# LLM enrollment rate limits The table below lists default tokens per minute (TPM) and requests per minute (RPM) limits for each model and backend. It includes per-user limits and enrollment tiers for commercial and US Government (USG) environments. Enrollment limits from enabled backends are added together. For enrollments restricted to a single geographic region, limits may be lower in any tier. View your enrollment's configured limits in [Resource Management](../llm-capacity-management/index.md#enrollment-capacity-and-rate-limits). USG rows apply only to the impact levels supported by each model and backend; separate rows identify models whose limits differ by impact level. Rows marked **Experimental** identify experimental offerings for that backend. Availability depends on your environment and experimental access prerequisites. For details, see [supported LLMs](../supported-llms/index.md). | Model Name | Model Backend | Per-user Limits | Small Tier | Medium Tier | Large Tier | XLarge Tier | | --- | --- | --- | --- | --- | --- | --- | | Claude Haiku 4.5 | Anthropic | 1,000,000 TPM
100 RPM | 300,000 TPM
60 RPM | 1,500,000 TPM
750 RPM | 2,000,000 TPM
875 RPM | 2,500,000 TPM
1,000 RPM | | Claude Haiku 4.5 | Amazon Bedrock | 1,000,000 TPM
100 RPM | 200,000 TPM
40 RPM | 1,100,000 TPM
300 RPM | 2,600,000 TPM
600 RPM | 5,100,000 TPM
1,100 RPM | | Claude Haiku 4.5 | Azure | 1,000,000 TPM
100 RPM | 250,000 TPM
50 RPM | 5,000,000 TPM
5,000 RPM | 7,500,000 TPM
7,500 RPM | 10,000,000 TPM
10,000 RPM | | Claude Haiku 4.5 | Google Vertex | 1,000,000 TPM
100 RPM | 250,000 TPM
50 RPM | 4,000,000 TPM
2,000 RPM | 6,000,000 TPM
3,000 RPM | 8,000,000 TPM
4,000 RPM | | Claude Haiku 4.5 | Google Vertex (USG) | 1,000,000 TPM
100 RPM | 100,000 TPM
50 RPM | 4,000,000 TPM
2,000 RPM | 6,000,000 TPM
3,000 RPM | 8,000,000 TPM
4,000 RPM | | Claude Haiku 5.5 | Anthropic | 1,000,000 TPM
100 RPM | 300,000 TPM
60 RPM | 1,500,000 TPM
750 RPM | 2,000,000 TPM
875 RPM | 2,500,000 TPM
1,000 RPM | | Claude Haiku 5.5 | Amazon Bedrock | 1,000,000 TPM
100 RPM | 200,000 TPM
40 RPM | 1,100,000 TPM
300 RPM | 2,600,000 TPM
600 RPM | 5,100,000 TPM
1,100 RPM | | Claude Haiku 5.5 | Amazon Bedrock (USG) | 1,000,000 TPM
100 RPM | 200,000 TPM
40 RPM | 1,100,000 TPM
300 RPM | 2,600,000 TPM
600 RPM | 5,100,000 TPM
1,100 RPM | | Claude Haiku 5.5 | Azure | 1,000,000 TPM
100 RPM | 250,000 TPM
50 RPM | 5,000,000 TPM
5,000 RPM | 7,500,000 TPM
7,500 RPM | 10,000,000 TPM
10,000 RPM | | Claude Haiku 5.5 | Google Vertex | 1,000,000 TPM
100 RPM | 250,000 TPM
50 RPM | 4,000,000 TPM
2,000 RPM | 6,000,000 TPM
3,000 RPM | 8,000,000 TPM
4,000 RPM | | Claude Haiku 5.5 | Google Vertex (USG) | 1,000,000 TPM
100 RPM | 100,000 TPM
50 RPM | 4,000,000 TPM
2,000 RPM | 6,000,000 TPM
3,000 RPM | 8,000,000 TPM
4,000 RPM | | Claude Opus 4.1 | Amazon Bedrock | 400,000 TPM
5 RPM | 70,000 TPM
14 RPM | 500,000 TPM
100 RPM | 1,000,000 TPM
150 RPM | 2,000,000 TPM
200 RPM | | Claude Opus 4.5 | Anthropic | 1,000,000 TPM
100 RPM | 80,000 TPM
16 RPM | 1,500,000 TPM
700 RPM | 2,000,000 TPM
800 RPM | 2,500,000 TPM
900 RPM | | Claude Opus 4.5 | Amazon Bedrock | 1,000,000 TPM
100 RPM | 50,000 TPM
10 RPM | 1,000,000 TPM
100 RPM | 2,000,000 TPM
200 RPM | 4,000,000 TPM
400 RPM | | Claude Opus 4.5 | Azure | 1,000,000 TPM
100 RPM | 60,000 TPM
12 RPM | 1,500,000 TPM
600 RPM | 2,500,000 TPM
700 RPM | 3,500,000 TPM
800 RPM | | Claude Opus 4.5 | Google Vertex | 1,000,000 TPM
100 RPM | 60,000 TPM
12 RPM | 1,000,000 TPM
100 RPM | 1,500,000 TPM
150 RPM | 2,000,000 TPM
200 RPM | | Claude Opus 4.5 | Google Vertex (USG) | 1,000,000 TPM
100 RPM | 100,000 TPM
25 RPM | 1,000,000 TPM
100 RPM | 1,500,000 TPM
150 RPM | 2,000,000 TPM
200 RPM | | Claude Opus 4.6 | Anthropic | 1,500,000 TPM
150 RPM | 80,000 TPM
16 RPM | 1,000,000 TPM
200 RPM | 1,500,000 TPM
300 RPM | 2,000,000 TPM
400 RPM | | Claude Opus 4.6 | Amazon Bedrock | 1,500,000 TPM
150 RPM | 50,000 TPM
10 RPM | 3,000,000 TPM
300 RPM | 4,000,000 TPM
400 RPM | 6,000,000 TPM
600 RPM | | Claude Opus 4.6 | Azure | 1,500,000 TPM
150 RPM | 60,000 TPM
12 RPM | 1,500,000 TPM
600 RPM | 2,500,000 TPM
700 RPM | 3,500,000 TPM
800 RPM | | Claude Opus 4.6 | Google Vertex | 1,500,000 TPM
150 RPM | 60,000 TPM
12 RPM | 5,000,000 TPM
2,000 RPM | 8,000,000 TPM
3,000 RPM | 10,000,000 TPM
4,000 RPM | | Claude Opus 4.6 | Google Vertex (USG) | 1,500,000 TPM
150 RPM | 200,000 TPM
25 RPM | 5,000,000 TPM
2,000 RPM | 8,000,000 TPM
3,000 RPM | 10,000,000 TPM
4,000 RPM | | Claude Opus 4.7 | Anthropic | 1,500,000 TPM
150 RPM | 80,000 TPM
16 RPM | 1,000,000 TPM
200 RPM | 1,500,000 TPM
300 RPM | 2,000,000 TPM
400 RPM | | Claude Opus 4.7 | Amazon Bedrock | 1,500,000 TPM
150 RPM | 50,000 TPM
10 RPM | 3,000,000 TPM
300 RPM | 4,000,000 TPM
400 RPM | 6,000,000 TPM
600 RPM | | Claude Opus 4.7 | Azure | 1,500,000 TPM
150 RPM | 60,000 TPM
12 RPM | 1,000,000 TPM
100 RPM | 2,000,000 TPM
200 RPM | 3,000,000 TPM
300 RPM | | Claude Opus 4.7 | Google Vertex | 1,500,000 TPM
150 RPM | 60,000 TPM
12 RPM | 5,000,000 TPM
2,000 RPM | 8,000,000 TPM
3,000 RPM | 10,000,000 TPM
4,000 RPM | | Claude Opus 4.7 | Google Vertex (USG) | 1,500,000 TPM
150 RPM | 200,000 TPM
25 RPM | 5,000,000 TPM
2,000 RPM | 8,000,000 TPM
3,000 RPM | 10,000,000 TPM
4,000 RPM | | Claude Opus 4.8 | Anthropic | 1,500,000 TPM
150 RPM | 80,000 TPM
16 RPM | 1,000,000 TPM
200 RPM | 1,500,000 TPM
300 RPM | 2,000,000 TPM
400 RPM | | Claude Opus 4.8 | Amazon Bedrock | 1,500,000 TPM
150 RPM | 50,000 TPM
10 RPM | 3,000,000 TPM
300 RPM | 4,000,000 TPM
400 RPM | 6,000,000 TPM
600 RPM | | Claude Opus 4.8 | Amazon Bedrock (USG) | 1,500,000 TPM
150 RPM | 100,000 TPM
25 RPM | 2,500,000 TPM
1,250 RPM | 5,000,000 TPM
2,500 RPM | 7,500,000 TPM
3,750 RPM | | Claude Opus 4.8 | Azure | 1,500,000 TPM
150 RPM | 60,000 TPM
12 RPM | 1,000,000 TPM
100 RPM | 2,000,000 TPM
200 RPM | 3,000,000 TPM
300 RPM | | Claude Opus 4.8 | Google Vertex | 1,500,000 TPM
150 RPM | 60,000 TPM
12 RPM | 5,000,000 TPM
2,000 RPM | 8,000,000 TPM
3,000 RPM | 10,000,000 TPM
4,000 RPM | | Claude Opus 4.8 | Google Vertex (USG) | 1,500,000 TPM
150 RPM | 200,000 TPM
25 RPM | 5,000,000 TPM
2,000 RPM | 8,000,000 TPM
3,000 RPM | 10,000,000 TPM
4,000 RPM | | Claude Opus 5 | Anthropic | 1,500,000 TPM
150 RPM | 300,000 TPM
60 RPM | 1,000,000 TPM
200 RPM | 1,500,000 TPM
300 RPM | 2,000,000 TPM
400 RPM | | Claude Opus 5 | Amazon Bedrock | 1,500,000 TPM
150 RPM | 200,000 TPM
40 RPM | 3,000,000 TPM
300 RPM | 4,000,000 TPM
400 RPM | 6,000,000 TPM
600 RPM | | Claude Opus 5 | Azure | 1,500,000 TPM
150 RPM | 250,000 TPM
50 RPM | 1,000,000 TPM
100 RPM | 2,000,000 TPM
200 RPM | 3,000,000 TPM
300 RPM | | Claude Opus 5 | Google Vertex | 1,500,000 TPM
150 RPM | 250,000 TPM
50 RPM | 5,000,000 TPM
2,000 RPM | 8,000,000 TPM
3,000 RPM | 10,000,000 TPM
4,000 RPM | | Claude Opus 5 | Google Vertex (USG) | 1,500,000 TPM
150 RPM | 200,000 TPM
25 RPM | 5,000,000 TPM
2,000 RPM | 8,000,000 TPM
3,000 RPM | 10,000,000 TPM
4,000 RPM | | Claude Opus 5 | Amazon Bedrock (USG) | 1,500,000 TPM
150 RPM | 100,000 TPM
25 RPM | 2,500,000 TPM
1,250 RPM | 5,000,000 TPM
2,500 RPM | 7,500,000 TPM
3,750 RPM | | Claude Opus 5.5 | Amazon Bedrock | 1,500,000 TPM
150 RPM | 200,000 TPM
40 RPM | 3,000,000 TPM
300 RPM | 4,000,000 TPM
400 RPM | 6,000,000 TPM
600 RPM | | Claude Opus 5.5 | Anthropic | 1,500,000 TPM
150 RPM | 300,000 TPM
60 RPM | 1,000,000 TPM
200 RPM | 1,500,000 TPM
300 RPM | 2,000,000 TPM
400 RPM | | Claude Opus 5.5 | Azure | 1,500,000 TPM
150 RPM | 250,000 TPM
50 RPM | 1,000,000 TPM
100 RPM | 2,000,000 TPM
200 RPM | 3,000,000 TPM
300 RPM | | Claude Opus 5.5 | Google Vertex | 1,500,000 TPM
150 RPM | 250,000 TPM
50 RPM | 5,000,000 TPM
2,000 RPM | 8,000,000 TPM
3,000 RPM | 10,000,000 TPM
4,000 RPM | | Claude Opus 5.5 | Google Vertex (USG) | 1,500,000 TPM
150 RPM | 200,000 TPM
25 RPM | 5,000,000 TPM
2,000 RPM | 8,000,000 TPM
3,000 RPM | 10,000,000 TPM
4,000 RPM | | Claude Opus 5.5 | Amazon Bedrock (USG) | 1,500,000 TPM
150 RPM | 100,000 TPM
25 RPM | 2,500,000 TPM
1,250 RPM | 5,000,000 TPM
2,500 RPM | 7,500,000 TPM
3,750 RPM | | Claude Sonnet 4 | Google Vertex (USG) | 400,000 TPM
25 RPM | 100,000 TPM
25 RPM | 250,000 TPM
50 RPM | 375,000 TPM
75 RPM | 500,000 TPM
100 RPM | | Claude Sonnet 4.5 | Anthropic | 1,000,000 TPM
100 RPM | 80,000 TPM
16 RPM | 1,500,000 TPM
700 RPM | 2,000,000 TPM
800 RPM | 2,500,000 TPM
900 RPM | | Claude Sonnet 4.5 | Amazon Bedrock | 1,000,000 TPM
100 RPM | 50,000 TPM
10 RPM | 1,100,000 TPM
300 RPM | 4,100,000 TPM
600 RPM | 8,100,000 TPM
1,100 RPM | | Claude Sonnet 4.5 | Amazon Bedrock (USG) | 1,000,000 TPM
100 RPM | 100,000 TPM
25 RPM | 5,000,000 TPM
2,500 RPM | 7,500,000 TPM
3,750 RPM | 10,000,000 TPM
5,000 RPM | | Claude Sonnet 4.5 | Azure | 1,000,000 TPM
100 RPM | 60,000 TPM
12 RPM | 1,500,000 TPM
600 RPM | 2,500,000 TPM
700 RPM | 3,500,000 TPM
800 RPM | | Claude Sonnet 4.5 | Google Vertex | 1,000,000 TPM
100 RPM | 60,000 TPM
12 RPM | 1,000,000 TPM
500 RPM | 1,500,000 TPM
750 RPM | 2,000,000 TPM
1,000 RPM | | Claude Sonnet 4.5 | Google Vertex (USG) | 1,000,000 TPM
100 RPM | 100,000 TPM
25 RPM | 500,000 TPM
500 RPM | 750,000 TPM
750 RPM | 1,000,000 TPM
1,000 RPM | | Claude Sonnet 4.6 | Anthropic | 1,000,000 TPM
100 RPM | 80,000 TPM
16 RPM | 1,500,000 TPM
700 RPM | 2,000,000 TPM
800 RPM | 2,500,000 TPM
900 RPM | | Claude Sonnet 4.6 | Amazon Bedrock | 1,000,000 TPM
100 RPM | 50,000 TPM
10 RPM | 3,000,000 TPM
750 RPM | 6,000,000 TPM
1,500 RPM | 9,000,000 TPM
2,250 RPM | | Claude Sonnet 4.6 | Azure | 1,000,000 TPM
100 RPM | 60,000 TPM
12 RPM | 1,500,000 TPM
600 RPM | 2,500,000 TPM
700 RPM | 3,500,000 TPM
800 RPM | | Claude Sonnet 4.6 | Google Vertex | 1,000,000 TPM
100 RPM | 60,000 TPM
12 RPM | 4,000,000 TPM
2,000 RPM | 6,000,000 TPM
3,000 RPM | 8,000,000 TPM
4,000 RPM | | Claude Sonnet 4.6 | Google Vertex (USG) | 1,000,000 TPM
100 RPM | 100,000 TPM
25 RPM | 4,000,000 TPM
2,000 RPM | 6,000,000 TPM
3,000 RPM | 8,000,000 TPM
4,000 RPM | | Claude Sonnet 5 | Anthropic | 1,000,000 TPM
100 RPM | 300,000 TPM
60 RPM | 1,500,000 TPM
700 RPM | 2,000,000 TPM
800 RPM | 2,500,000 TPM
900 RPM | | Claude Sonnet 5 | Amazon Bedrock | 1,000,000 TPM
100 RPM | 200,000 TPM
40 RPM | 3,000,000 TPM
750 RPM | 6,000,000 TPM
1,500 RPM | 9,000,000 TPM
2,250 RPM | | Claude Sonnet 5 | Amazon Bedrock (USG) | 1,000,000 TPM
100 RPM | 100,000 TPM
25 RPM | 1,000,000 TPM
500 RPM | 2,000,000 TPM
1,000 RPM | 3,000,000 TPM
1,500 RPM | | Claude Sonnet 5 | Azure | 1,000,000 TPM
100 RPM | 250,000 TPM
50 RPM | 2,500,000 TPM
1,250 RPM | 5,000,000 TPM
2,500 RPM | 7,500,000 TPM
3,750 RPM | | Claude Sonnet 5 | Google Vertex | 1,000,000 TPM
100 RPM | 250,000 TPM
50 RPM | 4,000,000 TPM
2,000 RPM | 6,000,000 TPM
3,000 RPM | 8,000,000 TPM
4,000 RPM | | Claude Sonnet 5 | Google Vertex (USG) | 1,000,000 TPM
100 RPM | 200,000 TPM
25 RPM | 4,000,000 TPM
2,000 RPM | 6,000,000 TPM
3,000 RPM | 8,000,000 TPM
4,000 RPM | | Claude Sonnet 5.5 (Experimental) | Anthropic | 1,000,000 TPM
100 RPM | 300,000 TPM
60 RPM | 1,500,000 TPM
700 RPM | 2,000,000 TPM
800 RPM | 2,500,000 TPM
900 RPM | | Claude Sonnet 5.5 (Experimental) | Amazon Bedrock | 1,000,000 TPM
100 RPM | 200,000 TPM
40 RPM | 3,000,000 TPM
750 RPM | 6,000,000 TPM
1,500 RPM | 9,000,000 TPM
2,250 RPM | | Claude Sonnet 5.5 (Experimental) | Amazon Bedrock (USG) | 1,000,000 TPM
100 RPM | 100,000 TPM
25 RPM | 2,500,000 TPM
1,250 RPM | 5,000,000 TPM
2,500 RPM | 7,500,000 TPM
3,750 RPM | | Claude Sonnet 5.5 (Experimental) | Azure | 1,000,000 TPM
100 RPM | 250,000 TPM
50 RPM | 2,500,000 TPM
1,250 RPM | 5,000,000 TPM
2,500 RPM | 7,500,000 TPM
3,750 RPM | | Claude Sonnet 5.5 (Experimental) | Google Vertex | 1,000,000 TPM
100 RPM | 250,000 TPM
50 RPM | 4,000,000 TPM
2,000 RPM | 6,000,000 TPM
3,000 RPM | 8,000,000 TPM
4,000 RPM | | Claude Sonnet 5.5 (Experimental) | Google Vertex (USG) | 1,000,000 TPM
100 RPM | 200,000 TPM
25 RPM | 4,000,000 TPM
2,000 RPM | 6,000,000 TPM
3,000 RPM | 8,000,000 TPM
4,000 RPM | | Gemini 3 Flash (Preview) | Google Vertex | 2,000,000 TPM
400 RPM | 250,000 TPM
50 RPM | 6,500,000 TPM
1,400 RPM | 9,500,000 TPM
2,300 RPM | 12,500,000 TPM
3,500 RPM | | Gemini 3 Flash (Preview) | Google Vertex (USG) | 2,000,000 TPM
400 RPM | 100,000 TPM
25 RPM | 1,000,000 TPM
300 RPM | 1,500,000 TPM
600 RPM | 2,000,000 TPM
1,000 RPM | | Gemini 3.1 Flash-Lite | Google Vertex | 2,000,000 TPM
400 RPM | 250,000 TPM
50 RPM | 6,500,000 TPM
1,400 RPM | 9,500,000 TPM
2,300 RPM | 12,500,000 TPM
3,500 RPM | | Gemini 3.1 Flash-Lite | Google Vertex (USG) | 2,000,000 TPM
400 RPM | 100,000 TPM
100 RPM | 6,000,000 TPM
900 RPM | 9,000,000 TPM
1,800 RPM | 12,000,000 TPM
3,000 RPM | | Gemini 3.1 Pro (Preview) | Google Vertex | 2,000,000 TPM
400 RPM | 1,000,000 TPM
200 RPM | 7,000,000 TPM
1,500 RPM | 10,000,000 TPM
2,250 RPM | 15,000,000 TPM
3,750 RPM | | Gemini 3.1 Pro (Preview) | Google Vertex (USG) | 2,000,000 TPM
400 RPM | 1,000,000 TPM
600 RPM | 7,000,000 TPM
1,500 RPM | 10,000,000 TPM
2,250 RPM | 15,000,000 TPM
3,750 RPM | | Gemini 3.5 Flash | Google Vertex | 2,000,000 TPM
400 RPM | 250,000 TPM
50 RPM | 6,500,000 TPM
1,400 RPM | 9,500,000 TPM
2,300 RPM | 12,500,000 TPM
3,500 RPM | | Gemini 3.5 Flash | Google Vertex (USG) | 2,000,000 TPM
400 RPM | 1,000,000 TPM
200 RPM | 12,000,000 TPM
1,800 RPM | 18,000,000 TPM
3,600 RPM | 24,000,000 TPM
6,000 RPM | | Gemini 3.5 Flash-Lite | Google Vertex | 2,000,000 TPM
400 RPM | 1,000,000 TPM
200 RPM | 12,000,000 TPM
6,000 RPM | 18,000,000 TPM
9,000 RPM | 30,000,000 TPM
15,000 RPM | | Gemini 3.5 Flash-Lite | Google Vertex (USG) | 2,000,000 TPM
400 RPM | 1,000,000 TPM
600 RPM | 12,000,000 TPM
6,000 RPM | 18,000,000 TPM
9,000 RPM | 30,000,000 TPM
15,000 RPM | | Gemini 3.6 Flash | Google Vertex | 2,000,000 TPM
400 RPM | 250,000 TPM
50 RPM | 12,000,000 TPM
3,000 RPM | 18,000,000 TPM
4,500 RPM | 24,000,000 TPM
7,500 RPM | | Gemini 3.6 Flash | Google Vertex (USG IL2 / IL4) | 2,000,000 TPM
400 RPM | 1,000,000 TPM
200 RPM | 12,000,000 TPM
3,000 RPM | 18,000,000 TPM
4,500 RPM | 24,000,000 TPM
7,500 RPM | | Gemini 3.6 Flash | Google Vertex (USG IL5) | 2,000,000 TPM
400 RPM | 1,000,000 TPM
600 RPM | 7,000,000 TPM
3,000 RPM | 10,000,000 TPM
4,500 RPM | 15,000,000 TPM
7,500 RPM | | Gemini 3.7 Flash | Google Vertex | 2,000,000 TPM
400 RPM | 1,000,000 TPM
200 RPM | 12,000,000 TPM
6,000 RPM | 18,000,000 TPM
9,000 RPM | 30,000,000 TPM
15,000 RPM | | Gemini 3.7 Flash | Google Vertex (USG) | 2,000,000 TPM
400 RPM | 1,000,000 TPM
200 RPM | 12,000,000 TPM
6,000 RPM | 18,000,000 TPM
9,000 RPM | 30,000,000 TPM
15,000 RPM | | Llama 3.1 8b Instruct | Amazon Bedrock | 50,000 TPM
100 RPM | 150,000 TPM
30 RPM | 300,000 TPM
450 RPM | 450,000 TPM
675 RPM | 600,000 TPM
900 RPM | | Llama 3.1 8b Instruct | Palantir-hosted | 50,000 TPM
100 RPM | 100,000 TPM
20 RPM | 300,000 TPM
450 RPM | 450,000 TPM
675 RPM | 600,000 TPM
900 RPM | | Llama 3.3 70b Instruct | Amazon Bedrock | 50,000 TPM
100 RPM | 150,000 TPM
30 RPM | 300,000 TPM
450 RPM | 450,000 TPM
675 RPM | 600,000 TPM
900 RPM | | Llama 3.3 70b Instruct | Palantir-hosted | 50,000 TPM
100 RPM | 100,000 TPM
20 RPM | 300,000 TPM
450 RPM | 450,000 TPM
675 RPM | 600,000 TPM
900 RPM | | Llama 4 Maverick 17b 128E Instruct | Amazon Bedrock | 100,000 TPM
100 RPM | 250,000 TPM
50 RPM | 1,000,000 TPM
500 RPM | 2,000,000 TPM
1,000 RPM | 4,000,000 TPM
2,000 RPM | | Llama 4 Scout 17b 16E Instruct | Amazon Bedrock | 100,000 TPM
100 RPM | 150,000 TPM
30 RPM | 1,000,000 TPM
500 RPM | 2,000,000 TPM
1,000 RPM | 4,000,000 TPM
2,000 RPM | | Llama 4 Scout 17b 16E Instruct | Palantir-hosted | 100,000 TPM
100 RPM | 100,000 TPM
20 RPM | 300,000 TPM
450 RPM | 450,000 TPM
675 RPM | 600,000 TPM
900 RPM | | Llama 3.2 NV EmbedQA 1B v2 | Palantir-hosted | 50,000 TPM
100 RPM | 60,000 TPM
150 RPM | 300,000 TPM
450 RPM | 450,000 TPM
675 RPM | 600,000 TPM
900 RPM | | Llama 3.3 Nemotron Super 49b v1.5 | Palantir-hosted | 50,000 TPM
100 RPM | 100,000 TPM
25 RPM | 300,000 TPM
450 RPM | 450,000 TPM
675 RPM | 600,000 TPM
900 RPM | | NVIDIA Nemotron 3 Nano 30B | Amazon Bedrock | 50,000 TPM
100 RPM | 1,000,000 TPM
200 RPM | 5,000,000 TPM
500 RPM | 10,000,000 TPM
1,000 RPM | 20,000,000 TPM
2,000 RPM | | NVIDIA Nemotron 3 Super 120B | Amazon Bedrock | 1,000,000 TPM
100 RPM | 1,000,000 TPM
200 RPM | 5,000,000 TPM
500 RPM | 10,000,000 TPM
1,000 RPM | 20,000,000 TPM
2,000 RPM | | GPT-4.1 | Azure | 400,000 TPM
1,000 RPM | 100,000 TPM
20 RPM | 2,000,000 TPM
1,500 RPM | 3,500,000 TPM
2,500 RPM | 5,500,000 TPM
4,500 RPM | | GPT-4.1 | Azure (USG) | 400,000 TPM
1,000 RPM | 100,000 TPM
25 RPM | 2,000,000 TPM
2,000 RPM | 4,000,000 TPM
4,000 RPM | 6,000,000 TPM
6,000 RPM | | GPT-4.1 | OpenAI | 400,000 TPM
1,000 RPM | 150,000 TPM
30 RPM | 2,000,000 TPM
1,500 RPM | 3,500,000 TPM
2,500 RPM | 5,500,000 TPM
4,500 RPM | | GPT-4.1 mini | Azure | 1,000,000 TPM
1,000 RPM | 100,000 TPM
20 RPM | 15,000,000 TPM
7,500 RPM | 35,000,000 TPM
12,500 RPM | 55,000,000 TPM
17,500 RPM | | GPT-4.1 mini | Azure (USG) | 1,000,000 TPM
1,000 RPM | 100,000 TPM
100 RPM | 2,000,000 TPM
2,000 RPM | 3,000,000 TPM
3,000 RPM | 4,000,000 TPM
4,000 RPM | | GPT-4.1 mini | OpenAI | 1,000,000 TPM
1,000 RPM | 150,000 TPM
30 RPM | 3,000,000 TPM
2,000 RPM | 4,000,000 TPM
3,000 RPM | 6,000,000 TPM
5,000 RPM | | GPT-4.1 nano | Azure | 1,000,000 TPM
1,000 RPM | 100,000 TPM
20 RPM | 15,000,000 TPM
7,500 RPM | 35,000,000 TPM
12,500 RPM | 55,000,000 TPM
17,500 RPM | | GPT-4o | Azure | 400,000 TPM
800 RPM | 100,000 TPM
20 RPM | 1,000,000 TPM
1,000 RPM | 1,500,000 TPM
2,000 RPM | 3,000,000 TPM
4,000 RPM | | GPT-4o | Azure (USG) | 400,000 TPM
800 RPM | 100,000 TPM
25 RPM | 1,000,000 TPM
1,000 RPM | 1,500,000 TPM
2,000 RPM | 3,000,000 TPM
4,000 RPM | | GPT-4o | OpenAI | 400,000 TPM
800 RPM | 150,000 TPM
30 RPM | 1,000,000 TPM
1,000 RPM | 1,500,000 TPM
2,000 RPM | 3,000,000 TPM
4,000 RPM | | GPT-5 | Azure | 1,000,000 TPM
1,000 RPM | 100,000 TPM
20 RPM | 3,500,000 TPM
1,500 RPM | 5,500,000 TPM
3,000 RPM | 10,500,000 TPM
5,500 RPM | | GPT-5 Codex | Azure | 1,000,000 TPM
1,000 RPM | 100,000 TPM
25 RPM | 2,000,000 TPM
1,000 RPM | 3,000,000 TPM
2,000 RPM | 5,000,000 TPM
4,000 RPM | | GPT-5 mini | Azure | 1,000,000 TPM
1,000 RPM | 100,000 TPM
20 RPM | 10,500,000 TPM
5,500 RPM | 20,500,000 TPM
10,500 RPM | 30,500,000 TPM
15,500 RPM | | GPT-5 nano | Azure | 1,000,000 TPM
1,000 RPM | 100,000 TPM
20 RPM | 11,000,000 TPM
6,000 RPM | 31,000,000 TPM
16,000 RPM | 51,000,000 TPM
26,000 RPM | | GPT-5.1 | Azure | 1,000,000 TPM
2,000 RPM | 100,000 TPM
20 RPM | 2,000,000 TPM
500 RPM | 4,000,000 TPM
1,000 RPM | 6,000,000 TPM
2,000 RPM | | GPT-5.1 | Azure (USG) | 1,000,000 TPM
2,000 RPM | 100,000 TPM
25 RPM | 3,000,000 TPM
3,000 RPM | 5,250,000 TPM
5,250 RPM | 7,500,000 TPM
7,500 RPM | | GPT-5.1 | OpenAI | 1,000,000 TPM
2,000 RPM | 150,000 TPM
30 RPM | 1,500,000 TPM
1,000 RPM | 3,000,000 TPM
2,000 RPM | 5,000,000 TPM
4,000 RPM | | GPT-5.1 Codex | Azure | 1,000,000 TPM
1,000 RPM | 100,000 TPM
25 RPM | 2,000,000 TPM
1,000 RPM | 3,000,000 TPM
2,000 RPM | 4,000,000 TPM
4,000 RPM | | GPT-5.1 Codex mini | Azure | 1,000,000 TPM
500 RPM | 100,000 TPM
100 RPM | 2,000,000 TPM
1,000 RPM | 3,000,000 TPM
2,000 RPM | 5,000,000 TPM
4,000 RPM | | GPT-5.2 | Azure | 500,000 TPM
1,000 RPM | 100,000 TPM
20 RPM | 2,000,000 TPM
500 RPM | 4,000,000 TPM
1,000 RPM | 6,000,000 TPM
2,000 RPM | | GPT-5.2 | OpenAI | 500,000 TPM
1,000 RPM | 150,000 TPM
30 RPM | 3,000,000 TPM
1,500 RPM | 6,000,000 TPM
3,000 RPM | 10,000,000 TPM
5,000 RPM | | GPT-5.2 Pro | OpenAI | 400,000 TPM
1,000 RPM | 250,000 TPM
50 RPM | 1,500,000 TPM
1,000 RPM | 3,000,000 TPM
2,000 RPM | 5,000,000 TPM
4,000 RPM | | GPT-5.3 Codex | Azure | 1,000,000 TPM
1,000 RPM | 100,000 TPM
100 RPM | 4,000,000 TPM
2,000 RPM | 6,000,000 TPM
4,000 RPM | 8,000,000 TPM
8,000 RPM | | GPT-5.3 Codex | OpenAI | 1,000,000 TPM
1,000 RPM | 100,000 TPM
25 RPM | 3,000,000 TPM
1,000 RPM | 4,000,000 TPM
2,000 RPM | 5,000,000 TPM
4,000 RPM | | GPT-5.4 | Azure | 1,000,000 TPM
1,000 RPM | 100,000 TPM
20 RPM | 4,000,000 TPM
2,000 RPM | 6,000,000 TPM
3,000 RPM | 8,000,000 TPM
4,000 RPM | | GPT-5.4 | OpenAI | 1,000,000 TPM
1,000 RPM | 150,000 TPM
30 RPM | 3,000,000 TPM
1,500 RPM | 6,000,000 TPM
3,000 RPM | 10,000,000 TPM
5,000 RPM | | GPT-5.4 | Amazon Bedrock | 1,000,000 TPM
1,000 RPM | 100,000 TPM
50 RPM | 250,000 TPM
60 RPM | 500,000 TPM
125 RPM | 1,000,000 TPM
250 RPM | | GPT-5.4 | Amazon Bedrock (USG) | 1,000,000 TPM
1,000 RPM | 100,000 TPM
50 RPM | 250,000 TPM
60 RPM | 500,000 TPM
125 RPM | 1,000,000 TPM
250 RPM | | GPT-5.4 Pro | OpenAI | 400,000 TPM
1,000 RPM | 250,000 TPM
50 RPM | 1,500,000 TPM
1,000 RPM | 3,000,000 TPM
2,000 RPM | 5,000,000 TPM
4,000 RPM | | GPT-5.4 mini | Azure | 1,000,000 TPM
1,000 RPM | 100,000 TPM
20 RPM | 4,500,000 TPM
2,250 RPM | 9,000,000 TPM
4,500 RPM | 15,000,000 TPM
7,500 RPM | | GPT-5.4 mini | OpenAI | 1,000,000 TPM
1,000 RPM | 150,000 TPM
30 RPM | 3,000,000 TPM
1,500 RPM | 6,000,000 TPM
3,000 RPM | 10,000,000 TPM
5,000 RPM | | GPT-5.4 nano | Azure | 1,000,000 TPM
1,000 RPM | 100,000 TPM
20 RPM | 4,500,000 TPM
2,250 RPM | 9,000,000 TPM
4,500 RPM | 15,000,000 TPM
7,500 RPM | | GPT-5.4 nano | OpenAI | 1,000,000 TPM
1,000 RPM | 150,000 TPM
30 RPM | 3,000,000 TPM
1,500 RPM | 6,000,000 TPM
3,000 RPM | 10,000,000 TPM
5,000 RPM | | GPT-5.5 | Azure | 1,000,000 TPM
1,000 RPM | 100,000 TPM
20 RPM | 4,000,000 TPM
2,000 RPM | 6,000,000 TPM
3,000 RPM | 8,000,000 TPM
4,000 RPM | | GPT-5.5 | OpenAI | 1,000,000 TPM
1,000 RPM | 150,000 TPM
30 RPM | 3,000,000 TPM
1,500 RPM | 6,000,000 TPM
3,000 RPM | 10,000,000 TPM
5,000 RPM | | GPT-5.5 | Amazon Bedrock | 1,000,000 TPM
1,000 RPM | 100,000 TPM
50 RPM | 250,000 TPM
60 RPM | 500,000 TPM
125 RPM | 1,000,000 TPM
250 RPM | | GPT-5.6 Luna | Azure | 5,000,000 TPM
2,500 RPM | 1,000,000 TPM
200 RPM | 10,000,000 TPM
5,000 RPM | 20,000,000 TPM
10,000 RPM | 30,000,000 TPM
15,000 RPM | | GPT-5.6 Luna | OpenAI | 5,000,000 TPM
2,500 RPM | 3,000,000 TPM
600 RPM | 20,000,000 TPM
10,000 RPM | 40,000,000 TPM
20,000 RPM | 60,000,000 TPM
30,000 RPM | | GPT-5.6 Luna | Amazon Bedrock | 5,000,000 TPM
2,500 RPM | 250,000 TPM
50 RPM | 500,000 TPM
125 RPM | 1,000,000 TPM
250 RPM | 2,000,000 TPM
500 RPM | | GPT-5.6 Luna | Amazon Bedrock (USG) | 5,000,000 TPM
2,500 RPM | 100,000 TPM
50 RPM | 1,000,000 TPM
250 RPM | 2,000,000 TPM
500 RPM | 4,000,000 TPM
1,000 RPM | | GPT-5.6 Luna | Azure (USG) | 5,000,000 TPM
2,500 RPM | 250,000 TPM
125 RPM | 15,000,000 TPM
7,500 RPM | 30,000,000 TPM
15,000 RPM | 40,000,000 TPM
20,000 RPM | | GPT-5.6 Sol | Azure | 5,000,000 TPM
2,500 RPM | 1,000,000 TPM
200 RPM | 9,000,000 TPM
4,500 RPM | 10,000,000 TPM
5,000 RPM | 15,000,000 TPM
7,500 RPM | | GPT-5.6 Sol | OpenAI | 5,000,000 TPM
2,500 RPM | 3,000,000 TPM
600 RPM | 20,000,000 TPM
10,000 RPM | 40,000,000 TPM
20,000 RPM | 60,000,000 TPM
30,000 RPM | | GPT-5.6 Sol | Azure (USG) | 5,000,000 TPM
2,500 RPM | 250,000 TPM
125 RPM | 10,000,000 TPM
5,000 RPM | 20,000,000 TPM
10,000 RPM | 40,000,000 TPM
20,000 RPM | | GPT-5.6 Terra | Azure | 5,000,000 TPM
2,500 RPM | 1,000,000 TPM
200 RPM | 10,000,000 TPM
5,000 RPM | 20,000,000 TPM
10,000 RPM | 30,000,000 TPM
15,000 RPM | | GPT-5.6 Terra | OpenAI | 5,000,000 TPM
2,500 RPM | 3,000,000 TPM
600 RPM | 30,000,000 TPM
15,000 RPM | 50,000,000 TPM
25,000 RPM | 70,000,000 TPM
35,000 RPM | | GPT-5.6 Terra | Amazon Bedrock | 5,000,000 TPM
2,500 RPM | 250,000 TPM
50 RPM | 500,000 TPM
125 RPM | 1,000,000 TPM
250 RPM | 2,000,000 TPM
500 RPM | | GPT-5.6 Terra | Amazon Bedrock (USG) | 5,000,000 TPM
2,500 RPM | 100,000 TPM
50 RPM | 1,000,000 TPM
250 RPM | 2,000,000 TPM
500 RPM | 4,000,000 TPM
1,000 RPM | | GPT-5.6 Terra | Azure (USG) | 5,000,000 TPM
2,500 RPM | 250,000 TPM
125 RPM | 15,000,000 TPM
7,500 RPM | 30,000,000 TPM
15,000 RPM | 40,000,000 TPM
20,000 RPM | | GPT-6 Astra | Amazon Bedrock | 2,000,000 TPM
100 RPM | 250,000 TPM
50 RPM | 300,000 TPM
60 RPM | 500,000 TPM
125 RPM | 1,000,000 TPM
250 RPM | | GPT-6 Astra | OpenAI | 2,000,000 TPM
100 RPM | 250,000 TPM
50 RPM | 20,000,000 TPM
10,000 RPM | 40,000,000 TPM
20,000 RPM | 60,000,000 TPM
30,000 RPM | | GPT-6 Astra | Azure | 2,000,000 TPM
100 RPM | 1,000,000 TPM
200 RPM | 9,000,000 TPM
4,500 RPM | 10,000,000 TPM
5,000 RPM | 15,000,000 TPM
7,500 RPM | | GPT-6 Luna | OpenAI | 5,000,000 TPM
2,500 RPM | 3,000,000 TPM
600 RPM | 30,000,000 TPM
15,000 RPM | 50,000,000 TPM
25,000 RPM | 70,000,000 TPM
35,000 RPM | | GPT-6 Luna | Amazon Bedrock | 5,000,000 TPM
2,500 RPM | 250,000 TPM
50 RPM | 500,000 TPM
125 RPM | 1,000,000 TPM
250 RPM | 2,000,000 TPM
500 RPM | | GPT-6 Luna | Azure | 5,000,000 TPM
2,500 RPM | 1,000,000 TPM
200 RPM | 10,000,000 TPM
5,000 RPM | 20,000,000 TPM
10,000 RPM | 30,000,000 TPM
15,000 RPM | | GPT-6 Sol | OpenAI | 5,000,000 TPM
2,500 RPM | 3,000,000 TPM
600 RPM | 30,000,000 TPM
15,000 RPM | 50,000,000 TPM
25,000 RPM | 70,000,000 TPM
35,000 RPM | | GPT-6 Sol | Amazon Bedrock | 5,000,000 TPM
2,500 RPM | 250,000 TPM
50 RPM | 300,000 TPM
60 RPM | 500,000 TPM
125 RPM | 1,000,000 TPM
250 RPM | | GPT-6 Sol | Azure | 5,000,000 TPM
2,500 RPM | 1,000,000 TPM
200 RPM | 9,000,000 TPM
4,500 RPM | 10,000,000 TPM
5,000 RPM | 15,000,000 TPM
7,500 RPM | | GPT-6.1 Sol (Experimental) | OpenAI | 5,000,000 TPM
2,500 RPM | 3,000,000 TPM
600 RPM | 30,000,000 TPM
15,000 RPM | 50,000,000 TPM
25,000 RPM | 70,000,000 TPM
35,000 RPM | | GPT-6.1 Sol (Experimental) | Amazon Bedrock | 5,000,000 TPM
2,500 RPM | 250,000 TPM
50 RPM | 300,000 TPM
60 RPM | 500,000 TPM
125 RPM | 1,000,000 TPM
250 RPM | | GPT-6.1 Sol (Experimental) | Azure | 5,000,000 TPM
2,500 RPM | 1,000,000 TPM
200 RPM | 9,000,000 TPM
4,500 RPM | 10,000,000 TPM
5,000 RPM | 15,000,000 TPM
7,500 RPM | | GPT-OSS-120B | Palantir-hosted | 50,000 TPM
100 RPM | 100,000 TPM
25 RPM | 300,000 TPM
450 RPM | 450,000 TPM
675 RPM | 600,000 TPM
900 RPM | | GPT-OSS-20B | Palantir-hosted | 50,000 TPM
100 RPM | 100,000 TPM
100 RPM | 300,000 TPM
450 RPM | 450,000 TPM
675 RPM | 600,000 TPM
900 RPM | | Text Embedding 3 Large | Azure | 1,000,000 TPM
1,500 RPM | 1,060,000 TPM
1,400 RPM | 2,250,000 TPM
3,500 RPM | 3,500,000 TPM
4,750 RPM | 4,750,000 TPM
8,500 RPM | | Text Embedding 3 Large | Azure (USG) | 1,000,000 TPM
1,500 RPM | 60,000 TPM
400 RPM | 1,000,000 TPM
2,000 RPM | 2,000,000 TPM
3,000 RPM | 3,000,000 TPM
6,000 RPM | | Text Embedding 3 Large | OpenAI | 1,000,000 TPM
1,500 RPM | 60,000 TPM
400 RPM | 1,250,000 TPM
2,500 RPM | 2,500,000 TPM
3,750 RPM | 3,750,000 TPM
7,500 RPM | | Text Embedding 3 Small | Azure | 1,000,000 TPM
1,500 RPM | 1,060,000 TPM
1,400 RPM | 1,625,000 TPM
3,500 RPM | 2,250,000 TPM
4,750 RPM | 2,875,000 TPM
8,500 RPM | | Text Embedding 3 Small | Azure (USG) | 1,000,000 TPM
1,500 RPM | 60,000 TPM
400 RPM | 500,000 TPM
2,000 RPM | 1,000,000 TPM
3,000 RPM | 1,500,000 TPM
6,000 RPM | | Text Embedding 3 Small | OpenAI | 1,000,000 TPM
1,500 RPM | 60,000 TPM
400 RPM | 625,000 TPM
2,500 RPM | 1,250,000 TPM
3,750 RPM | 1,875,000 TPM
7,500 RPM | | Whisper 1 | OpenAI | 1 TPM
50 RPM | 1 TPM
100 RPM | 2 TPM
500 RPM | 3 TPM
1,000 RPM | 4 TPM
2,000 RPM | | o1 | Azure | 600,000 TPM
5 RPM | 100,000 TPM
25 RPM | 250,000 TPM
50 RPM | 400,000 TPM
60 RPM | 750,000 TPM
75 RPM | | o3 | Azure | 400,000 TPM
100 RPM | 600,000 TPM
525 RPM | 1,500,000 TPM
1,500 RPM | 2,500,000 TPM
2,500 RPM | 4,500,000 TPM
4,500 RPM | | o3-mini | Azure (USG) | 300,000 TPM
30 RPM | 100,000 TPM
25 RPM | 1,000,000 TPM
100 RPM | 2,000,000 TPM
200 RPM | 4,000,000 TPM
400 RPM | | o4-mini | Azure | 300,000 TPM
100 RPM | 1,100,000 TPM
1,025 RPM | 2,000,000 TPM
2,000 RPM | 3,000,000 TPM
3,000 RPM | 5,000,000 TPM
5,000 RPM | | text-embedding-ada-002 | Azure | 1,000,000 TPM
1,500 RPM | 1,450,000 TPM
1,450 RPM | 3,625,000 TPM
3,625 RPM | 4,875,000 TPM
4,875 RPM | 6,250,000 TPM
6,250 RPM | | text-embedding-ada-002 | Azure (USG) | 1,000,000 TPM
1,500 RPM | 450,000 TPM
450 RPM | 3,000,000 TPM
3,500 RPM | 4,000,000 TPM
4,500 RPM | 5,000,000 TPM
5,500 RPM | | text-embedding-ada-002 | OpenAI | 1,000,000 TPM
1,500 RPM | 950,000 TPM
950 RPM | 3,125,000 TPM
3,125 RPM | 4,437,500 TPM
4,438 RPM | 5,750,000 TPM
5,750 RPM | | Document Information Extraction | Palantir-hosted | 1,000,000 TPM
40 RPM | 1,000,000 TPM
40 RPM | 1,500,000 TPM
300 RPM | 2,000,000 TPM
450 RPM | 3,000,000 TPM
600 RPM | | Gemma 4 26B A4B | Amazon Bedrock | 50,000 TPM
100 RPM | 900,000 TPM
180 RPM | 5,000,000 TPM
500 RPM | 10,000,000 TPM
1,000 RPM | 20,000,000 TPM
2,000 RPM | | Gemma 4 26B A4B | Palantir-hosted | 50,000 TPM
100 RPM | 100,000 TPM
20 RPM | 300,000 TPM
450 RPM | 450,000 TPM
675 RPM | 600,000 TPM
900 RPM | | Gemma 4 31B | Amazon Bedrock | 1,000,000 TPM
100 RPM | 1,000,000 TPM
200 RPM | 5,000,000 TPM
500 RPM | 10,000,000 TPM
1,000 RPM | 20,000,000 TPM
2,000 RPM | | Schematic 7B | Palantir-hosted | 50,000 TPM
100 RPM | 60,000 TPM
150 RPM | 300,000 TPM
450 RPM | 450,000 TPM
675 RPM | 600,000 TPM
900 RPM | | Whisper Large V3 | Palantir-hosted | 50,000 TPM
100 RPM | 60,000 TPM
150 RPM | 300,000 TPM
450 RPM | 450,000 TPM
675 RPM | 600,000 TPM
900 RPM | | Snowflake Arctic Embed Medium | Palantir-hosted | 500,000 TPM
500 RPM | 60,000 TPM
150 RPM | 300,000 TPM
450 RPM | 450,000 TPM
675 RPM | 600,000 TPM
900 RPM | | Grok 4.3 | xAI | 500,000 TPM
100 RPM | 250,000 TPM
50 RPM | 1,000,000 TPM
200 RPM | 1,500,000 TPM
300 RPM | 2,000,000 TPM
400 RPM | | Grok 4.5 | xAI | 1,000,000 TPM
200 RPM | 250,000 TPM
50 RPM | 3,000,000 TPM
800 RPM | 4,000,000 TPM
1,200 RPM | 5,000,000 TPM
1,600 RPM | | Grok 420 Non-Reasoning Latest | xAI | 500,000 TPM
100 RPM | 250,000 TPM
50 RPM | 1,000,000 TPM
200 RPM | 1,500,000 TPM
300 RPM | 2,000,000 TPM
400 RPM | | Grok 420 Reasoning Latest | xAI | 500,000 TPM
100 RPM | 250,000 TPM
50 RPM | 1,000,000 TPM
200 RPM | 1,500,000 TPM
300 RPM | 2,000,000 TPM
400 RPM | | Grok Build 0.1 | xAI | 400,000 TPM
100 RPM | 250,000 TPM
50 RPM | 1,000,000 TPM
200 RPM | 1,500,000 TPM
300 RPM | 2,000,000 TPM
400 RPM | | DeepSeek V3.2 | Amazon Bedrock | 1,000,000 TPM
100 RPM | 1,000,000 TPM
200 RPM | 5,000,000 TPM
500 RPM | 10,000,000 TPM
1,000 RPM | 20,000,000 TPM
2,000 RPM | | DeepSeek V4.1 Flash | Fireworks | 1,000,000 TPM
100 RPM | 100,000 TPM
100 RPM | 2,000,000 TPM
2,000 RPM | 4,000,000 TPM
4,000 RPM | 6,000,000 TPM
6,000 RPM | | DeepSeek V4.1 Flash (1017) (Experimental) | Fireworks | 1,000,000 TPM
100 RPM | 100,000 TPM
100 RPM | 2,000,000 TPM
2,000 RPM | 4,000,000 TPM
4,000 RPM | 6,000,000 TPM
6,000 RPM | | Gemini 3.8 Flash | Google Vertex | 2,000,000 TPM
400 RPM | 1,000,000 TPM
200 RPM | 12,000,000 TPM
6,000 RPM | 18,000,000 TPM
9,000 RPM | 30,000,000 TPM
15,000 RPM | | Gemini 3.8 Flash | Google Vertex (USG) | 2,000,000 TPM
400 RPM | 1,000,000 TPM
200 RPM | 12,000,000 TPM
6,000 RPM | 18,000,000 TPM
9,000 RPM | 30,000,000 TPM
15,000 RPM | | Gemini 4 Argon (Experimental) | Google Vertex | 2,000,000 TPM
400 RPM | 1,000,000 TPM
200 RPM | 7,000,000 TPM
1,500 RPM | 10,000,000 TPM
2,250 RPM | 15,000,000 TPM
3,750 RPM | | Gemini 4 Argon (Experimental) | Google Vertex (USG) | 2,000,000 TPM
400 RPM | 1,000,000 TPM
600 RPM | 7,000,000 TPM
1,500 RPM | 10,000,000 TPM
2,250 RPM | 15,000,000 TPM
3,750 RPM | | Grok 4.6 | xAI | 1,000,000 TPM
200 RPM | 1,000,000 TPM
200 RPM | 3,000,000 TPM
800 RPM | 4,000,000 TPM
1,200 RPM | 5,000,000 TPM
1,600 RPM | | Grok 4.7 | xAI | 1,000,000 TPM
200 RPM | 1,000,000 TPM
200 RPM | 3,000,000 TPM
800 RPM | 4,000,000 TPM
1,200 RPM | 5,000,000 TPM
1,600 RPM | | Kimi K2.5 | Amazon Bedrock | 1,000,000 TPM
100 RPM | 1,000,000 TPM
200 RPM | 5,000,000 TPM
500 RPM | 10,000,000 TPM
1,000 RPM | 20,000,000 TPM
2,000 RPM | | NVIDIA Nemotron 3 Super 120B FP8 | Palantir-hosted | 50,000 TPM
100 RPM | 100,000 TPM
25 RPM | 300,000 TPM
450 RPM | 450,000 TPM
675 RPM | 600,000 TPM
900 RPM | | Z.ai GLM-5 | Amazon Bedrock | 1,000,000 TPM
100 RPM | 1,000,000 TPM
200 RPM | 5,000,000 TPM
500 RPM | 10,000,000 TPM
1,000 RPM | 20,000,000 TPM
2,000 RPM | | Kimi K3 | Fireworks | 1,000,000 TPM
100 RPM | 100,000 TPM
100 RPM | 2,000,000 TPM
2,000 RPM | 4,000,000 TPM
4,000 RPM | 6,000,000 TPM
6,000 RPM | | Kimi K3 | Amazon Bedrock | 1,000,000 TPM
100 RPM | 1,000,000 TPM
200 RPM | 5,000,000 TPM
500 RPM | 10,000,000 TPM
1,000 RPM | 20,000,000 TPM
2,000 RPM | | Qwen3 235B A22B 2507 | Amazon Bedrock | 1,000,000 TPM
100 RPM | 250,000 TPM
50 RPM | 5,000,000 TPM
500 RPM | 10,000,000 TPM
1,000 RPM | 20,000,000 TPM
2,000 RPM | | Qwen3 32B | Amazon Bedrock | 1,000,000 TPM
100 RPM | 250,000 TPM
50 RPM | 5,000,000 TPM
500 RPM | 10,000,000 TPM
1,000 RPM | 20,000,000 TPM
2,000 RPM | | Z.ai GLM-5.3 | Fireworks | 1,000,000 TPM
100 RPM | 100,000 TPM
100 RPM | 2,000,000 TPM
2,000 RPM | 4,000,000 TPM
4,000 RPM | 6,000,000 TPM
6,000 RPM | | Z.ai GLM-5.3 | Amazon Bedrock | 1,000,000 TPM
100 RPM | 1,000,000 TPM
200 RPM | 5,000,000 TPM
500 RPM | 10,000,000 TPM
1,000 RPM | 20,000,000 TPM
2,000 RPM | | Z.ai GLM-5.3 Flash | Fireworks | 1,000,000 TPM
100 RPM | 100,000 TPM
100 RPM | 2,000,000 TPM
2,000 RPM | 4,000,000 TPM
4,000 RPM | 6,000,000 TPM
6,000 RPM |