Models | ModelRelay

Models

Prices are provider rates with no ModelRelay markup. Intelligence by Artificial Analysis.

Speed

Cost

Intelligence

Accepts

Claude Fable 5.1

Vision

TTFT

2.40s

Uptime

Intelligence

56.8

Input / 1M

$10.00

Output / 1M

$50.00

Max context

Claude Opus 5

Vision

TTFT

Uptime

Intelligence

54.1

Input / 1M

$5.00

Output / 1M

$25.00

Max context

Claude Sonnet 5

Vision

TTFT

1.29s

Uptime

Intelligence

45.1

Input / 1M

$2.00

Output / 1M

$10.00

Max context

DeepSeek V4 Flash 0731

TTFT

1.12s

Uptime

Intelligence

40.8

Input / 1M

$0.22

Output / 1M

$0.66

Max context

1.04M

GLM 5.3 Flash

Vision

TTFT

1.35s

Uptime

Intelligence

46.2

Input / 1M

$0.15

Output / 1M

$0.50

Max context

1.04M

GPT-5.6 Luna

Vision

TTFT

1.83s

Uptime

Intelligence

43.4

Input / 1M

$0.20 ≤272K input

Output / 1M

$1.20 ≤272K input

Max context

1.05M

GPT-5.6 Sol

Vision

TTFT

1.49s

Uptime

Intelligence

51.3

Input / 1M

$5.00 ≤272K input

Output / 1M

$30.00 ≤272K input

Max context

1.05M

GPT-5.6 Terra

Vision

TTFT

1.04s

Uptime

Intelligence

46.8

Input / 1M

$2.00 ≤272K input

Output / 1M

$12.00 ≤272K input

Max context

1.05M

GPT-6 Astra

Vision

TTFT

2.20s

Uptime

Intelligence

54.7

Input / 1M

$10.00 ≤272K input

Output / 1M

$50.00 ≤272K input

Max context

1.05M

Gemini 3.8 Flash

TTFT

1.01s

Uptime

Intelligence

47.1

Input / 1M

$0.75

Output / 1M

$3.75

Max context

1.04M

Grok 4.6

Vision

TTFT

2.36s

Uptime

Intelligence

50.6

Input / 1M

$2.00 ≤200K input

Output / 1M

$6.00 ≤200K input

Max context

500K

Kimi K3

Vision

TTFT

3.96s

Uptime

Intelligence

50.2

Input / 1M

$3.00

Output / 1M

$15.00

Max context

1.04M

Muse Spark 1.3

TTFT

Uptime

Intelligence

51.6

Input / 1M

$1.25

Output / 1M

$4.25

Max context

1.04M

Muse Spark 1.3 Contributor

TTFT

Uptime

Intelligence

51.6

Input / 1M

$0.10

Output / 1M

$0.20

Max context

1.04M

Nemotron Lightning 3.5 30B A3B

TTFT

0.67s

Uptime

Intelligence

16.4

Input / 1M

$0.05

Output / 1M

$0.20

Max context

262K

Qwen 3.8 Max

TTFT

1.03s

Uptime

Intelligence

46.9

Input / 1M

$2.00

Output / 1M

$6.00

Max context


Claude Fable 5.1 Vision	2.40s — evidence: controlled · n=8	1M	$10.00	$50.00	56.8
Claude Opus 5 Vision	-- — evidence: warming 0/3	1M	$5.00	$25.00	54.1
Claude Sonnet 5 Vision	1.29s — evidence: controlled · n=8	1M	$2.00	$10.00	45.1
DeepSeek V4 Flash 0731	1.12s — evidence: controlled · n=8	1.04M	$0.22	$0.66	40.8
GLM 5.3 Flash Vision	1.35s — evidence: controlled · n=8	1.04M	$0.15	$0.50	46.2
GPT-5.6 Luna Vision	1.83s — evidence: controlled · n=8	1.05M	$0.20 ≤272K input	$1.20 ≤272K input	43.4
GPT-5.6 Sol Vision	1.49s — evidence: controlled · n=8	1.05M	$5.00 ≤272K input	$30.00 ≤272K input	51.3
GPT-5.6 Terra Vision	1.04s — evidence: controlled · n=8	1.05M	$2.00 ≤272K input	$12.00 ≤272K input	46.8
GPT-6 Astra Vision	2.20s — evidence: controlled · n=8	1.05M	$10.00 ≤272K input	$50.00 ≤272K input	54.7
Gemini 3.8 Flash	1.01s — evidence: controlled · n=8	1.04M	$0.75	$3.75	47.1
Grok 4.6 Vision	2.36s — evidence: controlled · n=8	500K	$2.00 ≤200K input	$6.00 ≤200K input	50.6
Kimi K3 Vision	3.96s — evidence: controlled · n=8	1.04M	$3.00	$15.00	50.2
Muse Spark 1.3	-- — evidence: warming 0/3	1.04M	$1.25	$4.25	51.6
Muse Spark 1.3 Contributor	-- — evidence: warming 0/3	1.04M	$0.10	$0.20	51.6
Nemotron Lightning 3.5 30B A3B	0.67s — evidence: controlled · n=8	262K	$0.05	$0.20	16.4
Qwen 3.8 Max	1.03s — evidence: controlled · n=8	1M	$2.00	$6.00	46.9
Qwen3.8 27B Vision	0.56s — evidence: controlled · n=8	131K	$0.99	$1.49	41.4

TTFT is the median time to the first visible answer token over real ModelRelay requests, with a fixed prompt standing in for models that have no traffic yet. Speed ranks by it. Intelligence is the Artificial Analysis Intelligence Index.

One integration

One API, with drop-in compatibility.

Use ModelRelay's Responses API directly, or point an existing OpenAI or Anthropic SDK at the compatible endpoints.

Call a model

ModelRelay · POST /api/v1/responses Drop-in · OpenAI /v1/responses · Anthropic /v1/messages

curl https://api.modelrelay.ai/api/v1/responses \
-H "Authorization: Bearer $MODELRELAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"claude-sonnet-5","input":"Hello"}'

Change the model. Keep everything else.

Build across models without rebuilding your stack.

Open to everyone. Sign in with GitHub or Google to get started.

Get started