Model API pricing

/api/model-pricing

List prices and published task-bench scores for major model APIs. Each bench is one board, and an empty cell means that board published no score.

87 models

Anthropic

Pricing

Cache reads are 0.1× input, 0.05× on Opus 5.5 and 0.025× on Fable 5.1.

Claude Fable 5.1

claude-fable-5-1

Context

Input

$10.00

Output

$50.00

Cache read

$0.25

Cache write

5 min$12.50
1 hour$20.00

Claude Fable 5

claude-fable-5

Context

Input

$10.00

Output

$50.00

Cache read

$1.00

Cache write

5 min$12.50
1 hour$20.00

Claude Opus 5.5

claude-opus-5-5

Context

Input

$4.00

Output

$20.00

Cache read

$0.20

Cache write

5 min$5.00
1 hour$8.00

Claude Opus 5

claude-opus-5

Context

Input

$5.00

Output

$25.00

Cache read

$0.50

Cache write

5 min$6.25
1 hour$10.00

Claude Opus 4.8

claude-opus-4-8

Context

Input

$5.00

Output

$25.00

Cache read

$0.50

Cache write

5 min$6.25
1 hour$10.00

Claude Opus 4.7

claude-opus-4-7

Context

Input

$5.00

Output

$25.00

Cache read

$0.50

Cache write

5 min$6.25
1 hour$10.00

Claude Opus 4.6

claude-opus-4-6

Context

Input

$5.00

Output

$25.00

Cache read

$0.50

Cache write

5 min$6.25
1 hour$10.00

Claude Sonnet 5.5

claude-sonnet-5-5

Context

Input

$2.00

Output

$10.00

Cache read

$0.20

Cache write

5 min$2.50
1 hour$4.00

Claude Sonnet 5

claude-sonnet-5

Context

Input

$2.00

Output

$10.00

Cache read

$0.20

Cache write

5 min$2.50
1 hour$4.00

Claude Sonnet 4.6

claude-sonnet-4-6

Context

Input

$3.00

Output

$15.00

Cache read

$0.30

Cache write

5 min$3.75
1 hour$6.00

Claude Haiku 4.5

claude-haiku-4-5

Context

200k

Input

$1.00

Output

$5.00

Cache read

$0.10

Cache write

5 min$1.25
1 hour$2.00

Model	Context	Input	Cache read	Cache write	Output
Claude Fable 5.1 claude-fable-5-1	1M	$10.00	$0.25	5 min$12.50 1 hour$20.00	$50.00
Claude Fable 5 claude-fable-5	1M	$10.00	$1.00	5 min$12.50 1 hour$20.00	$50.00
Claude Opus 5.5 claude-opus-5-5	1M	$4.00	$0.20	5 min$5.00 1 hour$8.00	$20.00
Claude Opus 5 claude-opus-5	1M	$5.00	$0.50	5 min$6.25 1 hour$10.00	$25.00
Claude Opus 4.8 claude-opus-4-8	1M	$5.00	$0.50	5 min$6.25 1 hour$10.00	$25.00
Claude Opus 4.7 claude-opus-4-7	1M	$5.00	$0.50	5 min$6.25 1 hour$10.00	$25.00
Claude Opus 4.6 claude-opus-4-6	1M	$5.00	$0.50	5 min$6.25 1 hour$10.00	$25.00
Claude Sonnet 5.5 claude-sonnet-5-5	1M	$2.00	$0.20	5 min$2.50 1 hour$4.00	$10.00
Claude Sonnet 5 claude-sonnet-5	1M	$2.00	$0.20	5 min$2.50 1 hour$4.00	$10.00
Claude Sonnet 4.6 claude-sonnet-4-6	1M	$3.00	$0.30	5 min$3.75 1 hour$6.00	$15.00
Claude Haiku 4.5 claude-haiku-4-5	200k	$1.00	$0.10	5 min$1.25 1 hour$2.00	$5.00

OpenAI

Pricing

A prompt over 272k input tokens is billed at the long-context rate for every token in the request.

Language

GPT-6 Astra

gpt-6-astra

Context

1.05M

Input

≤272k$10.00
>272k$20.00

Output

≤272k$50.00
>272k$75.00

Cache read

≤272k$1.00
>272k$2.00

Cache write

≤272k$12.50
>272k$25.00

GPT-6 Sol

gpt-6-sol

Context

1.05M

Input

≤272k$2.00
>272k$4.00

Output

≤272k$10.00
>272k$15.00

Cache read

≤272k$0.20
>272k$0.40

Cache write

≤272k$2.50
>272k$5.00

GPT-6 Luna

gpt-6-luna

Context

1.05M

Input

≤272k$0.10
>272k$0.20

Output

≤272k$0.50
>272k$0.75

Cache read

≤272k$0.01
>272k$0.02

Cache write

≤272k$0.125
>272k$0.25

GPT-5.6 Sol

gpt-5.6-sol

Context

1.05M

Input

≤272k$4.00
>272k$8.00

Output

≤272k$20.00
>272k$30.00

Cache read

≤272k$0.40
>272k$0.80

Cache write

≤272k$5.00
>272k$10.00

GPT-5.6 Terra

gpt-5.6-terra

Context

1.05M

Input

≤272k$2.00
>272k$4.00

Output

≤272k$12.00
>272k$18.00

Cache read

≤272k$0.20
>272k$0.40

Cache write

≤272k$2.50
>272k$5.00

GPT-5.6 Luna

gpt-5.6-luna

Context

1.05M

Input

≤272k$0.20
>272k$0.40

Output

≤272k$1.20
>272k$1.80

Cache read

≤272k$0.02
>272k$0.04

Cache write

≤272k$0.25
>272k$0.50

GPT-5.6 Cyber

gpt-5.6-cyber

Input

$12.50

Output

$75.00

Cache read

$1.25

Cache write

$15.625

GPT-5.5

gpt-5.5

No list price is recorded on this sheet.

GPT-5.3 Codex

gpt-5.3-codex

Input

$1.75

Output

$14.00

Cache read

$0.175

GPT-5

gpt-5

API shutdown 11 December 2026

Context

400k

Input

$1.25

Output

$10.00

Cache read

$0.125

GPT-4.1

gpt-4.1

Context

Input

$2.00

Output

$8.00

Cache read

$0.50

GPT-4.1 mini

gpt-4.1-mini

Context

Input

$0.40

Output

$1.60

Cache read

$0.10

GPT-4.1 nano

gpt-4.1-nano

Context

Input

$0.10

Output

$0.40

Cache read

$0.025

GPT-4o

gpt-4o

Context

128k

Input

$2.50

Output

$10.00

Cache read

$1.25

GPT-4o mini

gpt-4o-mini

Context

128k

Input

$0.15

Output

$0.60

Cache read

$0.075

o3

API shutdown 11 December 2026

Context

200k

Input

$2.00

Output

$8.00

Cache read

$0.50

Voice

GPT-Realtime 2.1

gpt-realtime-2.1

Input

audio$32.00
text$4.00
image$5.00

Output

audio$64.00
text$24.00

Cache read

audio$0.40
text$0.40
image$0.50

GPT-Realtime 2.1 mini

gpt-realtime-2.1-mini

Input

audio$10.00
text$0.60
image$0.80

Output

audio$20.00
text$2.40

Cache read

audio$0.30
text$0.06
image$0.08

GPT-Live 1

gpt-live-1

Input

/ min$0.05

GPT-Realtime Translate

gpt-realtime-translate

Input

/ min$0.034

GPT-Realtime Whisper

gpt-realtime-whisper

Input

/ min$0.017

GPT-Live Transcribe

gpt-live-transcribe

Input

/ min$0.017

GPT-Transcribe

gpt-transcribe

Input

/ min$0.0045

GPT-4o Transcribe

gpt-4o-transcribe

Input

$2.50

Output

$10.00

GPT-4o mini Transcribe

gpt-4o-mini-transcribe

Input

$1.25

Output

$5.00

Image

GPT Image 2.5

gpt-image-2.5

Input

image$8.00
text$5.00

Output

image$30.00

Cache read

image$2.00
text$1.25

GPT Image 2

gpt-image-2

Input

image$4.00
text$2.50

Output

image$15.00

Cache read

image$1.00
text$0.625

Embeddings

text-embedding-3-large

Context

Input

$0.13

text-embedding-3-small

Context

Input

$0.02

Tools

Web search

web-search

Input

/ 1k calls$10.00

File search

file-search

Input

tool call / 1k calls$2.50
storage / GiB-day$0.10

Model	Context	Input	Cache read	Cache write	Output
Language
GPT-6 Astra gpt-6-astra	1.05M	≤272k$10.00 >272k$20.00	≤272k$1.00 >272k$2.00	≤272k$12.50 >272k$25.00	≤272k$50.00 >272k$75.00
GPT-6 Sol gpt-6-sol	1.05M	≤272k$2.00 >272k$4.00	≤272k$0.20 >272k$0.40	≤272k$2.50 >272k$5.00	≤272k$10.00 >272k$15.00
GPT-6 Luna gpt-6-luna	1.05M	≤272k$0.10 >272k$0.20	≤272k$0.01 >272k$0.02	≤272k$0.125 >272k$0.25	≤272k$0.50 >272k$0.75
GPT-5.6 Sol gpt-5.6-sol	1.05M	≤272k$4.00 >272k$8.00	≤272k$0.40 >272k$0.80	≤272k$5.00 >272k$10.00	≤272k$20.00 >272k$30.00
GPT-5.6 Terra gpt-5.6-terra	1.05M	≤272k$2.00 >272k$4.00	≤272k$0.20 >272k$0.40	≤272k$2.50 >272k$5.00	≤272k$12.00 >272k$18.00
GPT-5.6 Luna gpt-5.6-luna	1.05M	≤272k$0.20 >272k$0.40	≤272k$0.02 >272k$0.04	≤272k$0.25 >272k$0.50	≤272k$1.20 >272k$1.80
GPT-5.6 Cyber gpt-5.6-cyber	—	$12.50	$1.25	$15.625	$75.00
GPT-5.5 gpt-5.5 No list price is recorded on this sheet.	—	—	—	—	—
GPT-5.3 Codex gpt-5.3-codex	—	$1.75	$0.175	—	$14.00
GPT-5 gpt-5 API shutdown 11 December 2026	400k	$1.25	$0.125	—	$10.00
GPT-4.1 gpt-4.1	1M	$2.00	$0.50	—	$8.00
GPT-4.1 mini gpt-4.1-mini	1M	$0.40	$0.10	—	$1.60
GPT-4.1 nano gpt-4.1-nano	1M	$0.10	$0.025	—	$0.40
GPT-4o gpt-4o	128k	$2.50	$1.25	—	$10.00
GPT-4o mini gpt-4o-mini	128k	$0.15	$0.075	—	$0.60
o3 o3 API shutdown 11 December 2026	200k	$2.00	$0.50	—	$8.00
Voice
GPT-Realtime 2.1 gpt-realtime-2.1	—	audio$32.00 text$4.00 image$5.00	audio$0.40 text$0.40 image$0.50	—	audio$64.00 text$24.00
GPT-Realtime 2.1 mini gpt-realtime-2.1-mini	—	audio$10.00 text$0.60 image$0.80	audio$0.30 text$0.06 image$0.08	—	audio$20.00 text$2.40
GPT-Live 1 gpt-live-1	—	/ min$0.05	—	—	—
GPT-Realtime Translate gpt-realtime-translate	—	/ min$0.034	—	—	—
GPT-Realtime Whisper gpt-realtime-whisper	—	/ min$0.017	—	—	—
GPT-Live Transcribe gpt-live-transcribe	—	/ min$0.017	—	—	—
GPT-Transcribe gpt-transcribe	—	/ min$0.0045	—	—	—
GPT-4o Transcribe gpt-4o-transcribe	—	$2.50	—	—	$10.00
GPT-4o mini Transcribe gpt-4o-mini-transcribe	—	$1.25	—	—	$5.00
Image
GPT Image 2.5 gpt-image-2.5	—	image$8.00 text$5.00	image$2.00 text$1.25	—	image$30.00
GPT Image 2 gpt-image-2	—	image$4.00 text$2.50	image$1.00 text$0.625	—	image$15.00
Embeddings
text-embedding-3-large text-embedding-3-large	8k	$0.13	—	—	—
text-embedding-3-small text-embedding-3-small	8k	$0.02	—	—	—
Tools
Web search web-search	—	/ 1k calls$10.00	—	—	—
File search file-search	—	tool call / 1k calls$2.50 storage / GiB-day$0.10	—	—	—

Google

Pricing

Gemini 3.8 Flash is on an introductory rate through 31 December 2026.

Language

Gemini 3.8 Flash

gemini-3.8-flash

Input

$0.75

Output

$3.75

Cache read

$0.075

Gemini 3.1 Pro

gemini-3.1-pro-preview

Context

Input

≤200k$2.00
>200k$4.00

Output

≤200k$12.00
>200k$18.00

Cache read

≤200k$0.20
>200k$0.40

Gemini 3.5 Flash Lite

gemini-3.5-flash-lite

Input

$0.30

Output

$2.50

Cache read

$0.03

Gemini 3 Flash

gemini-3-flash-preview

Context

Input

text$0.50
audio$1.00

Output

$3.00

Cache read

text$0.05
audio$0.10

Voice

Gemini 3.1 Flash Live

gemini-3.1-flash-live-preview

Input

text$0.75
audio$3.00
audio / min$0.005
image$1.00

Output

text$4.50
audio$12.00
audio / min$0.018

Gemini 3.5 Live Translate

gemini-3.5-live-translate-preview

Input

audio$3.50
audio / min$0.0053

Output

audio$21.00
audio / min$0.0315

Gemini 3.5 Transcribe Live

gemini-3.5-transcribe-live

Input

audio$3.50
audio / min$0.005

Output

text$21.00
text / min$0.004

Gemini 3.5 Transcribe

gemini-3.5-transcribe

Input

audio$2.00
audio / min$0.003

Output

text$12.00
text / min$0.002

Gemini 2.5 Flash Live Audio

gemini-2.5-flash-native-audio

Input

text$0.50
audio$3.00

Output

text$2.00
audio$12.00

Gemini 3.1 Flash TTS

gemini-3.1-flash-tts-preview

Input

$1.00

Output

$20.00

Gemini 2.5 Flash TTS

gemini-2.5-flash-preview-tts

Input

text$0.50

Output

audio$10.00

Embeddings

Gemini Embedding

gemini-embedding-001

Input

$0.15

Tools

Search grounding

google-search-grounding

Input

/ 1k calls$14.00

Model	Context	Input	Cache read	Cache write	Output
Language
Gemini 3.8 Flash gemini-3.8-flash	—	$0.75	$0.075	—	$3.75
Gemini 3.1 Pro gemini-3.1-pro-preview	1M	≤200k$2.00 >200k$4.00	≤200k$0.20 >200k$0.40	—	≤200k$12.00 >200k$18.00
Gemini 3.5 Flash Lite gemini-3.5-flash-lite	—	$0.30	$0.03	—	$2.50
Gemini 3 Flash gemini-3-flash-preview	1M	text$0.50 audio$1.00	text$0.05 audio$0.10	—	$3.00
Voice
Gemini 3.1 Flash Live gemini-3.1-flash-live-preview	—	text$0.75 audio$3.00 audio / min$0.005 image$1.00	—	—	text$4.50 audio$12.00 audio / min$0.018
Gemini 3.5 Live Translate gemini-3.5-live-translate-preview	—	audio$3.50 audio / min$0.0053	—	—	audio$21.00 audio / min$0.0315
Gemini 3.5 Transcribe Live gemini-3.5-transcribe-live	—	audio$3.50 audio / min$0.005	—	—	text$21.00 text / min$0.004
Gemini 3.5 Transcribe gemini-3.5-transcribe	—	audio$2.00 audio / min$0.003	—	—	text$12.00 text / min$0.002
Gemini 2.5 Flash Live Audio gemini-2.5-flash-native-audio	—	text$0.50 audio$3.00	—	—	text$2.00 audio$12.00
Gemini 3.1 Flash TTS gemini-3.1-flash-tts-preview	—	$1.00	—	—	$20.00
Gemini 2.5 Flash TTS gemini-2.5-flash-preview-tts	—	text$0.50	—	—	audio$10.00
Embeddings
Gemini Embedding gemini-embedding-001	—	$0.15	—	—	—
Tools
Search grounding google-search-grounding	—	/ 1k calls$14.00	—	—	—

xAI

Pricing

A prompt of 200k tokens or more is billed at the higher rate for every token in the request.

Language

Grok 4.7

grok-4.7

Context

500k

Input

<200k$2.00
≥200k$4.00

Output

<200k$6.00
≥200k$12.00

Cache read

<200k$0.50
≥200k$1.00

Grok 4.6

grok-4.6

Context

500k

Input

<200k$2.00
≥200k$4.00

Output

<200k$6.00
≥200k$12.00

Cache read

<200k$0.50
≥200k$1.00

Grok 4.5

grok-4.5

Context

500k

Input

<200k$2.00
≥200k$4.00

Output

<200k$6.00
≥200k$12.00

Cache read

<200k$0.30
≥200k$0.60

Grok 4.3

grok-4.3

Context

Input

<200k$1.25
≥200k$2.50

Output

<200k$2.50
≥200k$5.00

Cache read

<200k$0.20
≥200k$0.40

Grok Build 0.1

grok-build-0.1

Context

256k

Input

<200k$1.00
≥200k$2.00

Output

<200k$2.00
≥200k$4.00

Cache read

<200k$0.20
≥200k$0.40

Voice

Grok Voice Think Fast 2.0

grok-voice-think-fast-2.0

Input

audio / min$0.08
text / message$0.004

Grok Speech to Text

grok-stt

Input

REST / hr$0.10
streaming / hr$0.20

Grok Text to Speech

grok-tts

Input

/ M chars$15.00

Image

Grok Imagine Image

grok-imagine-image

Output

/ image$0.02

Grok Imagine Image 2.0

grok-imagine-image-2.0

Output

/ image$0.04

Grok Imagine Image Quality

grok-imagine-image-quality

Output

/ image$0.05

Grok Imagine Video

grok-imagine-video

Output

/ sec$0.05

Grok Imagine Video 1.5

grok-imagine-video-1.5

Output

/ sec$0.08

Tools

Web search

x-web-search

Input

/ 1k calls$5.00

X search

x-search

Input

posts / 1k calls$5.00
profiles / 1k calls$10.00

Code execution

code-execution

Input

/ 1k calls$5.00

Collections search

collections-search

Input

/ 1k calls$2.50

Model	Context	Input	Cache read	Cache write	Output
Language
Grok 4.7 grok-4.7	500k	<200k$2.00 ≥200k$4.00	<200k$0.50 ≥200k$1.00	—	<200k$6.00 ≥200k$12.00
Grok 4.6 grok-4.6	500k	<200k$2.00 ≥200k$4.00	<200k$0.50 ≥200k$1.00	—	<200k$6.00 ≥200k$12.00
Grok 4.5 grok-4.5	500k	<200k$2.00 ≥200k$4.00	<200k$0.30 ≥200k$0.60	—	<200k$6.00 ≥200k$12.00
Grok 4.3 grok-4.3	1M	<200k$1.25 ≥200k$2.50	<200k$0.20 ≥200k$0.40	—	<200k$2.50 ≥200k$5.00
Grok Build 0.1 grok-build-0.1	256k	<200k$1.00 ≥200k$2.00	<200k$0.20 ≥200k$0.40	—	<200k$2.00 ≥200k$4.00
Voice
Grok Voice Think Fast 2.0 grok-voice-think-fast-2.0	—	audio / min$0.08 text / message$0.004	—	—	—
Grok Speech to Text grok-stt	—	REST / hr$0.10 streaming / hr$0.20	—	—	—
Grok Text to Speech grok-tts	—	/ M chars$15.00	—	—	—
Image
Grok Imagine Image grok-imagine-image	—	—	—	—	/ image$0.02
Grok Imagine Image 2.0 grok-imagine-image-2.0	—	—	—	—	/ image$0.04
Grok Imagine Image Quality grok-imagine-image-quality	—	—	—	—	/ image$0.05
Grok Imagine Video grok-imagine-video	—	—	—	—	/ sec$0.05
Grok Imagine Video 1.5 grok-imagine-video-1.5	—	—	—	—	/ sec$0.08
Tools
Web search x-web-search	—	/ 1k calls$5.00	—	—	—
X search x-search	—	posts / 1k calls$5.00 profiles / 1k calls$10.00	—	—	—
Code execution code-execution	—	/ 1k calls$5.00	—	—	—
Collections search collections-search	—	/ 1k calls$2.50	—	—	—

Moonshot

Pricing

Kimi K2.6

kimi-k2.6

Context

262k

Input

$0.95

Output

$4.00

Cache read

$0.16

Kimi K2.7 Code

kimi-k2.7-code

Context

262k

Input

$0.95

Output

$4.00

Cache read

$0.19

Kimi K2.7 Code Highspeed

kimi-k2.7-code-highspeed

Context

262k

Input

$1.90

Output

$8.00

Cache read

$0.38

Model	Context	Input	Cache read	Cache write	Output
Kimi K2.6 kimi-k2.6	262k	$0.95	$0.16	—	$4.00
Kimi K2.7 Code kimi-k2.7-code	262k	$0.95	$0.19	—	$4.00
Kimi K2.7 Code Highspeed kimi-k2.7-code-highspeed	262k	$1.90	$0.38	—	$8.00

DeepSeek

Pricing

Peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday. Other hours are half price.

DeepSeek Flash

deepseek-flash

Context

Input

off-peak$0.15
peak$0.30

Output

off-peak$0.60
peak$1.20

Cache read

off-peak$0.003
peak$0.006

DeepSeek V4 Pro

deepseek-v4-pro

Context

Input

off-peak$0.66
peak$1.32

Output

off-peak$1.98
peak$3.96

Cache read

off-peak$0.022
peak$0.044

Model	Context	Input	Cache read	Cache write	Output
DeepSeek Flash deepseek-flash	1M	off-peak$0.15 peak$0.30	off-peak$0.003 peak$0.006	—	off-peak$0.60 peak$1.20
DeepSeek V4 Pro deepseek-v4-pro	1M	off-peak$0.66 peak$1.32	off-peak$0.022 peak$0.044	—	off-peak$1.98 peak$3.96

Alibaba

Pricing

Qwen3-Max

qwen3-max

Context

262k

Input

international ≤32k$1.20
international ≤128k$2.40
international ≤256k$3.00

Output

international ≤32k$6.00
international ≤128k$12.00
international ≤256k$15.00

Cache read

international ≤32k$0.24
international ≤128k$0.48
international ≤256k$0.60

Qwen3-Max Beijing

qwen3-max-beijing

Context

262k

Input

≤32k$0.359
≤128k$0.574
≤256k$1.004

Output

≤32k$1.434
≤128k$2.294
≤256k$4.014

Cache read

≤32k$0.072
≤128k$0.115
≤256k$0.201

Qwen 3.7-Plus

qwen3.7-plus

No list price is recorded on this sheet.

Model	Context	Input	Cache read	Cache write	Output
Qwen3-Max qwen3-max	262k	international ≤32k$1.20 international ≤128k$2.40 international ≤256k$3.00	international ≤32k$0.24 international ≤128k$0.48 international ≤256k$0.60	—	international ≤32k$6.00 international ≤128k$12.00 international ≤256k$15.00
Qwen3-Max Beijing qwen3-max-beijing	262k	≤32k$0.359 ≤128k$0.574 ≤256k$1.004	≤32k$0.072 ≤128k$0.115 ≤256k$0.201	—	≤32k$1.434 ≤128k$2.294 ≤256k$4.014
Qwen 3.7-Plus qwen3.7-plus No list price is recorded on this sheet.	—	—	—	—	—

Mistral

Pricing

Language

Mistral Large 3

mistral-large-3

Input

$0.50

Output

$1.50

Mistral Medium 3.5

mistral-medium-3.5

Context

256k

Input

$1.50

Output

$7.50

Mistral Small 4

mistral-small-4

Input

$0.15

Output

$0.60

Voice

Voxtral Mini Transcribe Realtime

voxtral-mini-transcribe-realtime

Input

audio / min$0.006

Voxtral TTS

voxtral-tts

Input

/ 1k chars$0.016

Voxtral Small

voxtral-small

Input

audio / min$0.004

Output

$0.40

Model	Context	Input	Cache read	Cache write	Output
Language
Mistral Large 3 mistral-large-3	—	$0.50	—	—	$1.50
Mistral Medium 3.5 mistral-medium-3.5	256k	$1.50	—	—	$7.50
Mistral Small 4 mistral-small-4	—	$0.15	—	—	$0.60
Voice
Voxtral Mini Transcribe Realtime voxtral-mini-transcribe-realtime	—	audio / min$0.006	—	—	—
Voxtral TTS voxtral-tts	—	/ 1k chars$0.016	—	—	—
Voxtral Small voxtral-small	—	audio / min$0.004	—	—	$0.40

MiniMax

Pricing

MiniMax M3

minimax-m3

No list price is recorded on this sheet.

Model	Context	Input	Cache read	Cache write	Output
MiniMax M3 minimax-m3 No list price is recorded on this sheet.	—	—	—	—	—

OpenRouter

Pricing

One OpenAI-compatible endpoint in front of the providers above. Token rates are passed through. The fee is on buying credits, and on bring-your-own-key usage past a monthly allowance. The listed price for a model is the cheapest endpoint, and routing is price-weighted unless you pin a provider.

Inference: No markup. You pay the underlying provider's listed token rate.
Credit purchase, card: 5.5% of the top-up, minimum $0.80.
Credit purchase, crypto: 5% of the top-up, no minimum.
Bring your own key: Free through $25,000 of list-price inference a month, then 5% of the excess.
Prompt logging: 1% discount on usage if prompts may be retained.

Checked 27 September 2026. The table shows the standard list price. Batch and fast tiers are in the JSON.

Loading prices.