An AI token is the smallest unit of text that a large language model processes. In English, one token averages ~4 characters or three-quarters of a word — so "hamburger" tokenizes to 3 tokens ("ham", "bur", "ger") and "hi" is 1 token. AI APIs from Anthropic (Claude), OpenAI (GPT-4o), and Google (Gemini) bill by the token, charging separately for input (text you send) and output (text generated). This convention has held across every major provider since GPT-3 launched in 2020.

What is the difference between input and output tokens?

Input tokens are everything you send to the model — your prompt, system instructions, conversation history, and any retrieved context. Output tokens are what the model generates in response. As of May 2026, output tokens are 3–5× more expensive than input tokens across every major provider: Claude Sonnet 4 is $3/1M input vs $15/1M output (5×), GPT-4o is $2.50/1M input vs $10/1M output (4×), and Gemini 2.0 Flash is $0.10/1M input vs $0.40/1M output (4×). The reason: generating each output token requires a full forward pass through the model, while input tokens are processed in parallel during prefill.

How many tokens is 1,000 words?

1,000 words of English text is approximately 1,333 tokens, based on the standard ratio of ~1.33 tokens per English word (4 characters per token, ~5.3 characters per word including spaces). A 250-word page is ~333 tokens, a 2,500-word document is ~3,333 tokens, and an 80,000-word novel is ~106,667 tokens. Code, non-English languages, and structured data tokenize differently — Chinese and Japanese often run 1–2 tokens per character.

How many tokens is 1 page of text?

A standard single-spaced page of English text (250–300 words) contains ~330–400 tokens. A double-spaced manuscript page (~250 words) is also ~333 tokens. A densely packed US Letter page at 500 words is ~667 tokens. For reference, the entire works of Shakespeare (~835,000 words) come to roughly 1.1 million tokens — fitting comfortably inside a single Gemini 2.5 Pro request (1M context window).

Which AI model is the cheapest in 2026?

As of May 2026, Llama 3.1 8B is the cheapest hosted mainstream model at ~$0.05/1M input tokens, followed by Gemini 1.5 Flash at $0.075/1M, Gemini 2.0 Flash at $0.10/1M, Mistral Small at $0.10/1M, GPT-4o mini at $0.15/1M, and Claude Haiku 4 at $0.25/1M. For high-volume production workloads, Gemini 2.0 Flash usually wins on cost-per-quality because it pairs the $0.10/1M input price with a 1 million-token context window — far larger than the others at the same tier.

What does "per million tokens" mean?

AI APIs price by the million tokens (often written $/1M tokens or $/MTok). If a model lists "$3/1M input", a 1,000-token prompt costs $0.003 (1,000 ÷ 1,000,000 × $3). Most single API calls cost fractions of a cent — but at production scale (10M+ requests/month) the choice between $0.10/1M and $3/1M is the difference between a $30 bill and a $900 bill for the same workload.

How does the TokenRate calculator work?

Enter a budget (USD), a token count, or a character count into the calculator. TokenRate uses live pricing from the OpenRouter API — refreshed hourly via Next.js ISR — to compute the exact tokens-per-dollar or dollars-per-token for every tracked model in parallel. It uses the standard 4-characters-per-token approximation for English text; precise per-tokenizer counts require provider-specific libraries (tiktoken for OpenAI, the Anthropic SDK for Claude).

Is the pricing data real-time?

Live pricing is pulled from the OpenRouter API and refreshed every hour via Next.js Incremental Static Regeneration. OpenRouter aggregates real-time pricing from Anthropic, OpenAI, Google, Meta, DeepSeek, xAI, and Mistral. Reference pricing on individual model pages is reviewed on a rolling cadence (last full sweep: 2026-05-22). For mission-critical decisions, always confirm with the provider's own pricing page.

Can I reduce my AI API bill without changing model?

Yes. Three high-leverage moves: (1) Prompt caching cuts the cost of cached input tokens by ~90% on Anthropic and ~50% on OpenAI — ideal for long, static system prompts. (2) Batch APIs from Anthropic and OpenAI offer a 50% discount with a 24-hour turnaround for asynchronous workloads. (3) Output-length controls (setting max_tokens, requesting concise answers) directly reduce the expensive side of the bill. Combined, these can cut costs 5–10× without changing models.

NodeaBranching AI chat

A branching
AI chat canvas.

How should we launch?

A cautious plan — or a bolder one?

↳ branch the reply

Open a canvas — free

Free during beta · No credit card · nodea.ai

NodeaBranching AI chat

Why settle for
one answer?

Ask once. Branch the reply and explore every option in parallel — then keep the best.

Free during beta · No credit card · nodea.ai

TokenRate · tokenrate.dev

AI Token Calculator & Live Pricing Comparison

Prices updated daily — last verified 2026-10-12

TYPE ANY AMOUNT — RESULTS UPDATE LIVE

354 models · 24 providers

Quick

Model	Tier	Quality	Rate in / out / 1M	Tokens In	Tokens Out	Value
Claude Haiku 5.5	Fast	60	$0.100 – $0.500	—	—	600
Claude Haiku 5.5 (batch)	Fast	60	$0.050 – $0.250	—	—	1.2k
Nano Banana 2.1	Fast	—	$1.50 – $7.50	—	—	—
Mistral Large 4	Flagship	50	$0.680 – $2.09	—	—	74
GPT-6.1 Sol Pro	Balanced	—	$2.00 – $10.00	—	—	—
GPT-6.1 Sol Pro (batch)	Balanced	—	$1.00 – $5.00	—	—	—
GPT-6.1 Sol	Balanced	—	$2.00 – $10.00	—	—	—
GPT-6.1 Sol (batch)	Balanced	—	$1.00 – $5.00	—	—	—
Claude Sonnet 5.5	Balanced	85	$2.00 – $10.00	—	—	43
Claude Sonnet 5.5 (batch)	Balanced	85	$1.00 – $5.00	—	—	85
GLM 5.3 Prime	Balanced	—	$2.80 – $8.80	—	—	—
Qwen3.8 Max Prime	Flagship	74elo	$4.00 – $12.00	—	—	19
Solar Mini 4	Fast	—	$0.050 – $0.200	—	—	—
Command A+	Balanced	—	$0.300 – $1.50	—	—	—
GPT-6 Luna Pro	Balanced	—	$0.100 – $0.500	—	—	—
GPT-6 Luna Pro (batch)	Balanced	—	$0.050 – $0.250	—	—	—
GPT-6 Luna	Balanced	—	$0.100 – $0.500	—	—	—
GPT-6 Luna (batch)	Balanced	—	$0.050 – $0.250	—	—	—
GPT-6 Sol Pro	Balanced	—	$2.00 – $10.00	—	—	—
GPT-6 Sol Pro (batch)	Balanced	—	$1.00 – $5.00	—	—	—
GPT-6 Sol	Balanced	—	$2.00 – $10.00	—	—	—
GPT-6 Sol (batch)	Balanced	—	$1.00 – $5.00	—	—	—
Claude Opus 5.5	Flagship	79elo	$4.00 – $20.00	—	—	20
Claude Opus 5.5 (batch)	Flagship	79elo	$2.00 – $10.00	—	—	40
Grok 4.7	Flagship	78	$2.00 – $6.00	—	—	39
Qwen3.8 Omni Flash	Fast	—	$0.150 – $0.470	—	—	—
GLM 5.3 FlashX	Balanced	—	$0.370 – $1.25	—	—	—
DeepSeek V4.1 Flash (batch)	Fast	—	$0.112 – $0.336	—	—	—
DeepSeek V4.1 Flash	Fast	—	$0.044 – $0.630	—	—	—
GPT-6 Astra	Balanced	—	$10.00 – $50.00	—	—	—
GPT-6 Astra (batch)	Balanced	—	$5.00 – $25.00	—	—	—
GPT-6 Astra Pro	Balanced	—	$10.00 – $50.00	—	—	—
GPT-6 Astra Pro (batch)	Balanced	—	$5.00 – $25.00	—	—	—
Qwen3.8 Max (0902)	Flagship	74elo	$2.00 – $6.00	—	—	37
Gemini 3.8 Flash	Fast	77elo	$0.750 – $3.75	—	—	103
Gemini 3.8 Flash (batch)	Fast	77elo	$0.375 – $1.88	—	—	205
Claude Fable 5.1	Flagship	95	$10.00 – $50.00	—	—	9.5
Claude Fable 5.1 (batch)	Flagship	95	$5.00 – $25.00	—	—	19
Granite 4.2 8B	Balanced	—	$0.060 – $0.250	—	—	—
Hy4 preview	Balanced	—	$0.834 – $2.50	—	—	—
Qwen3.8 Flash	Fast	—	$0.150 – $0.470	—	—	—
GLM 5.3 Flash (batch)	Fast	72elo	$0.060 – $0.200	—	—	1.2k
GLM 5.3 Flash	Fast	72elo	$0.026 – $0.900	—	—	2.8k
DeepSeek V4 Flash Vision Exp	Fast	—	$0.216 – $0.647	—	—	—
Hy-MT2-1.8B	Balanced	—	$0.044 – $0.177	—	—	—
Hy-MT2-30B-A3B	Balanced	—	$0.074 – $0.295	—	—	—
Hy-MT2-7B	Balanced	—	$0.074 – $0.295	—	—	—
GLM 5.3 (batch)	Balanced	—	$0.450 – $2.00	—	—	—
GLM 5.3	Balanced	—	$0.079 – $4.80	—	—	—
Qwen3.8 27B	Balanced	—	$0.040 – $2.30	—	—	—
Gemini 3.7 Flash	Fast	75elo	$0.750 – $3.75	—	—	100
Gemini 3.7 Flash (batch)	Fast	75elo	$0.375 – $1.88	—	—	200
Seed 2.1 Turbo	Balanced	—	$0.500 – $2.50	—	—	—
Qwen3.8 2.4T A95B	Balanced	—	$2.00 – $6.00	—	—	—
Seed-2.0-Code	Balanced	—	$0.500 – $3.00	—	—	—
DeepSeek V4 Pro 0813	Balanced	—	$0.660 – $1.98	—	—	—
Grok 4.6	Flagship	78	$2.00 – $6.00	—	—	39
Nemotron 3.5 Lightning	Balanced	—	$0.070 – $0.200	—	—	—
Solar Pro 4	Balanced	—	$0.090 – $0.360	—	—	—
DeepSeek V4 Flash 0731	Fast	—	$0.016 – $0.640	—	—	—
Qwen3.7 Flash	Fast	—	$0.030 – $0.130	—	—	—
Claude Opus 5	Flagship	76elo	$5.00 – $25.00	—	—	15
Claude Opus 5 (batch)	Flagship	76elo	$2.50 – $12.50	—	—	30
Gemini 3.6 Flash	Fast	74elo	$0.750 – $3.75	—	—	99
Gemini 3.6 Flash (batch)	Fast	74elo	$0.375 – $1.88	—	—	197
Gemini 3.5 Flash Lite	Fast	73elo	$0.300 – $2.50	—	—	243
Gemini 3.5 Flash Lite (batch)	Fast	73elo	$0.150 – $1.25	—	—	487
Kimi K3 (batch)	Balanced	—	$2.28 – $11.40	—	—	—
Kimi K3	Balanced	—	$0.730 – $13.50	—	—	—
GPT-5.6 Luna Pro	Flagship	78	$0.200 – $1.20	—	—	390
GPT-5.6 Luna Pro (batch)	Flagship	78	$0.100 – $0.600	—	—	780
GPT-5.6 Luna	Flagship	78	$0.200 – $1.20	—	—	390
GPT-5.6 Luna (batch)	Flagship	78	$0.100 – $0.600	—	—	780
GPT-5.6 Terra Pro	Flagship	78	$2.00 – $12.00	—	—	39
GPT-5.6 Terra Pro (batch)	Flagship	78	$1.00 – $6.00	—	—	78
GPT-5.6 Terra	Flagship	78	$2.00 – $12.00	—	—	39
GPT-5.6 Terra (batch)	Flagship	78	$1.00 – $6.00	—	—	78
GPT-5.6 Sol Pro	Flagship	78	$2.00 – $10.00	—	—	39
GPT-5.6 Sol Pro (batch)	Flagship	78	$1.00 – $5.00	—	—	78
GPT-5.6 Sol	Flagship	78	$2.00 – $10.00	—	—	39
GPT-5.6 Sol (batch)	Flagship	78	$1.00 – $5.00	—	—	78
Grok 4.5	Flagship	70elo	$2.00 – $6.00	—	—	35
Hy3	Balanced	—	$0.132 – $0.528	—	—	—
Claude Sonnet 5	Balanced	85	$2.00 – $10.00	—	—	43
Claude Sonnet 5 (batch)	Balanced	85	$1.00 – $5.00	—	—	85
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)	Fast	—	$0.250 – $1.50	—	—	—
Nano Banana 2 (Gemini 3.1 Flash Image)	Fast	—	$0.500 – $3.00	—	—	—
Nano Banana Pro (Gemini 3 Pro Image)	Fast	74elo	$2.00 – $12.00	—	—	37
GLM 5.2	Balanced	—	$0.060 – $7.00	—	—	—
Kimi K2.7 Code	Balanced	—	$0.671 – $3.35	—	—	—
Claude Fable 5	Flagship	95	$10.00 – $50.00	—	—	9.5
Claude Fable 5 (batch)	Flagship	95	$5.00 – $25.00	—	—	19
Nemotron 3.5 Content Safety	Balanced	—	$0.200 – $0.200	—	—	—
Nemotron 3 Ultra	Flagship	—	$0.600 – $2.40	—	—	—
Qwen3.7 Plus	Balanced	—	$0.320 – $1.28	—	—	—
MiniMax M3	Balanced	—	$0.300 – $1.20	—	—	—
Claude Opus 4.8	Flagship	90	$5.00 – $25.00	—	—	18
Claude Opus 4.8 (batch)	Flagship	90	$2.50 – $12.50	—	—	36
Qwen3.7 Max	Flagship	72elo	$1.48 – $4.42	—	—	49
Grok Build 0.1	Balanced	50	$1.00 – $2.00	—	—	50
Gemini 3.5 Flash	Fast	73elo	$1.50 – $9.00	—	—	49
Gemini 3.5 Flash (batch)	Fast	73elo	$0.750 – $4.50	—	—	97
Gemini 3.1 Flash Lite	Fast	—	$0.250 – $1.50	—	—	—
Gemini 3.1 Flash Lite (batch)	Fast	—	$0.125 – $0.750	—	—	—
GPT Chat Latest	Balanced	—	$5.00 – $30.00	—	—	—
Grok 4.3	Flagship	78	$1.25 – $2.50	—	—	62
Grok 4.3 (batch)	Flagship	78	$1.00 – $2.00	—	—	78
Mistral Medium 3.5	Balanced	48	$1.50 – $7.50	—	—	32
Mistral Medium 3.5 (batch)	Balanced	48	$0.750 – $3.75	—	—	64
Qwen3.5 Plus 2026-04-20	Balanced	—	$0.300 – $1.80	—	—	—
Qwen3.6 Flash	Fast	—	$0.188 – $1.13	—	—	—
Qwen3.6 35B A3B	Balanced	—	$0.100 – $0.950	—	—	—
Qwen3.6 27B	Balanced	—	$0.320 – $3.20	—	—	—
GPT-5.5 Pro	Flagship	74elo	$30.00 – $180.00	—	—	2.5
GPT-5.5 Pro (batch)	Flagship	74elo	$15.00 – $90.00	—	—	4.9
GPT-5.5	Flagship	74elo	$5.00 – $30.00	—	—	15
GPT-5.5 (batch)	Flagship	74elo	$2.50 – $15.00	—	—	30
DeepSeek V4 Pro 0423	Balanced	—	$0.955 – $1.91	—	—	—
DeepSeek V4 Flash 0423	Fast	—	$0.050 – $1.28	—	—	—
Hy3 preview	Balanced	—	$0.180 – $0.600	—	—	—
GPT-5.4 Image 2	Flagship	72elo	$8.00 – $15.00	—	—	9.0
Kimi K2.6	Balanced	—	$0.650 – $3.41	—	—	—
Claude Opus 4.7	Flagship	88	$5.00 – $25.00	—	—	18
Claude Opus 4.7 (batch)	Flagship	88	$2.50 – $12.50	—	—	35
GLM 5.1	Balanced	—	$0.966 – $3.04	—	—	—
Gemma 4 26B A4B	Balanced	—	$0.090 – $0.300	—	—	—
Gemma 4 31B	Balanced	—	$0.090 – $0.340	—	—	—
Qwen3.6 Plus	Balanced	—	$0.325 – $1.95	—	—	—
GLM 5V Turbo	Balanced	—	$1.20 – $4.00	—	—	—
Trinity Large Thinking	Reasoning	—	$0.250 – $0.800	—	—	—
Grok 4.20 Multi-Agent	Flagship	78	$1.25 – $2.50	—	—	62
Grok 4.20	Flagship	78	$1.25 – $2.50	—	—	62
Reka Edge	Balanced	—	$0.100 – $0.100	—	—	—
MiniMax M2.7	Balanced	—	$0.300 – $1.20	—	—	—
GPT-5.4 Nano	Fast	72elo	$0.200 – $1.25	—	—	360
GPT-5.4 Nano (batch)	Fast	72elo	$0.100 – $0.625	—	—	720
GPT-5.4 Mini	Fast	72elo	$0.750 – $4.50	—	—	96
GPT-5.4 Mini (batch)	Fast	72elo	$0.375 – $2.25	—	—	192
Mistral Small 4	Balanced	42	$0.150 – $0.600	—	—	280
Mistral Small 4 (batch)	Balanced	42	$0.075 – $0.300	—	—	560
GLM 5 Turbo	Balanced	—	$1.20 – $4.00	—	—	—
Nemotron 3 Super	Balanced	—	$0.080 – $0.450	—	—	—
Seed-2.0-Lite	Fast	—	$0.250 – $2.00	—	—	—
Qwen3.5-9B	Balanced	—	$0.100 – $0.150	—	—	—
GPT-5.4 Pro	Flagship	72elo	$30.00 – $180.00	—	—	2.4
GPT-5.4 Pro (batch)	Flagship	72elo	$15.00 – $90.00	—	—	4.8
GPT-5.4	Flagship	72elo	$2.50 – $15.00	—	—	29
GPT-5.4 (batch)	Flagship	72elo	$1.25 – $7.50	—	—	58
Gemini 3.1 Flash Lite Preview	Fast	—	$0.250 – $1.50	—	—	—
Seed-2.0-Mini	Fast	—	$0.100 – $0.400	—	—	—
Nano Banana 2 (Gemini 3.1 Flash Image Preview)	Fast	—	$0.500 – $3.00	—	—	—
Qwen3.5-35B-A3B	Balanced	—	$0.080 – $0.750	—	—	—
Qwen3.5-27B	Balanced	—	$0.260 – $2.60	—	—	—
Qwen3.5-122B-A10B	Balanced	—	$0.260 – $2.08	—	—	—
Qwen3.5-Flash	Fast	—	$0.065 – $0.260	—	—	—
Gemini 3.1 Pro Preview Custom Tools	Flagship	75elo	$2.00 – $12.00	—	—	38
GPT-5.3-Codex	Flagship	78	$1.75 – $14.00	—	—	45
Gemini 3.1 Pro Preview	Flagship	75elo	$2.00 – $12.00	—	—	38
Gemini 3.1 Pro Preview (batch)	Flagship	75elo	$1.00 – $6.00	—	—	75
Claude Sonnet 4.6	Balanced	79	$3.00 – $15.00	—	—	26
Claude Sonnet 4.6 (batch)	Balanced	79	$1.50 – $7.50	—	—	53
Qwen3.5 Plus 2026-02-15	Balanced	—	$0.260 – $1.56	—	—	—
Qwen3.5 397B A17B	Balanced	—	$0.550 – $3.50	—	—	—
MiniMax M2.5	Balanced	—	$0.270 – $1.08	—	—	—
GLM 5	Balanced	—	$0.600 – $1.92	—	—	—
Claude Opus 4.6	Flagship	86	$5.00 – $25.00	—	—	17
Claude Opus 4.6 (batch)	Flagship	86	$2.50 – $12.50	—	—	34
Qwen3 Coder Next	Balanced	—	$0.120 – $0.800	—	—	—
Kimi K2.5	Balanced	—	$0.500 – $2.50	—	—	—
Solar Pro 3	Balanced	—	$0.150 – $0.600	—	—	—
MiniMax M2-her	Balanced	—	$0.300 – $1.20	—	—	—
Palmyra X5	Balanced	—	$0.600 – $6.00	—	—	—
GPT Audio	Balanced	—	$2.50 – $10.00	—	—	—
GPT Audio Mini	Fast	—	$0.600 – $2.40	—	—	—
GLM 4.7 Flash	Fast	—	$0.061 – $0.400	—	—	—
GPT-5.2-Codex	Flagship	78	$1.75 – $14.00	—	—	45
Seed 1.6 Flash	Fast	—	$0.075 – $0.300	—	—	—
Seed 1.6	Balanced	—	$0.250 – $2.00	—	—	—
MiniMax M2.1	Balanced	—	$0.300 – $1.20	—	—	—
GLM 4.7	Balanced	—	$0.600 – $2.20	—	—	—
Gemini 3 Flash Preview	Fast	72elo	$0.500 – $3.00	—	—	144
Gemini 3 Flash Preview (batch)	Fast	72elo	$0.250 – $1.50	—	—	288
Nemotron 3 Nano 30B A3B	Fast	—	$0.060 – $0.240	—	—	—
GPT-5.2 Chat	Flagship	78	$1.75 – $14.00	—	—	45
GPT-5.2 Pro	Flagship	78	$21.00 – $168.00	—	—	3.7
GPT-5.2 Pro (batch)	Flagship	78	$10.50 – $84.00	—	—	7.4
GPT-5.2	Flagship	78	$1.75 – $14.00	—	—	45
GPT-5.2 (batch)	Flagship	78	$0.875 – $7.00	—	—	89
Devstral 2 2512	Balanced	—	$0.400 – $2.00	—	—	—
GLM 4.6V	Balanced	—	$0.300 – $0.900	—	—	—
GPT-5.1-Codex-Max	Flagship	78	$1.25 – $10.00	—	—	62
Nova 2 Lite	Fast	—	$0.300 – $2.50	—	—	—
Ministral 3 14B 2512	Balanced	—	$0.200 – $0.200	—	—	—
Ministral 3 8B 2512	Balanced	35	$0.150 – $0.150	—	—	233
Ministral 3 8B 2512 (batch)	Balanced	35	$0.075 – $0.075	—	—	467
Ministral 3 3B 2512	Balanced	28	$0.100 – $0.100	—	—	280
Mistral Large 3 2512	Flagship	50	$0.500 – $1.50	—	—	100
Mistral Large 3 2512 (batch)	Flagship	50	$0.250 – $0.750	—	—	200
DeepSeek V3.2	Balanced	65	$0.259 – $0.800	—	—	251
Claude Opus 4.5	Flagship	84	$5.00 – $25.00	—	—	17
Claude Opus 4.5 (batch)	Flagship	84	$2.50 – $12.50	—	—	34
Nano Banana Pro (Gemini 3 Pro Image Preview)	Fast	74elo	$2.00 – $12.00	—	—	37
GPT-5.1	Flagship	78	$1.25 – $10.00	—	—	62
GPT-5.1 (batch)	Flagship	78	$0.625 – $5.00	—	—	125
GPT-5.1-Codex	Flagship	78	$1.25 – $10.00	—	—	62
GPT-5.1-Codex-Mini	Fast	78	$0.250 – $2.00	—	—	312
Kimi K2 Thinking	Reasoning	—	$0.600 – $2.50	—	—	—
Nova Premier 1.0	Balanced	—	$2.50 – $12.50	—	—	—
Sonar Pro Search	Balanced	—	$3.00 – $15.00	—	—	—
Voxtral Small 24B 2507	Balanced	—	$0.100 – $0.300	—	—	—
gpt-oss-safeguard-20b	Balanced	—	$0.075 – $0.300	—	—	—
MiniMax M2	Balanced	—	$0.300 – $1.20	—	—	—
Granite 4.0 Micro	Fast	—	$0.017 – $0.112	—	—	—
GPT-5 Image Mini	Fast	78	$2.50 – $2.00	—	—	31
Claude Haiku 4.5	Fast	66	$1.00 – $5.00	—	—	66
Claude Haiku 4.5 (batch)	Fast	66	$0.500 – $2.50	—	—	132
Qwen3 VL 8B Instruct	Balanced	—	$0.250 – $0.750	—	—	—
GPT-5 Image	Flagship	78	$10.00 – $10.00	—	—	7.8
Nano Banana (Gemini 2.5 Flash Image)	Fast	66	$0.300 – $2.50	—	—	220
Qwen3 VL 30B A3B Thinking	Reasoning	—	$0.290 – $1.00	—	—	—
Qwen3 VL 30B A3B Instruct	Balanced	—	$0.150 – $0.600	—	—	—
GPT-5 Pro	Flagship	78	$15.00 – $120.00	—	—	5.2
GPT-5 Pro (batch)	Flagship	78	$7.50 – $60.00	—	—	10
GLM 4.6	Balanced	—	$0.500 – $2.00	—	—	—
Claude Sonnet 4.5	Balanced	76	$3.00 – $15.00	—	—	25
Claude Sonnet 4.5 (batch)	Balanced	76	$1.50 – $7.50	—	—	51
DeepSeek V3.2 Exp	Balanced	65	$0.270 – $0.410	—	—	241
Qwen3 VL 235B A22B Instruct	Balanced	—	$0.210 – $1.90	—	—	—
DeepSeek V3.1 Terminus	Balanced	65	$0.270 – $1.00	—	—	241
Qwen3 Coder Flash	Fast	—	$0.195 – $0.975	—	—	—
Qwen3 Next 80B A3B Thinking	Reasoning	—	$0.150 – $1.20	—	—	—
Qwen3 Next 80B A3B Instruct	Balanced	—	$0.100 – $1.10	—	—	—
Kimi K2 0905	Balanced	—	$0.600 – $2.50	—	—	—
Hermes 4 405B	Flagship	—	$1.00 – $3.00	—	—	—
DeepSeek V3.1	Balanced	65	$0.250 – $0.950	—	—	260
Mistral Medium 3.1	Balanced	48	$0.400 – $2.00	—	—	120
Mistral Medium 3.1 (batch)	Balanced	48	$0.200 – $1.00	—	—	240
GLM 4.5V	Balanced	—	$0.600 – $1.80	—	—	—
GPT-5	Flagship	78	$1.25 – $10.00	—	—	62
GPT-5 (batch)	Flagship	78	$0.625 – $5.00	—	—	125
GPT-5 Mini	Fast	68	$0.250 – $2.00	—	—	272
GPT-5 Mini (batch)	Fast	68	$0.125 – $1.00	—	—	544
GPT-5 Nano	Fast	55	$0.050 – $0.400	—	—	1.1k
GPT-5 Nano (batch)	Fast	55	$0.025 – $0.200	—	—	2.2k
gpt-oss-120b	Balanced	—	$0.150 – $0.600	—	—	—
gpt-oss-120b (batch)	Balanced	—	$0.030 – $0.136	—	—	—
gpt-oss-20b (batch)	Balanced	—	$0.024 – $0.112	—	—	—
gpt-oss-20b	Balanced	—	$0.018 – $0.090	—	—	—
Claude Opus 4.1	Flagship	80	$15.00 – $75.00	—	—	5.3
Claude Opus 4.1 (batch)	Flagship	80	$7.50 – $37.50	—	—	11
Codestral 2508	Balanced	50	$0.300 – $0.900	—	—	167
Codestral 2508 (batch)	Balanced	50	$0.150 – $0.450	—	—	333
Qwen3 Coder 30B A3B Instruct	Balanced	—	$0.070 – $0.280	—	—	—
Qwen3 30B A3B Instruct 2507	Balanced	—	$0.100 – $0.300	—	—	—
GLM 4.5	Balanced	—	$0.600 – $2.20	—	—	—
GLM 4.5 Air	Balanced	—	$0.130 – $0.850	—	—	—
Qwen3 235B A22B Thinking 2507	Reasoning	—	$0.450 – $3.50	—	—	—
Qwen3 Coder 480B A35B	Balanced	—	$0.300 – $1.00	—	—	—
UI-TARS 7B	Balanced	—	$0.100 – $0.200	—	—	—
Gemini 2.5 Flash Lite	Fast	55	$0.100 – $0.400	—	—	550
Gemini 2.5 Flash Lite (batch)	Fast	55	$0.050 – $0.200	—	—	1.1k
Qwen3 235B A22B Instruct 2507	Balanced	—	$0.090 – $0.550	—	—	—
Kimi K2 0711	Balanced	—	$0.570 – $2.30	—	—	—
Hunyuan A13B Instruct	Balanced	—	$0.140 – $0.570	—	—	—
Mistral Small 3.2 24B	Balanced	42	$0.094 – $0.250	—	—	448
MiniMax M1	Balanced	—	$0.550 – $2.20	—	—	—
Gemini 2.5 Flash	Fast	66	$0.300 – $2.50	—	—	220
Gemini 2.5 Flash (batch)	Fast	66	$0.150 – $1.25	—	—	440
Gemini 2.5 Pro	Flagship	76	$1.25 – $10.00	—	—	61
Gemini 2.5 Pro (batch)	Flagship	76	$0.625 – $5.00	—	—	122
o3 Pro	Reasoning	—	$20.00 – $80.00	—	—	—
Gemini 2.5 Pro Preview 06-05	Flagship	76	$1.25 – $10.00	—	—	61
R1 0528	Reasoning	73	$0.500 – $2.15	—	—	146
Claude Sonnet 4	Balanced	72	$3.00 – $15.00	—	—	24
Mistral Medium 3	Balanced	48	$0.400 – $2.00	—	—	120
Llama Guard 4 12B	Balanced	—	$0.180 – $0.180	—	—	—
Qwen3 30B A3B	Balanced	—	$0.120 – $0.500	—	—	—
Qwen3 14B	Balanced	—	$0.120 – $0.240	—	—	—
Qwen3 32B	Balanced	—	$0.080 – $0.280	—	—	—
o4 Mini High	Reasoning	75	$1.10 – $4.40	—	—	68
o3	Reasoning	82	$2.00 – $8.00	—	—	41
o3 (batch)	Reasoning	—	$1.00 – $4.00	—	—	—
o4 Mini	Reasoning	75	$1.10 – $4.40	—	—	68
o4 Mini (batch)	Reasoning	75	$0.550 – $2.20	—	—	136
GPT-4.1	Flagship	62	$2.00 – $8.00	—	—	31
GPT-4.1 (batch)	Flagship	62	$1.00 – $4.00	—	—	62
GPT-4.1 Mini	Fast	52	$0.400 – $1.60	—	—	130
GPT-4.1 Mini (batch)	Fast	52	$0.200 – $0.800	—	—	260
GPT-4.1 Nano	Fast	62	$0.100 – $0.400	—	—	620
GPT-4.1 Nano (batch)	Fast	62	$0.050 – $0.200	—	—	1.2k
Llama 4 Maverick	Balanced	62	$0.188 – $0.652	—	—	331
Llama 4 Scout	Balanced	55	$0.180 – $0.590	—	—	306
DeepSeek V3 0324	Balanced	65	$0.290 – $1.14	—	—	224
o1-pro	Reasoning	—	$150.00 – $600.00	—	—	—
Mistral Small 3.1 24B	Balanced	42	$0.351 – $0.555	—	—	120
Gemma 3 4B	Balanced	—	$0.050 – $0.100	—	—	—
Gemma 3 12B	Balanced	—	$0.050 – $0.150	—	—	—
Command A	Balanced	—	$2.50 – $10.00	—	—	—
Reka Flash 3	Fast	—	$0.100 – $0.200	—	—	—
Gemma 3 27B	Balanced	—	$0.080 – $0.450	—	—	—
Sonar Reasoning Pro	Reasoning	—	$2.00 – $8.00	—	—	—
Sonar Pro	Balanced	—	$3.00 – $15.00	—	—	—
Sonar Deep Research	Balanced	—	$2.00 – $8.00	—	—	—
Saba	Balanced	—	$0.200 – $0.600	—	—	—
o3 Mini High	Reasoning	72	$1.10 – $4.40	—	—	65
Qwen2.5 VL 72B Instruct	Balanced	—	$0.800 – $1.00	—	—	—
Qwen-Plus	Balanced	—	$0.260 – $0.780	—	—	—
o3 Mini	Reasoning	72	$1.10 – $4.40	—	—	65
o3 Mini (batch)	Reasoning	72	$0.550 – $2.20	—	—	131
Mistral Small 3	Balanced	42	$0.050 – $0.080	—	—	840
Sonar	Balanced	—	$1.00 – $1.00	—	—	—
R1	Reasoning	73	$0.700 – $2.50	—	—	104
MiniMax-01	Balanced	—	$0.200 – $1.10	—	—	—
Phi 4	Balanced	—	$0.070 – $0.140	—	—	—
DeepSeek V3	Balanced	60	$0.320 – $0.890	—	—	188
o1	Reasoning	78	$15.00 – $60.00	—	—	5.2
Command R7B (12-2024)	Balanced	—	$0.037 – $0.150	—	—	—
Llama 3.3 70B Instruct	Balanced	52	$0.590 – $0.790	—	—	88
Nova Lite 1.0	Fast	—	$0.060 – $0.240	—	—	—
Nova Micro 1.0	Fast	—	$0.035 – $0.140	—	—	—
Nova Pro 1.0	Balanced	—	$0.800 – $3.20	—	—	—
GPT-4o (2024-11-20)	Balanced	64	$2.50 – $10.00	—	—	26
Mistral Large 2407	Flagship	50	$2.00 – $6.00	—	—	25
Qwen2.5 Coder 32B Instruct	Balanced	58	$0.660 – $1.00	—	—	88
Qwen2.5 7B Instruct	Balanced	36	$0.100 – $0.200	—	—	360
Llama 3.2 3B Instruct	Balanced	22	$0.050 – $0.330	—	—	440
Llama 3.2 1B Instruct	Balanced	15	$0.027 – $0.201	—	—	556
Qwen2.5 72B Instruct	Balanced	53	$0.360 – $0.400	—	—	147
Command R+ (08-2024)	Balanced	—	$2.50 – $10.00	—	—	—
Command R (08-2024)	Balanced	—	$0.150 – $0.600	—	—	—
Hermes 3 70B Instruct	Balanced	—	$0.700 – $0.700	—	—	—
Hermes 3 405B Instruct	Flagship	—	$1.00 – $1.00	—	—	—
GPT-4o (2024-08-06)	Balanced	64	$2.50 – $10.00	—	—	26
Llama 3.1 70B Instruct	Balanced	47	$0.400 – $0.400	—	—	118
Llama 3.1 8B Instruct	Balanced	30	$0.050 – $0.080	—	—	600
Mistral Nemo	Balanced	38	$0.029 – $0.030	—	—	1.3k
GPT-4o-mini	Fast	51	$0.150 – $0.600	—	—	340
GPT-4o-mini (batch)	Fast	51	$0.075 – $0.300	—	—	680
GPT-4o-mini (2024-07-18)	Fast	51	$0.150 – $0.600	—	—	340
Gemma 2 27B	Balanced	—	$0.650 – $0.650	—	—	—
GPT-4o	Balanced	64	$2.50 – $10.00	—	—	26
GPT-4o (batch)	Balanced	64	$1.25 – $5.00	—	—	51
GPT-4o (2024-05-13)	Balanced	64	$5.00 – $15.00	—	—	13
Mixtral 8x22B Instruct	Balanced	40	$2.00 – $6.00	—	—	20
WizardLM-2 8x22B	Balanced	—	$0.620 – $0.620	—	—	—
GPT-4 Turbo	Balanced	58	$10.00 – $30.00	—	—	5.8
GPT-4 Turbo (batch)	Balanced	58	$5.00 – $15.00	—	—	12
Mistral Large	Flagship	50	$2.00 – $6.00	—	—	25
GPT-3.5 Turbo (older v0613)	Balanced	35	$1.00 – $2.00	—	—	35
GPT-3.5 Turbo Instruct	Balanced	35	$1.50 – $2.00	—	—	23
GPT-3.5 Turbo 16k	Balanced	35	$3.00 – $4.00	—	—	12
GPT-4	Balanced	58	$30.00 – $60.00	—	—	1.9
GPT-3.5 Turbo	Balanced	35	$0.500 – $1.50	—	—	70
GPT-3.5 Turbo (batch)	Balanced	35	$0.250 – $0.750	—	—	140

Approximation: ~4 chars / 1 token · Rates shown per 1M tokens · Pricing is live via OpenRouter — confirm with provider before billing decisions.

Quick

354 models

↑ Type any amount — results update live

~4 chars ≈ 1 token · rates per 1M tokens · live via OpenRouter — confirm with provider before billing.

301+Models tracked

DailyPrices updated

FreeNo sign-up

Free, instant cost estimates for every major AI model. Convert money, tokens, and characters across Claude, GPT-4o, Gemini, Llama, DeepSeek, Grok, and Mistral — with live pricing from OpenRouter.

What is an AI token calculator? An AI token calculator converts between dollars, token counts, and characters using live API model rates. It answers two questions developers ask before shipping with an LLM: how much will this prompt cost? and how many tokens does my budget buy?

Current AI API pricing (October 2026): Llama 3.1 8B costs $0.05/1M input tokens; Gemini 2.0 Flash costs $0.10/1M; GPT-4o mini costs $0.15/1M; Claude Haiku 4 costs $0.25/1M. Input and output tokens have separate rates. For example, 1,000 input tokens at an illustrative $3/1M input rate cost $0.003 before any output or other charges. Use the calculator above to estimate both parts across 301+ tracked models.

Catalog built 2026-10-12 · Check the provider price sheet for your exact model and route

What Are AI Tokens?

A token is a unit that AI language models use to process text. Tokens may be words, fragments, punctuation or spaces. Their count varies by text and tokenizer.

Every AI API — including Claude, GPT-4o, and Gemini — charges by the token. You pay for the text you send (input tokens) and the text the model generates (output tokens). Understanding tokens is the key to predicting and controlling your AI costs.

Read the full guide →

How AI Token Pricing Works

AI models are priced by the million tokens — written as $/1M tokens. The two numbers you always see are:

InputThe text you send — your prompt, system instructions, and conversation history.
OutputThe text the model generates. Usually 3–5× more expensive than input, because generating tokens requires more compute than reading them.

A typical 1,000-token request (about 750 words of prompt) with Claude Sonnet 4 costs $0.003 — less than a third of a cent. At scale, though, those fractions add up fast.

Read the full pricing guide →

Cheapest AI Models in 2026

Ranked by input token price. All prices per 1 million tokens.

Model	Provider	Input / 1M	Output / 1M	Context
DeepSeek V4 Flash 0731	DeepSeek	$0.016	$0.640	1M
Granite 4.0 Micro	IBM	$0.017	$0.112	131K
gpt-oss-20b	OpenAI	$0.018	$0.090	131K
GLM 5.3 Flash	Zhipu AI	$0.023	$1.20	1M
Llama 3.2 1B	Meta	$0.027	$0.201	60K
Mistral Nemo	Mistral	$0.029	$0.030	131K

Prices are approximate and may change. See full comparison →

Token Calculation Examples

1,000 words of English text

~1,333 tokens

~4 chars per token

A standard email (150 words)

~200 tokens

under $0.001 on most models

A 10-page PDF (2,500 words)

~3,333 tokens

$0.01 with Claude Sonnet 4

An entire novel (80,000 words)

~107K tokens

fits in most flagship models

A full codebase (100K lines)

~300K+ tokens

needs 200K+ context window

1 million tokens budget at $1

~750K words

with Gemini 2.0 Flash

Want more? See the full token reference guide →

Browse All AI Models

Detailed pricing pages for every major model — with context windows, strengths, use cases, and cost examples.

Claude Opus 5Anthropic$5.00/1M in Claude Sonnet 5Anthropic$2.00/1M in Claude Opus 4Anthropic$15.00/1M in Claude Sonnet 4Anthropic$3.00/1M in Claude Haiku 4Anthropic$0.250/1M in Claude 3.5 SonnetAnthropic$3.00/1M in Claude 3 HaikuAnthropic$0.250/1M in Claude 3.7 SonnetAnthropic$3.00/1M in Claude 3.5 HaikuAnthropic$0.800/1M in

Frequently Asked Questions

Related Tools & Guides

Words → Tokens ConverterPaste any text and see the token count instantly.Token → USD CalculatorConvert a raw token count to dollars for any model.Cheapest AI Models 2026Ranked list of the most affordable LLMs available via API.What Are AI Tokens?A clear explanation of how tokens work and why they matter.Cost per Successful TaskCompare model spending alongside pass rate and retries.Artificial Analysis vs ArenaWhat each benchmark measures and how to use it.OpenAI API Pricing GuideCalculate a real request using the current price sheet.Claude API Pricing GuidePrice a Claude request and account for cache and batch use.AI API Budget WorksheetForecast monthly spend with request volume and retries.How AI API Pricing WorksInput, output, and other billing categories explained.

A branchingAI chat canvas.

Why settle forone answer?