Models

Models

Prices are provider rates with no ModelRelay markup. Intelligence by Artificial Analysis (Intelligence Index v5).

Speed
Cost
Intelligence
Accepts
Behavior
Privacy

Abliterated Large Flash

Vision
Abliterated
ZDR
TTFT
1.06s — evidence: controlled · n=8
Uptime
Intelligence
Pending
Input / 1M
$1.00
Output / 1M
$2.00
Max context
1.04M

Abliterated Large v2

Abliterated
ZDR
TTFT
1.72s — evidence: controlled · n=8
Uptime
Intelligence
Pending
Input / 1M
$3.00
Output / 1M
$5.00
Max context
1M

Abliterated Model

Vision
Abliterated
ZDR
TTFT
1.10s — evidence: controlled · n=8
Uptime
Intelligence
Pending
Input / 1M
$1.00
Output / 1M
$3.00
Max context
262K

Claude Fable 5.1

Vision
Retained
TTFT
1.04s — evidence: controlled · n=8
Uptime
Intelligence
49.2
Input / 1M
$10.00
Output / 1M
$50.00
Max context
1M

Claude Opus 5.5

Vision
Retained
TTFT
0.96s — evidence: controlled · n=8
Uptime
Intelligence
59.1
Input / 1M
$4.00
Output / 1M
$20.00
Max context
1M

Claude Sonnet 5.5

Vision
Retained
TTFT
0.64s — evidence: live provisional · 7d · n=41
Uptime
Intelligence
54.5
Input / 1M
$2.00
Output / 1M
$10.00
Max context
1M

DeepSeek V4.1 Flash

Vision
ZDR available
TTFT
0.35s — evidence: live provisional · 7d · n=87
Uptime
Intelligence
Pending
Input / 1M
$0.30
Output / 1M
$1.20
Max context
1.04M
TTFT
2.44s — evidence: live · 7d · n=1834
Uptime
Intelligence
32.6
Input / 1M
$0.30
Output / 1M
$1.20
Max context
1.04M

GLM 5.3

ZDR available
TTFT
1.04s — evidence: controlled · n=8
Uptime
Intelligence
31.7
Input / 1M
$0.19
Output / 1M
$4.40
Max context
1.04M

GLM 5.3 Flash

Vision
ZDR available
TTFT
0.80s — evidence: live · 7d · n=128
Uptime
Intelligence
27.8
Input / 1M
$0.15
Output / 1M
$0.50
Max context
1.04M

GPT-6 Astra

Vision
Retained
TTFT
1.53s — evidence: controlled · n=8
Uptime
Intelligence
56.9
Input / 1M
$10.00 ≤272K input
Output / 1M
$50.00 ≤272K input
Max context
1.05M

GPT-6 Luna

Vision
Retained
TTFT
0.63s — evidence: live · 7d · n=116
Uptime
Intelligence
27.9
Input / 1M
$0.10 ≤272K input
Output / 1M
$0.50 ≤272K input
Max context
1.05M

GPT-6.1 Sol

Vision
Retained
TTFT
1.20s — evidence: live provisional · 7d · n=32
Uptime
Intelligence
54.6
Input / 1M
$2.00 ≤272K input
Output / 1M
$10.00 ≤272K input
Max context
1.05M

Gemini 3.8 Flash

Vision
Retained
TTFT
1.61s — evidence: live provisional · 7d · n=30
Uptime
Intelligence
30.8
Input / 1M
$0.75
Output / 1M
$3.75
Max context
1.04M

Gemini 4 Argon

Vision
Retained
TTFT
5.02s — evidence: controlled · n=8
Uptime
Intelligence
50.4
Input / 1M
$2.00
Output / 1M
$10.00
Max context
1.04M

Grok 4.7

Vision
ZDR
TTFT
2.08s — evidence: controlled · n=8
Uptime
Intelligence
35.5
Input / 1M
$2.00 ≤200K input
Output / 1M
$6.00 ≤200K input
Max context
500K

Kimi K3

Vision
ZDR
TTFT
3.59s — evidence: controlled · n=8
Uptime
Intelligence
Pending
Input / 1M
$3.00
Output / 1M
$15.00
Max context
1.04M

Mercury 3

Retained Trains on prompts
TTFT
0.30s — evidence: live · 7d · n=115
Uptime
Intelligence
Pending
Input / 1M
$0.10
Output / 1M
$0.35
Max context
1M
TTFT
0.21s — evidence: live provisional · 7d · n=31
Uptime
Intelligence
29.1
Input / 1M
$0.15
Output / 1M
$0.60
Max context
1.04M

Muse Spark 1.3

Retention unknown
TTFT
3.38s — evidence: controlled · n=8
Uptime
Intelligence
Pending
Input / 1M
$1.25
Output / 1M
$4.25
Max context
1.04M

Muse Spark 1.3 Contributor

Retention unknown Trains on prompts
TTFT
10.00s — evidence: live provisional · 7d · n=32
Uptime
Intelligence
Pending
Input / 1M
$0.10
Output / 1M
$0.20
Max context
1.04M

Muse Spark Open

Vision
ZDR
TTFT
1.03s — evidence: controlled · n=8
Uptime
Intelligence
24.9
Input / 1M
$1.25
Output / 1M
$4.25
Max context
1.04M

Muse Wonder

Retention unknown
TTFT
2.18s — evidence: controlled · n=8
Uptime
Intelligence
43.6
Input / 1M
$4.00
Output / 1M
$20.00
Max context
1.04M

Qwen 3.8 Max

Vision
ZDR
TTFT
0.75s — evidence: controlled · n=8
Uptime
Intelligence
Pending
Input / 1M
$2.00
Output / 1M
$6.00
Max context
262K

Qwen3.8 27B

Vision
ZDR available
TTFT
0.71s — evidence: controlled · n=8
Uptime
Intelligence
20.1
Input / 1M
$0.225
Output / 1M
$1.98
Max context
262K

No model matches every selected filter.

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 v5.

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-5-5","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