Tier 3 Model Rate Limits
This page shows the rate limits for all models available in Tier 3 (Tier 3).
All Tier Rate Limits
Tier Overview
Tier 3 is built for organizations with demanding workloads. You unlock it once your cumulative top-ups reach $50 USD equivalent. At Tier 3 you get high rate limits across virtually every model in the catalogue — ideal for businesses integrating AI deeply into their core products, customer-facing features, and high-traffic services. The next step up is Tier 4 at $250 cumulative.
Qualification & Usage limits
| Tier | Qualification | Usage limits |
|---|---|---|
| 3 | $50 USD equivalent cumulative top-ups | Up to account balance |
Model Rate Limits
| Model | Requests Per Minute (RPM) | Tokens Per Minute (TPM) | Provider | Owner |
|---|---|---|---|---|
| anthropic.claude-haiku-4-5-20251001-v1:0 | 5.0 | 200000.0 | bedrock | anthropic |
| anthropic.claude-opus-4-5-20251101-v1:0 | 10.0 | 150000.0 | bedrock | anthropic |
| anthropic.claude-opus-4-6-v1 | 10.0 | 150000.0 | bedrock | anthropic |
| anthropic.claude-opus-4-7 | 50.0 | 800000.0 | bedrock | anthropic |
| anthropic.claude-opus-4-8 | 50.0 | 800000.0 | bedrock | anthropic |
| anthropic.claude-sonnet-4-5-20250929-v1:0 | 25.0 | 100000.0 | bedrock | anthropic |
| anthropic.claude-sonnet-4-6 | 10.0 | 150000.0 | bedrock | anthropic |
| cf.deepseek-r1-distill-qwen-32b | 750.0 | 1200000.0 | cloudflare | deepseek |
| cf.embeddinggemma-300m | 500.0 | 400000.0 | cloudflare | |
| cf.flux-2-dev | 50.0 | N/A | cloudflare | BFL |
| cf.flux-2-klein-4b | 50.0 | N/A | cloudflare | BFL |
| cf.flux-2-klein-9b | 50.0 | N/A | cloudflare | BFL |
| cf.gemma-3-12b-it | 750.0 | 1200000.0 | cloudflare | |
| cf.gemma-4-26b-a4b-it | 100.0 | 200000.0 | cloudflare | |
| cf.gemma-sea-lion-v4-27b-it | 750.0 | 1200000.0 | cloudflare | |
| cf.glm-5.2 | 100.0 | 400000.0 | cloudflare | |
| cf.gpt-oss-120b | 500.0 | 400000.0 | cloudflare | openai |
| cf.gpt-oss-20b | 500.0 | 400000.0 | cloudflare | openai |
| cf.granite-4.0-h-micro | 500.0 | 400000.0 | cloudflare | ibm |
| cf.kimi-k2.7-code | 100.0 | 400000.0 | cloudflare | |
| cf.llama-3.1-8b-instruct-fast | 750.0 | 1200000.0 | cloudflare | meta |
| cf.llama-3.2-1b-instruct | 750.0 | 1200000.0 | cloudflare | meta |
| cf.llama-3.2-3b-instruct | 750.0 | 1200000.0 | cloudflare | meta |
| cf.llama-3.3-70b-instruct-fp8-fast | 750.0 | 1200000.0 | cloudflare | meta |
| cf.llama-4-scout-17b-16e-instruct | 750.0 | 1200000.0 | cloudflare | meta |
| cf.llama-guard-3-8b | 750.0 | 1200000.0 | cloudflare | meta |
| cf.lucid-origin | 50.0 | N/A | cloudflare | BFL |
| cf.mistral-small-3.1-24b-instruct | 750.0 | 1200000.0 | cloudflare | mistral ai |
| cf.nemotron-3-120b-a12b | 500.0 | 400000.0 | cloudflare | openai |
| cf.phoenix-1.0 | 50.0 | N/A | cloudflare | BFL |
| cf.plamo-embedding-1b | 500.0 | 400000.0 | cloudflare | pfn |
| cf.qwen2.5-coder-32b-instruct | 750.0 | 1200000.0 | cloudflare | alibaba |
| cf.qwen3-30b-a3b-fp8 | 500.0 | 400000.0 | cloudflare | alibaba |
| cf.qwq-32b | 750.0 | 1200000.0 | cloudflare | alibaba |
| claude-fable-5 | 50.0 | 800000.0 | anthropic | anthropic |
| claude-haiku-4-5 | 250.0 | 1000000.0 | anthropic | anthropic |
| claude-opus-4-5 | 250.0 | 800000.0 | anthropic | anthropic |
| claude-opus-4-6 | 50.0 | 800000.0 | anthropic | anthropic |
| claude-opus-4-7 | 50.0 | 800000.0 | anthropic | anthropic |
| claude-opus-4-8 | 50.0 | 800000.0 | anthropic | anthropic |
| claude-opus-5 | 50.0 | 800000.0 | anthropic | anthropic |
| claude-sonnet-4-5 | 250.0 | 800000.0 | anthropic | anthropic |
| claude-sonnet-4-6 | 250.0 | 800000.0 | anthropic | anthropic |
| claude-sonnet-5 | 250.0 | 800000.0 | anthropic | anthropic |
| codex-auto-review | 1000.0 | 2000000.0 | openai | openai |
| cohere-rerank-v4.0-fast | 100.0 | N/A | azure | cohere |
| cohere-rerank-v4.0-pro | 100.0 | N/A | azure | cohere |
| cohere.command-light-text-v14 | 50.0 | 200000.0 | bedrock | cohere |
| cohere.command-r-plus-v1:0 | 50.0 | 200000.0 | bedrock | cohere |
| cohere.command-r-v1:0 | 50.0 | 200000.0 | bedrock | cohere |
| cohere.command-text-v14 | 50.0 | 200000.0 | bedrock | cohere |
| cohere.embed-multilingual-v3 | 50.0 | 200000.0 | bedrock | cohere |
| cohere.embed-v4:0 | 50.0 | 200000.0 | bedrock | cohere |
| cohere.rerank-v3-5:0 | 150.0 | N/A | bedrock | cohere |
| computer-use-preview | 1000.0 | 10000000.0 | openai | openai |
| computer-use-preview-2025-03-11 | 1000.0 | 10000000.0 | openai | openai |
| dataforseo-search | 75.0 | N/A | dataforseo | dataforseo |
| deepseek-chat | 1500.0 | 4000000.0 | deepseek | deepseek |
| deepseek-coder | 1500.0 | 4000000.0 | deepseek | deepseek |
| deepseek-reasoner | 1500.0 | 4000000.0 | deepseek | deepseek |
| deepseek-v3-0324 | 1500.0 | 2000000.0 | azure | deepseek |
| deepseek-v3.1 | 1500.0 | 2000000.0 | azure | deepseek |
| deepseek-v3.2 | 1500.0 | 2000000.0 | azure | deepseek |
| deepseek-v3.2-speciale | 1500.0 | 2000000.0 | azure | deepseek |
| deepseek-v4-flash | 1500.0 | 4000000.0 | deepseek | deepseek |
| deepseek-v4-pro | 500.0 | 4000000.0 | deepseek | deepseek |
| eleven_flash_v2 | 500.0 | N/A | elevenlabs | elevenlabs |
| eleven_flash_v2_5 | 500.0 | N/A | elevenlabs | elevenlabs |
| eleven_multilingual_v2 | 500.0 | N/A | elevenlabs | elevenlabs |
| eleven_turbo_v2 | 500.0 | N/A | elevenlabs | elevenlabs |
| eleven_turbo_v2_5 | 500.0 | N/A | elevenlabs | elevenlabs |
| eleven_v3 | 500.0 | N/A | elevenlabs | elevenlabs |
| embed-v-4-0 | 75.0 | N/A | azure | cohere |
| exa_ai-search | 75.0 | N/A | exa_ai | exa_ai |
| firecrawl-search | 75.0 | N/A | firecrawl | firecrawl |
| flux-1.1-pro | 50.0 | N/A | azure | BFL |
| flux.1-kontext-pro | 50.0 | N/A | azure | BFL |
| flux.2-pro | 25.0 | N/A | azure | BFL |
| gemini-2.5-flash | 1000.0 | 8000000.0 | gemini | |
| gemini-2.5-flash-image | 50.0 | 2000000.0 | gemini | |
| gemini-2.5-flash-lite | 1000.0 | 3000000.0 | gemini | |
| gemini-2.5-flash-lite-preview-09-2025 | 500.0 | 3000000.0 | gemini | |
| gemini-2.5-flash-preview-09-2025 | 500.0 | 8000000.0 | gemini | |
| gemini-2.5-flash-preview-tts | 500.0 | 3000000.0 | gemini | |
| gemini-2.5-flash-tts | 500.0 | 3000000.0 | vertex_ai | |
| gemini-2.5-pro | 500.0 | 3000000.0 | gemini | |
| gemini-2.5-pro-preview-tts | 500.0 | 3000000.0 | gemini | |
| gemini-2.5-pro-tts | 500.0 | 3000000.0 | vertex_ai | |
| gemini-3-flash-preview | 1000.0 | 2000000.0 | gemini | |
| gemini-3-pro-image | 25.0 | 450000.0 | gemini | |
| gemini-3-pro-image-preview | 25.0 | 450000.0 | gemini | |
| gemini-3.1-flash-image | 25.0 | 450000.0 | gemini | |
| gemini-3.1-flash-image-preview | 25.0 | 450000.0 | gemini | |
| gemini-3.1-flash-lite | 1000.0 | 3000000.0 | gemini | |
| gemini-3.1-flash-lite-image | 25.0 | 450000.0 | gemini | |
| gemini-3.1-flash-lite-preview | 1000.0 | 3000000.0 | gemini | |
| gemini-3.1-pro-preview | 250.0 | 4000000.0 | gemini | |
| gemini-3.5-flash | 1000.0 | 2000000.0 | gemini | |
| gemini-3.5-flash-lite | 1000.0 | 3000000.0 | gemini | |
| gemini-3.6-flash | 1000.0 | 2000000.0 | gemini | |
| gemini-embedding-001 | 500.0 | 3000000.0 | gemini | |
| gemini-embedding-2 | 500.0 | 3000000.0 | gemini | |
| gemini-flash-latest | 500.0 | 2000000.0 | gemini | |
| gemini-flash-lite-latest | 500.0 | 5000000.0 | gemini | |
| gemini-robotics-er-1.5-preview | 500.0 | 3000000.0 | gemini | |
| gemma-4-26b-a4b-it | 450.0 | 1000000.0 | gemini | |
| gemma-4-31b-it | 15.0 | 20000.0 | gemini | |
| gen4.5 | 5.0 | N/A | runwayml | runwayml |
| gen4_image | 25.0 | N/A | runwayml | runwayml |
| gen4_image_turbo | 25.0 | N/A | runwayml | runwayml |
| gen4_turbo | 5.0 | N/A | runwayml | runwayml |
| glm-5.1 | 500.0 | 4000000.0 | zai | zai |
| glm-5.2 | 500.0 | 4000000.0 | zai | zai |
| gpt-4-0613 | 5000.0 | 80000.0 | openai | openai |
| gpt-4.1 | 5000.0 | 4000000.0 | openai | openai |
| gpt-4.1-2025-04-14 | 5000.0 | 4000000.0 | openai | openai |
| gpt-4.1-mini | 5000.0 | 10000000.0 | openai | openai |
| gpt-4.1-mini-2025-04-14 | 5000.0 | 10000000.0 | openai | openai |
| gpt-4.1-nano | 5000.0 | 10000000.0 | openai | openai |
| gpt-4.1-nano-2025-04-14 | 5000.0 | 10000000.0 | openai | openai |
| gpt-4o | 5000.0 | 4000000.0 | openai | openai |
| gpt-4o-2024-05-13 | 5000.0 | 800000.0 | openai | openai |
| gpt-4o-2024-08-06 | 5000.0 | 800000.0 | openai | openai |
| gpt-4o-2024-11-20 | 5000.0 | 4000000.0 | openai | openai |
| gpt-4o-mini | 7500.0 | 5000000.0 | openai | openai |
| gpt-4o-mini-2024-07-18 | 5000.0 | 5000000.0 | openai | openai |
| gpt-4o-mini-search-preview | 500.0 | 1000000.0 | openai | openai |
| gpt-4o-mini-search-preview-2025-03-11 | 500.0 | 1000000.0 | openai | openai |
| gpt-4o-mini-transcribe | 3500.0 | 1000000.0 | openai | openai |
| gpt-4o-mini-tts | 1500.0 | 600000.0 | openai | openai |
| gpt-4o-search-preview | 500.0 | 1000000.0 | openai | openai |
| gpt-4o-search-preview-2025-03-11 | 500.0 | 1000000.0 | openai | openai |
| gpt-4o-transcribe | 3500.0 | 2000000.0 | openai | openai |
| gpt-4o-transcribe-diarize | 3500.0 | 2000000.0 | openai | openai |
| gpt-5 | 750.0 | 2000000.0 | openai | openai |
| gpt-5-2025-08-07 | 750.0 | 2000000.0 | openai | openai |
| gpt-5-chat | 750.0 | 2000000.0 | openai | openai |
| gpt-5-chat-latest | 750.0 | 2000000.0 | openai | openai |
| gpt-5-codex | 750.0 | 2000000.0 | openai | openai |
| gpt-5-mini | 750.0 | 4000000.0 | openai | openai |
| gpt-5-mini-2025-08-07 | 750.0 | 4000000.0 | openai | openai |
| gpt-5-nano | 750.0 | 4000000.0 | openai | openai |
| gpt-5-nano-2025-08-07 | 750.0 | 4000000.0 | openai | openai |
| gpt-5-pro | 50.0 | 800000.0 | openai | openai |
| gpt-5-pro-2025-10-06 | 50.0 | 800000.0 | openai | openai |
| gpt-5.1 | 1000.0 | 2000000.0 | openai | openai |
| gpt-5.1-2025-11-13 | 1000.0 | 2000000.0 | openai | openai |
| gpt-5.1-chat | 750.0 | 2000000.0 | openai | openai |
| gpt-5.1-codex | 1000.0 | 2000000.0 | openai | openai |
| gpt-5.1-codex-max | 1000.0 | 2000000.0 | openai | openai |
| gpt-5.1-codex-mini | 1000.0 | 2000000.0 | openai | openai |
| gpt-5.2 | 1000.0 | 2000000.0 | openai | openai |
| gpt-5.2-2025-12-11 | 1000.0 | 2000000.0 | openai | openai |
| gpt-5.2-chat | 1000.0 | 2000000.0 | openai | openai |
| gpt-5.2-codex | 1000.0 | 2000000.0 | openai | openai |
| gpt-5.2-pro | 25.0 | 2000000.0 | openai | openai |
| gpt-5.2-pro-2025-12-11 | 25.0 | 2000000.0 | openai | openai |
| gpt-5.3-chat | 1000.0 | 2000000.0 | openai | openai |
| gpt-5.3-codex | 1000.0 | 4000000.0 | openai | openai |
| gpt-5.4 | 1000.0 | 4000000.0 | openai | openai |
| gpt-5.4-mini | 50.0 | 800000.0 | openai | openai |
| gpt-5.4-nano | 50.0 | 800000.0 | openai | openai |
| gpt-5.4-pro | 50.0 | 800000.0 | openai | openai |
| gpt-5.5 | 250.0 | 4000000.0 | openai | openai |
| gpt-5.6-luna | 250.0 | 4000000.0 | openai | openai |
| gpt-5.6-sol | 250.0 | 4000000.0 | openai | openai |
| gpt-5.6-terra | 250.0 | 4000000.0 | openai | openai |
| gpt-audio | 1500.0 | 800000.0 | openai | openai |
| gpt-audio-1.5 | 1500.0 | 800000.0 | openai | openai |
| gpt-audio-2025-08-28 | 1500.0 | 800000.0 | openai | openai |
| gpt-audio-mini | 1500.0 | 800000.0 | openai | openai |
| gpt-audio-mini-2025-10-06 | 1500.0 | 800000.0 | openai | openai |
| gpt-image-1 | 50.0 | 400000.0 | openai | openai |
| gpt-image-1-mini | 50.0 | 400000.0 | openai | openai |
| gpt-image-1.5 | 50.0 | 40000.0 | openai | openai |
| gpt-image-2 | 50.0 | 1000000.0 | openai | openai |
| gpt-oss-120b | 750.0 | 1200000.0 | azure | openai |
| grok-3 | 500.0 | 4000000.0 | xai | xai |
| grok-3-beta | 500.0 | 4000000.0 | xai | xai |
| grok-3-fast | 500.0 | 4000000.0 | xai | xai |
| grok-3-fast-beta | 500.0 | 4000000.0 | xai | xai |
| grok-3-fast-latest | 500.0 | 4000000.0 | xai | xai |
| grok-3-latest | 500.0 | 4000000.0 | xai | xai |
| grok-3-mini | 800.0 | 4000000.0 | xai | xai |
| grok-3-mini-beta | 800.0 | 4000000.0 | xai | xai |
| grok-3-mini-fast | 800.0 | 4000000.0 | xai | xai |
| grok-3-mini-fast-beta | 800.0 | 4000000.0 | xai | xai |
| grok-3-mini-fast-latest | 800.0 | 4000000.0 | xai | xai |
| grok-3-mini-latest | 800.0 | 4000000.0 | xai | xai |
| grok-4 | 80.0 | 200000.0 | xai | xai |
| grok-4-0709 | 80.0 | 200000.0 | xai | xai |
| grok-4-1-fast-non-reasoning | 150.0 | 1500000.0 | xai | xai |
| grok-4-1-fast-reasoning | 150.0 | 1500000.0 | xai | xai |
| grok-4-fast-non-reasoning | 150.0 | 1500000.0 | xai | xai |
| grok-4-fast-reasoning | 150.0 | 1500000.0 | xai | xai |
| grok-4-latest | 80.0 | 200000.0 | xai | xai |
| grok-4.20-beta-0309-non-reasoning | 15.0 | 150000.0 | xai | xai |
| grok-4.20-beta-0309-reasoning | 15.0 | 150000.0 | xai | xai |
| grok-4.20-non-reasoning | 150.0 | 1500000.0 | xai | xai |
| grok-4.20-reasoning | 150.0 | 1500000.0 | xai | xai |
| grok-4.3 | 150.0 | 1500000.0 | xai | xai |
| grok-4.5 | 150.0 | 1500000.0 | xai | xai |
| grok-code-fast-1 | 250.0 | 1200000.0 | xai | xai |
| groq.gpt-oss-120b | 100.0 | 150000.0 | groq | openai |
| groq.gpt-oss-20b | 100.0 | 150000.0 | groq | openai |
| groq.gpt-oss-safeguard-20b | 250.0 | 100000.0 | groq | openai |
| groq.kimi-k2-instruct-0905 | 250.0 | 200000.0 | groq | moonshot |
| groq.llama-4-maverick-17b-128e-instruct | 250.0 | 200000.0 | groq | meta |
| groq.llama-4-scout-17b-16e-instruct | 250.0 | 200000.0 | groq | meta |
| groq.llama-guard-4-12b | 50.0 | 20000.0 | groq | meta |
| groq.llama-prompt-guard-2-22m | 50.0 | 20000.0 | groq | meta |
| groq.llama-prompt-guard-2-86m | 25.0 | 20000.0 | groq | meta |
| groq.playai-tts | 100.0 | 30000.0 | groq | play ai |
| groq.playai-tts-arabic | 100.0 | 30000.0 | groq | play ai |
| groq.qwen3-32b | 150.0 | 200000.0 | groq | alibaba |
| groq.whisper-large-v3 | 150.0 | 200000.0 | groq | openai |
| groq.whisper-large-v3-turbo | 150.0 | 200000.0 | groq | openai |
| imagen-3.0-fast-generate-001 | 100.0 | N/A | vertex_ai | |
| imagen-3.0-generate-001 | 100.0 | N/A | vertex_ai | |
| imagen-3.0-generate-002 | 100.0 | N/A | vertex_ai | |
| imagen-4.0-fast-generate-001 | 50.0 | N/A | vertex_ai | |
| imagen-4.0-generate-001 | 50.0 | N/A | vertex_ai | |
| imagen-4.0-ultra-generate-001 | 50.0 | N/A | vertex_ai | |
| kimi-k2.5 | 250.0 | 1000000.0 | moonshot | moonshot |
| kimi-k2.6 | 250.0 | 1000000.0 | moonshot | moonshot |
| kimi-k2.7-code | 250.0 | 1000000.0 | moonshot | moonshot |
| kimi-k2.7-code-highspeed | 250.0 | 1000000.0 | moonshot | moonshot |
| kimi-k3 | 250.0 | 1000000.0 | moonshot | moonshot |
| kimi-latest | 250.0 | 1000000.0 | moonshot | moonshot |
| llama-4-maverick-17b-128e-instruct-fp8 | 250.0 | 2000000.0 | together_ai | meta |
| llama-4-scout-17b-16e-instruct | 250.0 | 2000000.0 | together_ai | meta |
| meta.llama3-1-405b-instruct-v1:0 | 40.0 | 200000.0 | bedrock | meta |
| meta.llama3-1-70b-instruct-v1:0 | 40.0 | 200000.0 | bedrock | meta |
| meta.llama3-1-8b-instruct-v1:0 | 40.0 | 200000.0 | bedrock | meta |
| meta.llama3-3-70b-instruct-v1:0 | 40.0 | 200000.0 | bedrock | meta |
| minimax-m2.5 | 200.0 | 800000.0 | minimax | minimax |
| minimax-m2.5-lightning | 200.0 | 800000.0 | minimax | minimax |
| minimax-m2.7 | 200.0 | 800000.0 | minimax | minimax |
| minimax-m2.7-highspeed | 200.0 | 800000.0 | minimax | minimax |
| minimax-m3 | 200.0 | 800000.0 | minimax | minimax |
| mistral-large-3 | 750.0 | 2000000.0 | openai | openai |
| mistral-ocr-2512 | 30.0 | N/A | azure | mistral ai |
| mistral-ocr-4-0 | 60.0 | N/A | azure | mistral ai |
| mistral-ocr-latest | 60.0 | N/A | azure | mistral ai |
| mistral-small-2503 | 500.0 | 3000000.0 | vertex_ai | |
| mistral.mistral-large-2407-v1:0 | 40.0 | 200000.0 | bedrock | mistral ai |
| nemotron-3-ultra | 200.0 | 800000.0 | fireworks_ai | nvidia |
| nvidia_nim.bge-m3 | 15.0 | 30000.0 | nvidia_nim | baai |
| nvidia_nim.gpt-oss-120b | 15.0 | 30000.0 | nvidia_nim | openai |
| nvidia_nim.gpt-oss-20b | 15.0 | 30000.0 | nvidia_nim | openai |
| nvidia_nim.llama-3.3-nemotron-super-49b-v1.5 | 15.0 | 30000.0 | nvidia_nim | nvidia |
| nvidia_nim.nemotron-nano-12b-v2-vl | 15.0 | 30000.0 | nvidia_nim | nvidia |
| nvidia_nim.nemotron-parse | 15.0 | 30000.0 | nvidia_nim | nvidia |
| nvidia_nim.nv-embed-v1 | 15.0 | 30000.0 | nvidia_nim | nvidia |
| nvidia_nim.nv-embedqa-e5-v5 | 15.0 | 30000.0 | nvidia_nim | nvidia |
| o1 | 5000.0 | 2000000.0 | openai | openai |
| o1-2024-12-17 | 5000.0 | 2000000.0 | openai | openai |
| o3 | 2500.0 | 800000.0 | openai | openai |
| o3-2025-04-16 | 2500.0 | 800000.0 | openai | openai |
| o3-deep-research | 1000.0 | 800000.0 | openai | openai |
| o3-deep-research-2025-06-26 | 1000.0 | 800000.0 | openai | openai |
| o3-mini | 5000.0 | 4000000.0 | openai | openai |
| o3-mini-2025-01-31 | 5000.0 | 4000000.0 | openai | openai |
| o3-pro | 1500.0 | 800000.0 | openai | openai |
| o3-pro-2025-06-10 | 1500.0 | 800000.0 | openai | openai |
| o4-mini | 500.0 | 200000.0 | openai | openai |
| o4-mini-2025-04-16 | 500.0 | 200000.0 | openai | openai |
| o4-mini-deep-research | 1500.0 | 4000000.0 | openai | openai |
| o4-mini-deep-research-2025-06-26 | 1500.0 | 4000000.0 | openai | openai |
| omni-moderation-2024-09-26 | 50.0 | 50000.0 | openai | openai |
| omni-moderation-latest | 50.0 | 50000.0 | openai | openai |
| openai.gpt-oss-120b-1:0 | 75.0 | 450000.0 | bedrock | openai |
| openai.gpt-oss-20b-1:0 | 75.0 | 450000.0 | bedrock | openai |
| parallel_ai-search | 75.0 | N/A | parallel_ai | parallel_ai |
| parallel_ai-search-pro | 75.0 | N/A | parallel_ai | parallel_ai |
| perplexity-search | 75.0 | N/A | perplexity | perplexity |
| qwen-flash | 75.0 | 800000.0 | dashscope | alibaba |
| qwen-flash-2025-07-28 | 75.0 | 800000.0 | dashscope | alibaba |
| qwen-image | 25.0 | N/A | dashscope | alibaba |
| qwen-image-2.0 | 25.0 | N/A | dashscope | alibaba |
| qwen-image-2.0-pro | 25.0 | N/A | dashscope | alibaba |
| qwen-image-edit | 25.0 | N/A | dashscope | alibaba |
| qwen-image-edit-plus | 25.0 | N/A | dashscope | alibaba |
| qwen-image-plus | 25.0 | N/A | dashscope | alibaba |
| qwen-mt-flash | 75.0 | 500000.0 | dashscope | alibaba |
| qwen-mt-lite | 75.0 | 500000.0 | dashscope | alibaba |
| qwen-mt-plus | 75.0 | 500000.0 | dashscope | alibaba |
| qwen-mt-turbo | 75.0 | 500000.0 | dashscope | alibaba |
| qwen-plus-2025-04-28 | 150.0 | 800000.0 | dashscope | alibaba |
| qwen-plus-2025-07-14 | 150.0 | 800000.0 | dashscope | alibaba |
| qwen-plus-2025-07-28 | 75.0 | 800000.0 | dashscope | alibaba |
| qwen-plus-2025-09-11 | 75.0 | 800000.0 | dashscope | alibaba |
| qwen-plus-2025-12-01 | 75.0 | 800000.0 | dashscope | alibaba |
| qwen-plus-character | 100.0 | 800000.0 | dashscope | alibaba |
| qwen-plus-latest | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3-14b | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3-235b-a22b | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3-235b-a22b-fp8-tput | 500.0 | 2000000.0 | together_ai | alibaba |
| qwen3-235b-a22b-instruct-2507 | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3-235b-a22b-thinking-2507 | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3-30b-a3b | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3-30b-a3b-instruct-2507 | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3-30b-a3b-thinking-2507 | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3-32b | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3-8b | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3-coder-480b-a35b-instruct | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3-coder-flash | 75.0 | 800000.0 | dashscope | alibaba |
| qwen3-coder-flash-2025-07-28 | 75.0 | 800000.0 | dashscope | alibaba |
| qwen3-coder-next | 50.0 | 800000.0 | dashscope | alibaba |
| qwen3-coder-plus | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3-coder-plus-2025-07-22 | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3-coder-plus-2025-09-23 | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3-max | 75.0 | 800000.0 | dashscope | alibaba |
| qwen3-max-2025-09-23 | 75.0 | 800000.0 | dashscope | alibaba |
| qwen3-max-2026-01-23 | 75.0 | 800000.0 | dashscope | alibaba |
| qwen3-max-preview | 75.0 | 800000.0 | dashscope | alibaba |
| qwen3-next-80b-a3b-instruct | 75.0 | 800000.0 | dashscope | alibaba |
| qwen3-next-80b-a3b-thinking | 75.0 | 800000.0 | dashscope | alibaba |
| qwen3-rerank | 1500.0 | 10000000.0 | dashscope | alibaba |
| qwen3-vl-32b-instruct | 50.0 | 800000.0 | dashscope | alibaba |
| qwen3-vl-flash | 75.0 | 800000.0 | dashscope | alibaba |
| qwen3-vl-flash-2025-10-15 | 75.0 | 800000.0 | dashscope | alibaba |
| qwen3-vl-flash-2026-01-22 | 75.0 | 800000.0 | dashscope | alibaba |
| qwen3-vl-plus | 75.0 | 800000.0 | dashscope | alibaba |
| qwen3-vl-plus-2025-12-19 | 75.0 | 800000.0 | dashscope | alibaba |
| qwen3.5-122b-a10b | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3.5-27b | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3.5-35b-a3b | 150.0 | 2000000.0 | dashscope | alibaba |
| qwen3.5-397b-a17b | 50.0 | 800000.0 | dashscope | alibaba |
| qwen3.5-flash | 1500.0 | 2000000.0 | dashscope | alibaba |
| qwen3.5-plus | 1500.0 | 1000000.0 | dashscope | alibaba |
| qwen3.6-27b | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3.6-35b-a3b | 150.0 | 800000.0 | dashscope | alibaba |
| qwen3.6-flash | 1500.0 | 4000000.0 | dashscope | alibaba |
| qwen3.6-max-preview | 50.0 | 800000.0 | dashscope | alibaba |
| qwen3.6-plus | 1500.0 | 2000000.0 | dashscope | alibaba |
| qwen3.7-max | 50.0 | 800000.0 | dashscope | alibaba |
| qwen3.7-plus | 1500.0 | 2000000.0 | dashscope | alibaba |
| qwq-32b | 150.0 | 800000.0 | together_ai | alibaba |
| qwq-plus | 150.0 | 800000.0 | dashscope | alibaba |
| qwq-plus-2025-03-05 | 150.0 | 800000.0 | dashscope | alibaba |
| runwayml.eleven_multilingual_v2 | 250.0 | N/A | runwayml | runwayml |
| scribe_v1 | 500.0 | N/A | elevenlabs | elevenlabs |
| scribe_v2 | 500.0 | N/A | elevenlabs | elevenlabs |
| seedream-5-0-260128 | 100.0 | N/A | byteplus | bytedance |
| semantic-ranker-default-004 | 150.0 | N/A | vertex_ai | |
| semantic-ranker-fast-004 | 150.0 | N/A | vertex_ai | |
| serper-search | 75.0 | N/A | serper | serper |
| sonar | 75.0 | 2000000.0 | perplexity | perplexity |
| sonar-deep-research | 75.0 | 2000000.0 | perplexity | perplexity |
| sonar-pro | 75.0 | 2000000.0 | perplexity | perplexity |
| sonar-reasoning | 75.0 | 2000000.0 | perplexity | perplexity |
| sonar-reasoning-pro | 75.0 | 2000000.0 | perplexity | perplexity |
| sora-2 | 5.0 | None | openai | openai |
| sora-2-pro | 3.0 | None | openai | openai |
| tavily-search | 75.0 | N/A | tavily | tavily |
| tavily-search-advanced | 75.0 | N/A | tavily | tavily |
| text-embedding-3-large | 5000.0 | 5000000.0 | openai | openai |
| text-embedding-3-small | 5000.0 | 5000000.0 | openai | openai |
| text-embedding-ada-002 | 5000.0 | 5000000.0 | openai | openai |
| text-embedding-v3 | 75.0 | 800000.0 | dashscope | alibaba |
| text-embedding-v4 | 750.0 | 800000.0 | dashscope | alibaba |
| text-moderation-latest | 500.0 | 1000000.0 | openai | openai |
| text-moderation-stable | 500.0 | 1000000.0 | openai | openai |
| tongyi-embedding-vision-flash | 75.0 | 100000.0 | dashscope | alibaba |
| tongyi-embedding-vision-plus | 75.0 | 800000.0 | dashscope | alibaba |
| tts-1 | 5000.0 | N/A | openai | openai |
| tts-1-hd | 5000.0 | N/A | openai | openai |
| veo-3.1-fast-generate-001 | 3.0 | None | vertex_ai | |
| veo-3.1-fast-generate-preview | 5.0 | None | gemini | |
| veo-3.1-generate-001 | 3.0 | None | vertex_ai | |
| veo-3.1-generate-preview | 5.0 | None | gemini | |
| wan2.2-t2i-flash | 50.0 | N/A | dashscope | alibaba |
| wan2.2-t2i-plus | 50.0 | N/A | dashscope | alibaba |
| whisper-1 | 5000.0 | 2147483647.0 | openai | openai |
| z-image-turbo | 25.0 | N/A | dashscope | alibaba |
Model Availability
Tier 3 (Tier 3) provides access to 376 models.