $1.25 | $10.00 | $0.13 | 400K |
| OpenAI: GPT-5.1 Chat | OpenAI | $1.25 | $10.00 | $0.13 | 128K |
| OpenAI: GPT-5.1-Codex | OpenAI | $1.25 | $10.00 | $0.13 | 400K |
| OpenAI: GPT-5.1-Codex-Max | OpenAI | $1.25 | $10.00 | $0.13 | 400K |
| OpenAI: GPT-5.1-Codex-Mini | OpenAI | $0.25 | $2.00 | $0.03 | 400K |
| OpenAI: GPT-5.2 | OpenAI | $1.75 | $14.00 | $0.17 | 400K |
| OpenAI: GPT-5.2 Chat | OpenAI | $1.75 | $14.00 | $0.17 | 128K |
| OpenAI: GPT-5.2 Pro | OpenAI | $21.00 | $168.00 | — | 400K |
| OpenAI: GPT-5.2-Codex | OpenAI | $1.75 | $14.00 | $0.17 | 400K |
| OpenAI: GPT-5.3 Chat | OpenAI | $1.75 | $14.00 | $0.17 | 128K |
| OpenAI: GPT-5.3-Codex | OpenAI | $1.75 | $14.00 | $0.17 | 400K |
| OpenAI: GPT-5.4 | OpenAI | $2.50 | $15.00 | $0.25 | 1050K |
| OpenAI: GPT-5.4 Mini | OpenAI | $0.75 | $4.50 | $0.07 | 400K |
| OpenAI: GPT-5.4 Nano | OpenAI | $0.20 | $1.25 | $0.02 | 400K |
| OpenAI: GPT-5.4 Pro | OpenAI | $30.00 | $180.00 | — | 1050K |
| OpenAI: o3 | OpenAI | $2.00 | $8.00 | $0.50 | 200K |
| OpenAI: o3 Deep Research | OpenAI | $10.00 | $40.00 | $2.50 | 200K |
| OpenAI: o3 Mini | OpenAI | $1.10 | $4.40 | $0.55 | 200K |
| OpenAI: o3 Mini High | OpenAI | $1.10 | $4.40 | $0.55 | 200K |
| OpenAI: o3 Pro | OpenAI | $20.00 | $80.00 | — | 200K |
| OpenAI: o4 Mini | OpenAI | $1.10 | $4.40 | $0.28 | 200K |
| OpenAI: o4 Mini Deep Research | OpenAI | $2.00 | $8.00 | $0.50 | 200K |
| OpenAI: o4 Mini High | OpenAI | $1.10 | $4.40 | $0.28 | 200K |
| Qwen: Qwen3 14B | Qwen | $0.06 | $0.24 | — | 41K |
| Qwen: Qwen3 235B A22B | Qwen | $0.45 | $1.82 | — | 131K |
| Qwen: Qwen3 235B A22B Instruct 2507 | Qwen | $0.07 | $0.10 | — | 262K |
| Qwen: Qwen3 235B A22B Thinking 2507 | Qwen | $0.13 | $0.60 | — | 262K |
| Qwen: Qwen3 30B A3B | Qwen | $0.08 | $0.28 | — | 41K |
| Qwen: Qwen3 30B A3B Instruct 2507 | Qwen | $0.09 | $0.30 | — | 262K |
| Qwen: Qwen3 30B A3B Thinking 2507 | Qwen | $0.08 | $0.40 | $0.08 | 131K |
| Qwen: Qwen3 32B | Qwen | $0.08 | $0.24 | $0.04 | 41K |
| Qwen: Qwen3 8B | Qwen | $0.05 | $0.40 | $0.05 | 41K |
| Qwen: Qwen3 Coder 30B A3B Instruct | Qwen | $0.07 | $0.27 | — | 160K |
| Qwen: Qwen3 Coder 480B A35B | Qwen | $0.22 | $1.00 | $0.02 | 262K |
| Qwen: Qwen3 Coder Flash | Qwen | $0.20 | $0.97 | $0.04 | 1000K |
| Qwen: Qwen3 Coder Next | Qwen | $0.15 | $0.80 | $0.12 | 262K |
| Qwen: Qwen3 Coder Plus | Qwen | $0.65 | $3.25 | $0.13 | 1000K |
| Qwen: Qwen3 Max | Qwen | $0.78 | $3.90 | $0.16 | 262K |
| Qwen: Qwen3 Max Thinking | Qwen | $0.78 | $3.90 | — | 262K |
| Qwen: Qwen3 Next 80B A3B Instruct | Qwen | $0.09 | $1.10 | — | 262K |
| Qwen: Qwen3 Next 80B A3B Thinking | Qwen | $0.10 | $0.78 | — | 131K |
| Qwen: Qwen3 VL 235B A22B Instruct | Qwen | $0.20 | $0.88 | $0.11 | 262K |
| Qwen: Qwen3 VL 235B A22B Thinking | Qwen | $0.26 | $2.60 | — | 131K |
| Qwen: Qwen3 VL 30B A3B Instruct | Qwen | $0.13 | $0.52 | — | 131K |
| Qwen: Qwen3 VL 30B A3B Thinking | Qwen | $0.13 | $1.56 | — | 131K |
| Qwen: Qwen3 VL 32B Instruct | Qwen | $0.10 | $0.42 | — | 131K |
| Qwen: Qwen3 VL 8B Instruct | Qwen | $0.08 | $0.50 | — | 131K |
| Qwen: Qwen3 VL 8B Thinking | Qwen | $0.12 | $1.36 | — | 131K |
| Qwen: Qwen3.5 397B A17B | Qwen | $0.39 | $2.34 | $0.20 | 262K |
| Qwen: Qwen3.5 Plus 2026-02-15 | Qwen | $0.26 | $1.56 | — | 1000K |
| Qwen: Qwen3.5-122B-A10B | Qwen | $0.26 | $2.08 | — | 262K |
| Qwen: Qwen3.5-27B | Qwen | $0.20 | $1.56 | — | 262K |
| Qwen: Qwen3.5-35B-A3B | Qwen | $0.16 | $1.30 | — | 262K |
| Qwen: Qwen3.5-9B | Qwen | $0.10 | $0.15 | — | 262K |
| Qwen: Qwen3.5-Flash | Qwen | $0.07 | $0.26 | — | 1000K |
| Qwen: Qwen3.6 Plus | Qwen | $0.33 | $1.95 | — | 1000K |
| xAI: Grok 4 | xAI | $3.00 | $15.00 | $0.75 | 256K |
| xAI: Grok 4 Fast | xAI | $0.20 | $0.50 | $0.05 | 2000K |
| xAI: Grok 4.1 Fast | xAI | $0.20 | $0.50 | $0.05 | 2000K |
| xAI: Grok 4.20 | xAI | $2.00 | $6.00 | $0.20 | 2000K |
| xAI: Grok 4.20 Multi-Agent | xAI | $2.00 | $6.00 | $0.20 | 2000K |
Frequently asked questions
How are these LLM prices kept up to date?
Prices are pulled directly from OpenRouter’s public models API once every 24 hours via a Convex cron job, then normalized to per-1M-token figures. Each row displays the timestamp of the last successful refresh.
What are cached-input and batch-API discounts?
Cached input applies when you send the same system prompt or context repeatedly — providers like OpenAI and Anthropic charge 50–90% less for cached tokens. Batch mode processes requests asynchronously within 24 hours for a flat 50% discount on both input and output. Toggle either in the calculator above to model real-world cost.
How accurate are the token estimates?
The paste-text estimator uses a rough chars÷4 heuristic. For mission-critical billing forecasts, run your prompts through the official tokenizer for your provider (tiktoken for OpenAI, Anthropic’s count endpoint, Gemini’scount_tokens API).
Which model is cheapest for high-volume production use?
For raw price-per-token, the small-model tier (GPT-5 nano, Claude Haiku 4.5, Gemini 3 Flash, DeepSeek V3) is typically 10–50× cheaper than the flagship reasoning models. Use the calculator to compare your specific input/output ratio — output tokens are usually 3–5× more expensive than input tokens, so verbose models can lose to less-verbose ones at scale.