LLM Price Calculator

Compare LLM API pricing across Claude, GPT, Gemini, and GLM. Calculate per-call costs, set budgets, and estimate multi-turn chain costs with prompt caching.

Input TokensTokens you send to the model per API call - your prompt, system instructions, and any context.

Output TokensTokens the model generates in its response. Usually costs 3-5x more than input tokens.

Reasoning TokensInternal thinking tokens used by reasoning models (o3, o4-mini, Claude with extended thinking). Billed at the output token rate. Set to 0 for non-reasoning models.

API CallsNumber of requests you'll make. Multiply per-call cost by this to get the total.

Cache Hit RateHow often the model reuses cached input tokens instead of reprocessing them. Cached tokens cost 5-10x less. The first call is never cached.

1,000 in + 500 out × 1,000 calls61 models

Provider

Input

#	Provider	Model	Context	In/M	Out/M	Per call	Total
58	Anthropic	thinking max output 128K	1M/128K	$5	$25	$0.018	$17.50
59	Anthropic	thinking max output 128K	200K/128K	$5	$25	$0.018	$17.50
56	Anthropic	thinking max output 64K	1M/64K	$3	$15	$0.010	$10.50
57	Anthropic	thinking max output 64K	200K/64K	$3	$15	$0.010	$10.50
36	Anthropic	max output 64K	200K/64K	$1	$5	$0.0035	$3.50
60	OpenAI	thinking max output 128K	1.1M/128K	$5	$30	$0.020	$20.00
55	OpenAI	thinking max output 128K	1.1M/128K	$2.5	$15	$0.010	$10.00
34	OpenAI	thinking max output 128K	400K/128K	$0.75	$4.5	$0.0030	$3.00
15	OpenAI	thinking max output 128K	400K/128K	$0.2	$1.25	$0.0008	$0.825
53	OpenAI	thinking max output 128K	400K/128K	$1.75	$14	$0.0088	$8.75
46	OpenAI	thinking max output 128K	400K/128K	$1.25	$10	$0.0063	$6.25
47	OpenAI	thinking max output 128K	400K/128K	$1.25	$10	$0.0063	$6.25
20	OpenAI	thinking max output 128K	400K/128K	$0.25	$2	$0.0013	$1.25
3	OpenAI	thinking max output 128K	400K/128K	$0.05	$0.4	$0.0003	$0.250
43	OpenAI	max output 32K	1M/32K	$2	$8	$0.0060	$6.00
19	OpenAI	max output 32K	1M/32K	$0.4	$1.6	$0.0012	$1.20
7	OpenAI	max output 32K	1M/32K	$0.1	$0.4	$0.0003	$0.300
50	OpenAI	max output 16K	128K/16K	$2.5	$10	$0.0075	$7.50
10	OpenAI	max output 16K	128K/16K	$0.15	$0.6	$0.0005	$0.450
61	OpenAI	thinking max output 100K	200K/100K	$20	$80	$0.060	$60.00
44	OpenAI	thinking max output 100K	200K/100K	$2	$8	$0.0060	$6.00
35	OpenAI	thinking max output 100K	200K/100K	$1.1	$4.4	$0.0033	$3.30
45	Google	thinking max output 65K	1M/65K	$1.5	$9	$0.0060	$6.00
52	Google	max output 65K	1M/65K	$2	$12	$0.0080	$8.00
18	Google	max output 65K	1M/65K	$0.25	$1.5	$0.0010	$1.00
27	Google	thinking max output 65K	1M/65K	$0.5	$3	$0.0020	$2.00
48	Google	thinking max output 65K	1M/65K	$1.25	$10	$0.0063	$6.25
24	Google	thinking max output 65K	1M/65K	$0.3	$2.5	$0.0016	$1.55
8	Google	max output 65K	1M/65K	$0.1	$0.4	$0.0003	$0.300
9	Google	max output 8.2K	1M/8.2K	$0.1	$0.4	$0.0003	$0.300
16	DeepSeek	thinking max output 384K	1M/384K	$0.43	$0.87	$0.0009	$0.865
5	DeepSeek	thinking max output 384K	1M/384K	$0.14	$0.28	$0.0003	$0.280
31	xAI	thinking max output 30K	1M/30K	$1.25	$2.5	$0.0025	$2.50
32	xAI	thinking max output 30K	2M/30K	$1.25	$2.5	$0.0025	$2.50
28	xAI	max output 256K	256K/256K	$1	$2	$0.0020	$2.00
42	Mistral	thinking max output 262K	262K/262K	$1.5	$7.5	$0.0052	$5.25
21	Mistral	max output 262K	262K/262K	$0.5	$1.5	$0.0013	$1.25
22	Mistral	max output 262K	262K/262K	$0.4	$2	$0.0014	$1.40
11	Mistral	thinking max output 256K	256K/256K	$0.15	$0.6	$0.0005	$0.450
40	Mistral	thinking max output 16K	128K/16K	$2	$5	$0.0045	$4.50
23	Mistral	max output 262K	262K/262K	$0.4	$2	$0.0014	$1.40
13	Mistral	max output 4K	256K/4K	$0.3	$0.9	$0.0008	$0.750
12	Meta	max output 16K	1M/16K	$0.15	$0.6	$0.0005	$0.450
2	Meta	max output 16K	328K/16K	$0.08	$0.3	$0.0002	$0.230
41	Qwen	thinking max output 65K	262K/65K	$1.3	$7.8	$0.0052	$5.20
39	Qwen	max output 65K	262K/65K	$1.2	$6	$0.0042	$4.20
37	Qwen	max output 65K	1M/65K	$1	$5	$0.0035	$3.50
29	Qwen	thinking max output 65K	1M/65K	$0.5	$3	$0.0020	$2.00
14	Qwen	thinking max output 65K	1M/65K	$0.19	$1.12	$0.0008	$0.750
17	Xiaomi	thinking max output 131K	1M/131K	$0.435	$0.87	$0.0009	$0.870
6	Xiaomi	thinking max output 131K	1M/131K	$0.14	$0.28	$0.0003	$0.280
54	Amazon	max output 32K	1M/32K	$2.5	$12.5	$0.0088	$8.75
30	Amazon	max output 8K	300K/8K	$0.8	$3.2	$0.0024	$2.40
1	Amazon	max output 8K	300K/8K	$0.06	$0.24	$0.0002	$0.180
51	Cohere	max output 8K	256K/8K	$2.5	$10	$0.0075	$7.50
33	Zhipu AI	max output 128K	200K/128K	$1	$3.2	$0.0026	$2.60
38	Zhipu AI	max output 128K	200K/128K	$1.2	$5	$0.0037	$3.70
25	Zhipu AI	max output 128K	200K/128K	$0.6	$2.2	$0.0017	$1.70
4	Zhipu AI	max output 128K	200K/128K	$0.07	$0.4	$0.0003	$0.270
26	Zhipu AI	max output 128K	128K/128K	$0.6	$2.2	$0.0017	$1.70
49	Zhipu AI	max output 128K	128K/128K	$2.2	$8.9	$0.0067	$6.65

58thinking

Anthropic

1M / 128K|In: $5/M · Out: $25/M

Per call

$0.018

Total

$17.50

59thinking

Anthropic

200K / 128K|In: $5/M · Out: $25/M

Per call

$0.018

Total

$17.50

56thinking

Anthropic

1M / 64K|In: $3/M · Out: $15/M

Per call

$0.010

Total

$10.50

57thinking

Anthropic

200K / 64K|In: $3/M · Out: $15/M

Per call

$0.010

Total

$10.50

Anthropic

200K / 64K|In: $1/M · Out: $5/M

Per call

$0.0035

Total

$3.50

60thinking

OpenAI

1.1M / 128K|In: $5/M · Out: $30/M

Per call

$0.020

Total

$20.00

55thinking

OpenAI

1.1M / 128K|In: $2.5/M · Out: $15/M

Per call

$0.010

Total

$10.00

34thinking

OpenAI

400K / 128K|In: $0.75/M · Out: $4.5/M

Per call

$0.0030

Total

$3.00

15thinking

OpenAI

400K / 128K|In: $0.2/M · Out: $1.25/M

Per call

$0.0008

Total

$0.825

53thinking

OpenAI

400K / 128K|In: $1.75/M · Out: $14/M

Per call

$0.0088

Total

$8.75

46thinking

OpenAI

400K / 128K|In: $1.25/M · Out: $10/M

Per call

$0.0063

Total

$6.25

47thinking

OpenAI

400K / 128K|In: $1.25/M · Out: $10/M

Per call

$0.0063

Total

$6.25

20thinking

OpenAI

400K / 128K|In: $0.25/M · Out: $2/M

Per call

$0.0013

Total

$1.25

3thinking

OpenAI

400K / 128K|In: $0.05/M · Out: $0.4/M

Per call

$0.0003

Total

$0.250

OpenAI

1M / 32K|In: $2/M · Out: $8/M

Per call

$0.0060

Total

$6.00

OpenAI

1M / 32K|In: $0.4/M · Out: $1.6/M

Per call

$0.0012

Total

$1.20

OpenAI

1M / 32K|In: $0.1/M · Out: $0.4/M

Per call

$0.0003

Total

$0.300

OpenAI

128K / 16K|In: $2.5/M · Out: $10/M

Per call

$0.0075

Total

$7.50

OpenAI

128K / 16K|In: $0.15/M · Out: $0.6/M

Per call

$0.0005

Total

$0.450

61thinking

OpenAI

200K / 100K|In: $20/M · Out: $80/M

Per call

$0.060

Total

$60.00

44thinking

OpenAI

200K / 100K|In: $2/M · Out: $8/M

Per call

$0.0060

Total

$6.00

35thinking

OpenAI

200K / 100K|In: $1.1/M · Out: $4.4/M

Per call

$0.0033

Total

$3.30

45thinking

Google

1M / 65K|In: $1.5/M · Out: $9/M

Per call

$0.0060

Total

$6.00

Google

1M / 65K|In: $2/M · Out: $12/M

Per call

$0.0080

Total

$8.00

Google

1M / 65K|In: $0.25/M · Out: $1.5/M

Per call

$0.0010

Total

$1.00

27thinking

Google

1M / 65K|In: $0.5/M · Out: $3/M

Per call

$0.0020

Total

$2.00

48thinking

Google

1M / 65K|In: $1.25/M · Out: $10/M

Per call

$0.0063

Total

$6.25

24thinking

Google

1M / 65K|In: $0.3/M · Out: $2.5/M

Per call

$0.0016

Total

$1.55

Google

1M / 65K|In: $0.1/M · Out: $0.4/M

Per call

$0.0003

Total

$0.300

Google

1M / 8.2K|In: $0.1/M · Out: $0.4/M

Per call

$0.0003

Total

$0.300

16thinking

DeepSeek

1M / 384K|In: $0.43/M · Out: $0.87/M

Per call

$0.0009

Total

$0.865

5thinking

DeepSeek

1M / 384K|In: $0.14/M · Out: $0.28/M

Per call

$0.0003

Total

$0.280

31thinking

xAI

1M / 30K|In: $1.25/M · Out: $2.5/M

Per call

$0.0025

Total

$2.50

32thinking

xAI

2M / 30K|In: $1.25/M · Out: $2.5/M

Per call

$0.0025

Total

$2.50

xAI

256K / 256K|In: $1/M · Out: $2/M

Per call

$0.0020

Total

$2.00

42thinking

Mistral

262K / 262K|In: $1.5/M · Out: $7.5/M

Per call

$0.0052

Total

$5.25

Mistral

262K / 262K|In: $0.5/M · Out: $1.5/M

Per call

$0.0013

Total

$1.25

Mistral

262K / 262K|In: $0.4/M · Out: $2/M

Per call

$0.0014

Total

$1.40

11thinking

Mistral

256K / 256K|In: $0.15/M · Out: $0.6/M

Per call

$0.0005

Total

$0.450

40thinking

Mistral

128K / 16K|In: $2/M · Out: $5/M

Per call

$0.0045

Total

$4.50

Mistral

262K / 262K|In: $0.4/M · Out: $2/M

Per call

$0.0014

Total

$1.40

Mistral

256K / 4K|In: $0.3/M · Out: $0.9/M

Per call

$0.0008

Total

$0.750

What this calculator does

This calculator compares API pricing across 30+ large language models from Anthropic, OpenAI, Google, and Zhipu AI. It covers input tokens, output tokens, prompt caching discounts, and reasoning token costs - all the variables that affect your actual bill.

There are three modes. Calculate cost shows per-call and total costs for a given workload, with presets for common scenarios. Set budget flips the question - enter a dollar amount and see how many API calls each model can handle. Chain models multi-turn conversations where context accumulates. All settings are saved in the URL for bookmarking and sharing.

How LLM API pricing works

LLM APIs charge per token - roughly 0.75 English words each. Type something below to see tokens in action.

~16 tokens

9 words

GPT-5-mini

<$0.0001

Claude Haiku 4.5

<$0.0001

Claude Sonnet 4.6

<$0.0001

Claude Opus 4.6

<$0.0001

Input vs. output cost

Input and output tokens are priced separately. Output typically costs 3-5x more - a task generating long responses is significantly more expensive than one processing long inputs.

Input4K tokens

Output1K tokens

GPT-5-mini$0.0012

Claude Haiku 4.5$0.0090

Claude Sonnet 4.6$0.0270

Claude Opus 4.6$0.0450

Input Output

Prompt caching

If your application sends the same prefix on every call (system prompts, few-shot examples), caching lets you reuse it at 75-90% off. It's the single biggest cost lever for most applications.

Cache hit rate80%

GPT-5-mini

$0.0004

$0.0006

-40%

Claude Haiku 4.5

$0.0011

$0.0040

-72%

Claude Sonnet 4.6

$0.0034

$0.0120

-72%

Claude Opus 4.6

$0.0056

$0.0200

-72%

Based on 4K input tokens per call. Cached tokens use each provider's discounted rate.

Multi-turn conversations

Each API call sends the full conversation history as input, so costs grow with every turn. This is why a 10-turn conversation costs more than 10 independent calls.

Turns5

1.5K

2.5K

3.5K

4.5K

5.5K

$0.09005 turns with Claude Sonnet 4.61.5x vs independent calls

Pricing is pulled from OpenRouter across 30+ models from Anthropic, OpenAI, Google, and Zhipu AI, and updated regularly. All calculator settings save to the URL - bookmark a comparison or share it with your team.