⌘K
FX:
Simulate Spread
🏛

OFFICIAL DIRECT-TO-PROVIDER LABS

1ST PARTY TIER-1

First-party foundation model APIs without intermediaries or multi-model routers. Features full per-token price breakdowns, prompt caching economics (up to 90% discount), reasoning grades, context limits, and Zero Data Retention (ZDR) guarantees.

TRACKED LABS 8 Labs
OFFICIAL MODELS 99 Models
100% First-Party SLA

Direct low-latency pipes to Anthropic, OpenAI, DeepSeek, and Google without third-party proxies.

Zero Data Retention (ZDR)

Enterprise non-training agreements, HIPAA Business Associate Agreements (BAA), and SOC2 Type II.

Native Context Caching

50% to 90% direct prompt caching discounts built natively into the model inference engines.

Dedicated Provisioning (PTU)

Dedicated cloud throughput on Microsoft Azure and AWS for guaranteed TPS during market volatility.

FIRST-PARTY MODEL PRICE & SPECIFICATION MATRIX

Compare official per-token rates, prompt caching discounts, batch pricing, context sizes, and reasoning grades.

SORT BY:
🔍
LAB:
GRADE:
CONTEXT:
MODEL & PROVIDER LAB
REASONING GRADE
CONTEXT / MAX OUT
STANDARD INPUT (1M)
STANDARD OUTPUT (1M)
PROMPT CACHE READ
BATCH MODE (50%)
CAPABILITIES
ACTION
01
Multimodal Vision/Audio
1M / 128k
$10.00 / 1M in $50.00 / 1M out
$1.00 -90%
Write: $12.50
$5.00 / $25.00 Async 24h
👁 🛡
SPECS →
02
Claude Opus 5 MMLU 88.5% Anthropic Direct API
Multimodal Vision/Audio
1M / 128k
$5.00 / 1M in $25.00 / 1M out
$0.50 -90%
Write: $6.25
$2.50 / $12.50 Async 24h
👁 🛡
SPECS →
03
Multimodal Vision/Audio
1M / 128k
$2.50 / 1M in $12.50 / 1M out
$0.25 -90%
Write: $3.13
$1.25 / $6.25 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
1M / 128k
$2.00 / 1M in $10.00 / 1M out
$0.20 -90%
Write: $2.50
$1.00 / $5.00 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
1M / 128k
$1.00 / 1M in $5.00 / 1M out
$0.10 -90%
Write: $1.25
$0.50 / $2.50 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
1M / 128k
$10.00 / 1M in $50.00 / 1M out
$1.00 -90%
Write: $12.50
$5.00 / $25.00 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
1M / 128k
$5.00 / 1M in $25.00 / 1M out
$0.50 -90%
Write: $6.25
$2.50 / $12.50 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
1M / 128k
$10.00 / 1M in $50.00 / 1M out
$1.00 -90%
Write: $12.50
$5.00 / $25.00 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
1M / 128k
$5.00 / 1M in $25.00 / 1M out
$0.50 -90%
Write: $6.25
$2.50 / $12.50 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
1M / 128k
$2.50 / 1M in $12.50 / 1M out
$0.25 -90%
Write: $3.13
$1.25 / $6.25 Async 24h
👁 🛡
SPECS →
SOTA Frontier
256k / 8k
$1.00 / 1M in $2.00 / 1M out
$0.50 -50%
Write: $1.25
$0.50 / $1.00 Async 24h
🛡
SPECS →
Multimodal Vision/Audio
1M / 128k
$30.00 / 1M in $150.00 / 1M out
$3.00 -90%
Write: $37.50
$15.00 / $75.00 Async 24h
👁 🛡
SPECS →
SOTA Frontier
400k / 128k
$5.00 / 1M in $30.00 / 1M out
$2.50 -50%
Write: $6.25
$2.50 / $15.00 Async 24h
🛡
SPECS →
Multimodal Vision/Audio
1M / 128k
$5.00 / 1M in $25.00 / 1M out
$0.50 -90%
Write: $6.25
$2.50 / $12.50 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
1M / 128k
$2.50 / 1M in $12.50 / 1M out
$0.25 -90%
Write: $3.13
$1.25 / $6.25 Async 24h
👁 🛡
SPECS →
16
Google: Gemma 4 26B A4B MMLU 88.5% Google Vertex AI / AI Studio
Fast Economy
262k / 16k
$0.07 / 1M in $0.34 / 1M out
$0.018 -75%
Write: $0.09
$0.04 / $0.17 Async 24h
🛡
SPECS →
17
Google: Gemma 4 31B MMLU 88.5% Google Vertex AI / AI Studio
Fast Economy
262k / 16k
$0.09 / 1M in $0.34 / 1M out
$0.022 -75%
Write: $0.11
$0.04 / $0.17 Async 24h
🛡
SPECS →
18
Google: Lyria 3 Pro Preview MMLU 88.5% Google Vertex AI / AI Studio
Fast Economy
1M / 66k
$0.01 / 1M in $0.02 / 1M out
$0.003 -75%
Write: $0.01
$0.01 / $0.01 Async 24h
🛡
SPECS →
19
Google: Lyria 3 Clip Preview MMLU 88.5% Google Vertex AI / AI Studio
Fast Economy
1M / 66k
$0.01 / 1M in $0.02 / 1M out
$0.003 -75%
Write: $0.01
$0.01 / $0.01 Async 24h
🛡
SPECS →
Multimodal Vision/Audio
1M / 128k
$3.00 / 1M in $15.00 / 1M out
$0.30 -90%
Write: $3.75
$1.50 / $7.50 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
1M / 128k
$1.50 / 1M in $7.50 / 1M out
$0.15 -90%
Write: $1.88
$0.75 / $3.75 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
1M / 128k
$5.00 / 1M in $25.00 / 1M out
$0.50 -90%
Write: $6.25
$2.50 / $12.50 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
1M / 128k
$2.50 / 1M in $12.50 / 1M out
$0.25 -90%
Write: $3.13
$1.25 / $6.25 Async 24h
👁 🛡
SPECS →
24
SOTA Frontier
128k / 16k
$2.50 / 1M in $10.00 / 1M out
$1.25 -50%
Write: $3.13
$1.25 / $5.00 Async 24h
🎙 🛡
SPECS →
SOTA Frontier
128k / 16k
$0.60 / 1M in $2.40 / 1M out
$0.30 -50%
Write: $0.75
$0.30 / $1.20 Async 24h
🎙 🛡
SPECS →
Fast Economy
164k / 66k
$0.27 / 1M in $0.40 / 1M out
$0.07 -75%
Write: $0.34
$0.13 / $0.20 Async 24h
🛡
SPECS →
Multimodal Vision/Audio
200k / 64k
$5.00 / 1M in $25.00 / 1M out
$0.50 -90%
Write: $6.25
$2.50 / $12.50 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
200k / 64k
$2.50 / 1M in $12.50 / 1M out
$0.25 -90%
Write: $3.13
$1.25 / $6.25 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
200k / 64k
$1.00 / 1M in $5.00 / 1M out
$0.10 -90%
Write: $1.25
$0.50 / $2.50 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
200k / 64k
$0.50 / 1M in $2.50 / 1M out
$0.05 -90%
Write: $0.63
$0.25 / $1.25 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
33k / 8k
$0.30 / 1M in $2.50 / 1M out
$0.07 -75%
Write: $0.38
$0.15 / $1.25 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
1M / 64k
$3.00 / 1M in $15.00 / 1M out
$0.30 -90%
Write: $3.75
$1.50 / $7.50 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
1M / 64k
$1.50 / 1M in $7.50 / 1M out
$0.15 -90%
Write: $1.88
$0.75 / $3.75 Async 24h
👁 🛡
SPECS →
Fast Economy
164k / 66k
$0.27 / 1M in $0.41 / 1M out
$0.07 -75%
Write: $0.34
$0.14 / $0.20 Async 24h
🛡
SPECS →
Fast Economy
164k / 164k
$0.27 / 1M in $1.00 / 1M out
$0.07 -75%
Write: $0.34
$0.14 / $0.50 Async 24h
🛡
SPECS →
Fast Economy
164k / 33k
$0.25 / 1M in $0.95 / 1M out
$0.06 -75%
Write: $0.31
$0.13 / $0.47 Async 24h
🛡
SPECS →
Multimodal Vision/Audio
200k / 32k
$15.00 / 1M in $75.00 / 1M out
$1.50 -90%
Write: $18.75
$7.50 / $37.50 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
200k / 32k
$7.50 / 1M in $37.50 / 1M out
$0.75 -90%
Write: $9.38
$3.75 / $18.75 Async 24h
👁 🛡
SPECS →
39
Google: Gemini 2.5 Flash Lite MMLU 82% Google Vertex AI / AI Studio
Multimodal Vision/Audio
1M / 66k
$0.10 / 1M in $0.40 / 1M out
$0.025 -75%
Write: $0.13
$0.05 / $0.20 Async 24h
👁 🛡
SPECS →
40
Multimodal Vision/Audio
1M / 66k
$0.05 / 1M in $0.20 / 1M out
$0.013 -75%
Write: $0.06
$0.03 / $0.10 Async 24h
👁 🛡
SPECS →
41
Google: Gemini 2.5 Flash MMLU 82% Google Vertex AI / AI Studio
Multimodal Vision/Audio
1M / 66k
$0.30 / 1M in $2.50 / 1M out
$0.07 -75%
Write: $0.38
$0.15 / $1.25 Async 24h
👁 🛡
SPECS →
42
Google: Gemini 2.5 Flash (batch) MMLU 82% Google Vertex AI / AI Studio
Multimodal Vision/Audio
1M / 66k
$0.15 / 1M in $1.25 / 1M out
$0.037 -75%
Write: $0.19
$0.07 / $0.63 Async 24h
👁 🛡
SPECS →
43
Google: Gemini 2.5 Pro MMLU 82% Google Vertex AI / AI Studio
Multimodal Vision/Audio
1M / 66k
$1.25 / 1M in $10.00 / 1M out
$0.31 -75%
Write: $1.56
$0.63 / $5.00 Async 24h
👁 🛡
SPECS →
44
Google: Gemini 2.5 Pro (batch) MMLU 82% Google Vertex AI / AI Studio
Multimodal Vision/Audio
1M / 66k
$0.63 / 1M in $5.00 / 1M out
$0.16 -75%
Write: $0.78
$0.31 / $2.50 Async 24h
👁 🛡
SPECS →
45
OpenAI: o3 Pro MMLU 92.1% OpenAI Direct API
Deep Reasoning
200k / 100k
$20.00 / 1M in $80.00 / 1M out
$10.00 -50%
Write: $25.00
$10.00 / $40.00 Async 24h
🧠 🛡
SPECS →
Deep Reasoning
200k / 100k
$10.00 / 1M in $40.00 / 1M out
$5.00 -50%
Write: $12.50
$5.00 / $20.00 Async 24h
🧠 🛡
SPECS →
47
Multimodal Vision/Audio
1M / 66k
$1.25 / 1M in $10.00 / 1M out
$0.31 -75%
Write: $1.56
$0.63 / $5.00 Async 24h
👁 🛡
SPECS →
48
DeepSeek: R1 0528 MMLU 90.8% DeepSeek Direct API
Deep Reasoning
164k / 33k
$0.50 / 1M in $2.15 / 1M out
$0.13 -75%
Write: $0.63
$0.25 / $1.07 Async 24h
🧠 🛡
SPECS →
Multimodal Vision/Audio
200k / 32k
$15.00 / 1M in $75.00 / 1M out
$1.50 -90%
Write: $18.75
$7.50 / $37.50 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
1M / 64k
$3.00 / 1M in $15.00 / 1M out
$0.30 -90%
Write: $3.75
$1.50 / $7.50 Async 24h
👁 🛡
SPECS →
51
Google: Gemma 3n 4B MMLU 88.5% Google Vertex AI / AI Studio
Fast Economy
33k / 8k
$0.06 / 1M in $0.12 / 1M out
$0.015 -75%
Write: $0.07
$0.03 / $0.06 Async 24h
🛡
SPECS →
52
Multimodal Vision/Audio
1M / 66k
$1.25 / 1M in $10.00 / 1M out
$0.31 -75%
Write: $1.56
$0.63 / $5.00 Async 24h
👁 🛡
SPECS →
Fast Economy
1M / 16k
$0.18 / 1M in $0.18 / 1M out
$0.09 -50%
Write: $0.23
$0.09 / $0.09 Async 24h
🛡
SPECS →
54
OpenAI: o3 MMLU 92.1% OpenAI Direct API
Deep Reasoning
200k / 100k
$2.00 / 1M in $8.00 / 1M out
$1.00 -50%
Write: $2.50
$1.00 / $4.00 Async 24h
🧠 🛡
SPECS →
55
Deep Reasoning
200k / 100k
$1.00 / 1M in $4.00 / 1M out
$0.50 -50%
Write: $1.25
$0.50 / $2.00 Async 24h
🧠 🛡
SPECS →
Fast Economy
1M / 16k
$0.20 / 1M in $0.80 / 1M out
$0.10 -50%
Write: $0.25
$0.10 / $0.40 Async 24h
🛡
SPECS →
57
Fast Economy
1M / 16k
$0.10 / 1M in $0.30 / 1M out
$0.05 -50%
Write: $0.13
$0.05 / $0.15 Async 24h
🛡
SPECS →
Fast Economy
164k / 164k
$0.25 / 1M in $1.00 / 1M out
$0.06 -75%
Write: $0.31
$0.13 / $0.50 Async 24h
🛡
SPECS →
59
OpenAI: o1-pro MMLU 91.8% OpenAI Direct API
Deep Reasoning
200k / 100k
$150.00 / 1M in $600.00 / 1M out
$75.00 -50%
Write: $187.50
$75.00 / $300.00 Async 24h
🧠 🛡
SPECS →
Deep Reasoning
200k / 100k
$75.00 / 1M in $300.00 / 1M out
$37.50 -50%
Write: $93.75
$37.50 / $150.00 Async 24h
🧠 🛡
SPECS →
61
Google: Gemma 3 4B MMLU 88.5% Google Vertex AI / AI Studio
Fast Economy
131k / 16k
$0.05 / 1M in $0.10 / 1M out
$0.013 -75%
Write: $0.06
$0.03 / $0.05 Async 24h
🛡
SPECS →
62
Google: Gemma 3 12B MMLU 88.5% Google Vertex AI / AI Studio
Fast Economy
131k / 16k
$0.05 / 1M in $0.15 / 1M out
$0.013 -75%
Write: $0.06
$0.03 / $0.07 Async 24h
🛡
SPECS →
63
Google: Gemma 3 27B MMLU 88.5% Google Vertex AI / AI Studio
Fast Economy
262k / 131k
$0.08 / 1M in $0.45 / 1M out
$0.020 -75%
Write: $0.10
$0.04 / $0.23 Async 24h
🛡
SPECS →
Deep Reasoning
200k / 100k
$1.10 / 1M in $4.40 / 1M out
$0.55 -50%
Write: $1.38
$0.55 / $2.20 Async 24h
🧠 🛡
SPECS →
Deep Reasoning
200k / 100k
$0.55 / 1M in $2.20 / 1M out
$0.28 -50%
Write: $0.69
$0.28 / $1.10 Async 24h
🧠 🛡
SPECS →
66
Deep Reasoning
200k / 100k
$1.10 / 1M in $4.40 / 1M out
$0.55 -50%
Write: $1.38
$0.55 / $2.20 Async 24h
🧠 🛡
SPECS →
Deep Reasoning
200k / 100k
$0.55 / 1M in $2.20 / 1M out
$0.28 -50%
Write: $0.69
$0.28 / $1.10 Async 24h
🧠 🛡
SPECS →
Deep Reasoning
8k / 8k
$0.80 / 1M in $0.80 / 1M out
$0.20 -75%
Write: $1.00
$0.40 / $0.40 Async 24h
🧠 🛡
SPECS →
69
DeepSeek: R1 MMLU 90.8% DeepSeek Direct API
Deep Reasoning
64k / 16k
$0.70 / 1M in $2.50 / 1M out
$0.17 -75%
Write: $0.88
$0.35 / $1.25 Async 24h
🧠 🛡
SPECS →
70
Fast Economy
164k / 16k
$0.26 / 1M in $1.03 / 1M out
$0.06 -75%
Write: $0.32
$0.13 / $0.51 Async 24h
🛡
SPECS →
71
OpenAI: o1 MMLU 91.8% OpenAI Direct API
Deep Reasoning
200k / 100k
$15.00 / 1M in $60.00 / 1M out
$7.50 -50%
Write: $18.75
$7.50 / $30.00 Async 24h
🧠 🛡
SPECS →
72
Deep Reasoning
200k / 100k
$7.50 / 1M in $30.00 / 1M out
$3.75 -50%
Write: $9.38
$3.75 / $15.00 Async 24h
🧠 🛡
SPECS →
Fast Economy
131k / 16k
$0.10 / 1M in $0.32 / 1M out
$0.05 -50%
Write: $0.13
$0.05 / $0.16 Async 24h
🛡
SPECS →
Multimodal Vision/Audio
128k / 16k
$2.50 / 1M in $10.00 / 1M out
$1.25 -50%
Write: $3.13
$1.25 / $5.00 Async 24h
👁 🛡
SPECS →
Fast Economy
60k / 60k
$0.03 / 1M in $0.20 / 1M out
$0.013 -50%
Write: $0.03
$0.01 / $0.10 Async 24h
🛡
SPECS →
Fast Economy
131k / 131k
$0.05 / 1M in $0.33 / 1M out
$0.025 -50%
Write: $0.06
$0.03 / $0.17 Async 24h
🛡
SPECS →
Multimodal Vision/Audio
128k / 16k
$2.50 / 1M in $10.00 / 1M out
$1.25 -50%
Write: $3.13
$1.25 / $5.00 Async 24h
👁 🛡
SPECS →
Fast Economy
131k / 16k
$0.40 / 1M in $0.40 / 1M out
$0.20 -50%
Write: $0.50
$0.20 / $0.20 Async 24h
🛡
SPECS →
Fast Economy
131k / 131k
$0.05 / 1M in $0.08 / 1M out
$0.025 -50%
Write: $0.06
$0.03 / $0.04 Async 24h
🛡
SPECS →
Multimodal Vision/Audio
128k / 16k
$0.15 / 1M in $0.60 / 1M out
$0.07 -50%
Write: $0.19
$0.07 / $0.30 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
128k / 16k
$0.15 / 1M in $0.60 / 1M out
$0.07 -50%
Write: $0.19
$0.07 / $0.30 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
128k / 16k
$0.07 / 1M in $0.30 / 1M out
$0.037 -50%
Write: $0.09
$0.04 / $0.15 Async 24h
👁 🛡
SPECS →
83
Google: Gemma 2 27B MMLU 88.5% Google Vertex AI / AI Studio
SOTA Frontier
8k / 4k
$0.65 / 1M in $0.65 / 1M out
$0.16 -75%
Write: $0.81
$0.33 / $0.33 Async 24h
🛡
SPECS →
84
OpenAI: GPT-4o MMLU 88.7% OpenAI Direct API
Multimodal Vision/Audio
128k / 16k
$2.50 / 1M in $10.00 / 1M out
$1.25 -50%
Write: $3.13
$1.25 / $5.00 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
128k / 4k
$5.00 / 1M in $15.00 / 1M out
$2.50 -50%
Write: $6.25
$2.50 / $7.50 Async 24h
👁 🛡
SPECS →
Multimodal Vision/Audio
128k / 16k
$1.25 / 1M in $5.00 / 1M out
$0.63 -50%
Write: $1.56
$0.63 / $2.50 Async 24h
👁 🛡
SPECS →
SOTA Frontier
128k / 4k
$10.00 / 1M in $30.00 / 1M out
$5.00 -50%
Write: $12.50
$5.00 / $15.00 Async 24h
🛡
SPECS →
SOTA Frontier
128k / 4k
$5.00 / 1M in $15.00 / 1M out
$2.50 -50%
Write: $6.25
$2.50 / $7.50 Async 24h
🛡
SPECS →
89
Multimodal Vision/Audio
200k / 4k
$0.25 / 1M in $1.25 / 1M out
$0.025 -90%
Write: $0.31
$0.13 / $0.63 Async 24h
👁 🛡
SPECS →
SOTA Frontier
8k / 4k
$1.00 / 1M in $2.00 / 1M out
$0.50 -50%
Write: $1.25
$0.50 / $1.00 Async 24h
🛡
SPECS →
SOTA Frontier
128k / 4k
$10.00 / 1M in $30.00 / 1M out
$5.00 -50%
Write: $12.50
$5.00 / $15.00 Async 24h
🛡
SPECS →
SOTA Frontier
8k / 4k
$1.50 / 1M in $2.00 / 1M out
$0.75 -50%
Write: $1.88
$0.75 / $1.00 Async 24h
🛡
SPECS →
SOTA Frontier
16k / 4k
$3.00 / 1M in $4.00 / 1M out
$1.50 -50%
Write: $3.75
$1.50 / $2.00 Async 24h
🛡
SPECS →
Fast Economy
16k / 4k
$0.50 / 1M in $1.50 / 1M out
$0.25 -50%
Write: $0.63
$0.25 / $0.75 Async 24h
🛡
SPECS →
Fast Economy
16k / 4k
$0.25 / 1M in $0.75 / 1M out
$0.13 -50%
Write: $0.31
$0.13 / $0.38 Async 24h
🛡
SPECS →
96
OpenAI: GPT-4 MMLU 88.5% OpenAI Direct API
SOTA Frontier
8k / 4k
$30.00 / 1M in $60.00 / 1M out
$15.00 -50%
Write: $37.50
$15.00 / $30.00 Async 24h
🛡
SPECS →
Coding Specialist
128k / 8k
$0.60 / 1M in $0.60 / 1M out
$0.30 -50%
Write: $0.75
$0.30 / $0.30 Async 24h
🛡
SPECS →
98
Fast Economy
128k / 8k
$0.10 / 1M in $0.10 / 1M out
$0.05 -50%
Write: $0.13
$0.05 / $0.05 Async 24h
🛡
SPECS →
99
Deep Reasoning
128k / 8k
$0.60 / 1M in $0.60 / 1M out
$0.30 -50%
Write: $0.75
$0.30 / $0.30 Async 24h
🧠 🛡
SPECS →

🏛 LAB INFRASTRUCTURE, SLAS & PAYMENT RAILS

Enterprise policies across Anthropic, OpenAI, DeepSeek, Google, xAI, Microsoft Azure, and AWS Bedrock.

Cerebras Inference Direct API Cerebras Systems Inc.
First-Party AI Lab
First-Party SLA: 99.9% Production SLA
Auth & Deployment: API Key
Zero Data Retention: Zero Data Retention (ZDR) available
Rate Limits (Tier 5): 10,000 RPM / High Concurrency Wafer-Scale Bandwidth
Accepted Payment: Stripe Credit Card, Enterprise Monthly Invoicing, ACH / Wire
Native Lab Features:
Wafer-Scale Engine CS-3 silicon World-record speed (2,100 tok/s on 70B) OpenAI SDK drop-in baseURL
First-Party AI Lab
First-Party SLA: 99.9% Production SLA
Auth & Deployment: API Key
Zero Data Retention: Zero Data Retention (ZDR) available via BAA
Rate Limits (Tier 5): 10,000 RPM / 100,000,000 TPM
Accepted Payment: Stripe Credit Card, Enterprise Monthly Invoice, ACH / Wire
Native Lab Features:
Structured Outputs Prompt Caching (50% discount) Realtime WebRTC Audio API
First-Party AI Lab
First-Party SLA: 99.9% Enterprise SLA
Auth & Deployment: API Key
Zero Data Retention: Zero Data Retention (ZDR) available
Rate Limits (Tier 5): 4,000 RPM / 4,000,000 TPM
Accepted Payment: Stripe Credit Card, Enterprise Monthly Invoicing, Wire Transfer
Native Lab Features:
Extended Thinking Budget Native Prompt Caching (90% discount) Computer Use API
DeepSeek Direct API DeepSeek AI (深度求索)
First-Party AI Lab
First-Party SLA: 99.5% Standard SLA
Auth & Deployment: API Key
Zero Data Retention: Zero user data training guarantee on official API
Rate Limits (Tier 5): High Concurrency Pay-As-You-Go
Accepted Payment: Alipay (支付宝), WeChat Pay (微信支付), Stripe Credit Card
Native Lab Features:
Native Reasoning CoT Context Caching ($0.014 / 1M hit) OpenAI SDK drop-in baseURL
Google Vertex AI / AI Studio Google LLC / Alphabet
Hyperscale Cloud AI
First-Party SLA: 99.95% Google Cloud SLA
Auth & Deployment: API Key
Zero Data Retention: No data logging for paid tier (Google Cloud Trust Principles)
Rate Limits (Tier 5): 1,000 to 4,000 RPM
Accepted Payment: Google Cloud Billing, Credit Card, Invoicing
Native Lab Features:
2,000,000 Tokens Context Window Multimodal Audio/Video Native Context Caching
First-Party AI Lab
First-Party SLA: 99.5% Standard SLA
Auth & Deployment: API Key
Zero Data Retention: Standard API developer terms
Rate Limits (Tier 5): Tier 3 Concurrency
Accepted Payment: Credit Card (Stripe)
Native Lab Features:
Frontier Vision Capabilities Realtime X / Twitter live grounding OpenAI SDK drop-in
Microsoft Azure OpenAI Microsoft Corporation
Hyperscale Cloud AI
First-Party SLA: 99.99% Enterprise Cloud SLA
Auth & Deployment: Azure AD
Zero Data Retention: Zero Data Retention
Rate Limits (Tier 5): Dedicated PTU instances
Accepted Payment: Microsoft Enterprise Agreement (EA), Azure Cloud Billing
Native Lab Features:
VNet Private Endpoints Provisioned Throughput (PTU) EU Data Boundary Guarantee
AWS Bedrock Direct Amazon Web Services Inc.
Hyperscale Cloud AI
First-Party SLA: 99.99% AWS Global Infrastructure SLA
Auth & Deployment: IAM / OAuth2
Zero Data Retention: No customer data logged or stored for model training
Rate Limits (Tier 5): High Service Quotas / Provisioned Units
Accepted Payment: AWS Cloud Billing, EDP Commitments, Invoicing
Native Lab Features:
AWS IAM Fine-grained Access PrivateLink VPC peering Cross-region Inference Profiles