Model Pricing

This page shows pricing structures and model limits across supported model types so you can compare integration cost and capabilities more easily. Please refer to the model marketplace as the source of truth, as documentation may lag behind.

Search models or suppliers

Updated 2026-10-16

Text (25)

Gemini 4 Argon

gemini-4-argon

Context

1M

Max output

65K

USD / 1M tokens

Gemini 4 Argon supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write	Image input	Audio input
G1	Default	4	20	0.2	0.375	4	4

Claude Opus 5.5

claude-opus-5-5

Context

1M

Max output

128K

USD / 1M tokens

Claude Opus 5.5 supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write	Cache write (1h)
G1	Default	4	20	0.2	5	8

GPT-6.1 Sol

gpt-6.1-sol

Context

1M

Max output

128K

USD / 1M tokens

GPT-6.1 Sol supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write
G1	Input tokens ≤ 272,000	2	10	0.1	2.5
	Input tokens > 272,000	4	15	0.2	5

Claude Sonnet 5.5

claude-sonnet-5-5

Context

1M

Max output

128K

USD / 1M tokens

Claude Sonnet 5.5 supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write	Cache write (1h)
G1	Default	2	10	0.1	2.5	4

Claude Haiku 5.5

claude-haiku-5-5

Context

1M

Max output

128K

USD / 1M tokens

Claude Haiku 5.5 supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write	Cache write (1h)
G1	Input tokens ≤ 100,000	0.1	0.5	0.01	0.125	0.2
	Input tokens > 100,000	0.5	2.5	0.05	0.625	1

Deepseek V4.1 Flash

deepseek-flash

Context

1M

Max output

384K

USD / 1M tokens

Deepseek V4.1 Flash supplier pricing

Supplier	Applies to	Input	Output	Cache read
D1	Default	0.3	1.2	0.006

GPT-5.6 Sol

gpt-5.6-sol

Context

1100K

Max output

128K

USD / 1M tokens

GPT-5.6 Sol supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write
G1	Input tokens ≤ 272,000	5	30	0.5	6.25
	Input tokens > 272,000	10	45	1	12.5

GPT-5.6 Terra

gpt-5.6-terra

Context

1M

Max output

128K

USD / 1M tokens

GPT-5.6 Terra supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write
OS	Input tokens ≤ 272,000	2.5	15	0.25	3.13
	Input tokens > 272,000	5	22.5	0.5	6.25
G1	Input tokens ≤ 272,000	2.5	15	0.25	3.13
	Input tokens > 272,000	5	22.5	0.5	6.25

GPT-5.6 Luna

gpt-5.6-luna

Context

1M

Max output

128K

USD / 1M tokens

GPT-5.6 Luna supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write
G1	Input tokens ≤ 272,000	1	6	0.1	1.25
	Input tokens > 272,000	2	9	0.2	2.5

GPT-6 Astra

gpt-6-astra

Context

1M

Max output

128K

USD / 1M tokens

GPT-6 Astra supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write
G1	Input tokens ≤ 272,000	10	50	1	12.5
	Input tokens > 272,000	20	75	2	25

Claude Opus 5

claude-opus-5

Context

1M

Max output

128K

USD / 1M tokens

Claude Opus 5 supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write	Cache write (1h)
G1	Default	5	25	0.5	6.25	10

Claude Sonnet 5

claude-sonnet-5

Context

1M

Max output

128K

USD / 1M tokens

Claude Sonnet 5 supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write	Cache write (1h)
G1	Default	2	10	0.2	2.5	4

Claude Opus 4.8

claude-opus-4-8

Context

1M

Max output

128K

USD / 1M tokens

Claude Opus 4.8 supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write	Cache write (1h)
G1	Default	5	25	0.5	6.25	10

Claude Haiku 4.5

claude-haiku-4-5-20251001

Context

200K

Max output

64K

USD / 1M tokens

Claude Haiku 4.5 supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write	Cache write (1h)
G1	Default	1	5	0.1	1.25	2

GLM 5.3 Flash

glm-5.3-flash

Context

1M

Max output

131,072

USD / 1M tokens

GLM 5.3 Flash supplier pricing

Supplier	Applies to	Input	Output	Cache read
OR-Z1	Default	0.15	0.50	0.03
OR-S1	Default	0.15	0.50	0.03

DeepSeek V4 Flash 0731

deepseek-v4-flash-0731

Context

1M

Max output

384K

USD / 1M tokens

DeepSeek V4 Flash 0731 supplier pricing

Supplier	Applies to	Input	Output	Cache read
OR-S1	Default	0.22	0.66	0.028
OPEAI	Default	0.36	0.64	0.072
D1	Default	0.45	1.34	0.072

DeepSeek V4 Pro

deepseek-v4-pro

Context

1M

Max output

393,216

USD / 1M tokens

DeepSeek V4 Pro supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write	Cache write (1h)
D1	Default	1.34	4.02	0.045	0	0

Gemini 3.8 Flash

gemini-3.8-flash

Context

1,048,576

Max output

65,536

USD / 1M tokens

Gemini 3.8 Flash supplier pricing

Supplier	Applies to	Input	Output	Cache read
G1	Default	0.75	3.75	0.075

DeepSeek V4 Flash Vision Exp

deepseek-v4-flash-vision-exp

Context

1,048,576

Max output

262,144

USD / 1M tokens

DeepSeek V4 Flash Vision Exp supplier pricing

Supplier	Applies to	Input	Output	Cache read
D1	Default	0.44	1.32	0.014

GLM-OCR

glm-ocr

Context

128K

Max output

4,096

USD / 1M tokens

GLM-OCR supplier pricing

Supplier	Applies to	Input	Output
OPEAI	Default	0.03	0.03

Qwen3.8-27B-FP8

qwen3.8-27b-fp8

Context

128K

Max output

4,096

USD / 1M tokens

Qwen3.8-27B-FP8 supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write
OPE.AI-H200	Default	0.425	2.55	0.085	0.5315

Qwen3.6-35B-A3B

qwen3.6-35b-a3b

Context

128K

Max output

4,096

USD / 1M tokens

Qwen3.6-35B-A3B supplier pricing

Supplier	Applies to	Input	Output	Cache read
OR-AkashML	Default	0.24	1.8	0.15

Hy4 preview

hy4-preview

Context

1M

Max output

64K

USD / 1M tokens

Hy4 preview supplier pricing

Supplier	Applies to	Input	Output	Cache read
TC	Default	0.834	2.501	0.042

GPT-6 Luna

gpt-6-luna

Context

1M

Max output

128K

USD / 1M tokens

GPT-6 Luna supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write
G1	Input tokens ≤ 272,000	0.1	0.5	0.01	0.125
	Input tokens > 272,000	0.2	0.75	0.02	0.25

GPT-6 Sol

gpt-6-sol

Context

1M

Max output

128K

USD / 1M tokens

GPT-6 Sol supplier pricing

Supplier	Applies to	Input	Output	Cache read	Cache write
G1	Input tokens ≤ 272,000	2	10	0.2	2.5
	Input tokens > 272,000	4	15	0.4	5

Video (4)

Seedance 2.0

seedance-2-0

USD / 1M tokens

Seedance 2.0 supplier pricing

Supplier	Applies to	Output (video input)	Output (no video input)
G1	Resolution = 480p	4.515	7.35
	Resolution = 720p	4.515	7.35
	Resolution = 1080p	4.935	8.085
	Resolution = 2160p	2.52	4.20

Seedance 2.0 Fast

seedance-2-0-fast

USD / 1M tokens

Seedance 2.0 Fast supplier pricing

Supplier	Applies to	Output (video input)	Output (no video input)
G1	Resolution = 480p	3.465	5.88
	Resolution = 720p	3.465	5.88

MiniMax H3

minimax-h3

USD / second

MiniMax H3 supplier pricing

Supplier	Applies to	Video output
OPE.AI-minimax	Resolution = 480p	0.038
	Resolution = 720p	0.076
	Resolution = 1080p	0.095
	Resolution = 1440p	0.1235
	Resolution = 2160p	0.1235

MiniMax H3 NSFW

minimax-h3-nsfw

USD / second

MiniMax H3 NSFW supplier pricing

Supplier	Applies to	Video output
OPE.AI-minimax-n	Resolution = 480p	0.038
	Resolution = 720p	0.076
	Resolution = 1080p	0.095
	Resolution = 1440p	0.1235
	Resolution = 2160p	0.1235

Decision (1)

jev-1.13

typesafe/jev-1.13

Context

32K

USD / 1M tokens

jev-1.13 supplier pricing

Supplier	Applies to	Input
OR-Ts	Default	0.042