Compare LLM API prices
Input and output prices per million tokens and context windows for every model this gateway routes, live from the catalog. Each price is the provider’s list price: what your provider bills you, since Autonomous Relay adds 0%.
294 models, every one served on your own provider key at the provider's list price. Prices are per million tokens.
| Model | Served by | Context | Input | Output |
|---|---|---|---|---|
| Audio8/Audio8-TTS-Preview-0.6b | deepinfra | — | — | — |
| BAAI/bge-base-en-v1.5 | deepinfra | 512 | $0.005 per M | — |
| BAAI/bge-en-icl | deepinfra | 8,192 | $0.01 per M | — |
| BAAI/bge-large-en-v1.5 | deepinfra | 512 | $0.01 per M | — |
| BAAI/bge-m3 | deepinfra | 8,192 | $0.01 per M | — |
| BAAI/bge-m3-multi | deepinfra | 512 | $0.01 per M | — |
| BAAI/bge-m3-multi-8k | deepinfra | 8,192 | $0.01 per M | — |
| Bria/Bria-3.2 | deepinfra | — | — | — |
| Bria/Bria-3.2-vector | deepinfra | — | — | — |
| Bria/blur_background | deepinfra | — | — | — |
| Bria/erase_foreground | deepinfra | — | — | — |
| Bria/expand | deepinfra | — | — | — |
| Bria/fibo | deepinfra | — | — | — |
| Bria/fibo_edit | deepinfra | — | — | — |
| Bria/remove_background | deepinfra | — | — | — |
| ByteDance/Seed-1.8 | deepinfra | 256,000 | $0.25 per M | $2.00 per M |
| ByteDance/Seed-2.0-pro | deepinfra | 256,000 | $0.50 per M | $3.00 per M |
| ByteDance/Seedance-1.5-Pro | deepinfra | — | — | — |
| ByteDance/Seedance-2.0 | deepinfra | — | — | — |
| ByteDance/Seedream-4 | deepinfra | — | — | — |
| MiniMaxAI/MiniMax-M2.7-Turbo | deepinfra | 196,608 | $0.38 per M | $1.70 per M |
| MiniMaxAI/MiniMax-M3 | sambanova | 1,048,576 | $0.60 per M | $2.40 per M |
| Pixverse/Pixverse-6-T2V | deepinfra | — | — | — |
| Pixverse/Pixverse-T2V | deepinfra | — | — | — |
| Pixverse/Pixverse-T2V-HD | deepinfra | — | — | — |
| PrunaAI/p-image | deepinfra | — | — | — |
| PrunaAI/p-video | deepinfra | — | — | — |
| Qwen/Qwen-Image-Edit | deepinfra | — | — | — |
| Qwen/Qwen-Image-Max | deepinfra | — | — | — |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | deepinfra | 262,144 | $0.09 per M | $0.55 per M |
| Qwen/Qwen3-ASR-0.6B | deepinfra | — | — | — |
| Qwen/Qwen3-ASR-1.7B | deepinfra | — | — | — |
| Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | deepinfra | 262,144 | $0.30 per M | $1.00 per M |
| Qwen/Qwen3-Embedding-0.6B | deepinfra | 32,768 | $0.01 per M | — |
| Qwen/Qwen3-Embedding-4B | deepinfra | 32,768 | $0.02 per M | — |
| Qwen/Qwen3-Embedding-8B | deepinfra | 32,768 | $0.01 per M | — |
| Qwen/Qwen3-Reranker-0.6B | deepinfra | 32,768 | $0.01 per M | — |
| Qwen/Qwen3-Reranker-4B | deepinfra | 32,768 | $0.025 per M | — |
| Qwen/Qwen3-Reranker-8B | deepinfra | 32,768 | $0.05 per M | — |
| Qwen/Qwen3-TTS | deepinfra | — | — | — |
| Qwen/Qwen3-TTS-VoiceDesign | deepinfra | — | — | — |
| Qwen/Qwen3.8-Max | deepinfra | 256,000 | $1.65 per M | $4.95 per M |
| ResembleAI/chatterbox-multilingual | deepinfra | — | — | — |
| ResembleAI/chatterbox-turbo | deepinfra | — | — | — |
| Sao10K/L3-8B-Lunaris-v1-Turbo | deepinfra | 8,192 | $0.04 per M | $0.05 per M |
| Llama 3 8B Stheno V3.2 | novita | 8,192 | $0.05 per M | $0.05 per M |
| Sao10K/L3.1-70B-Euryale-v2.2 | deepinfra | 131,072 | $0.85 per M | $0.85 per M |
| Wan-AI/Wan2.2-T2V-A14B | deepinfra | — | — | — |
| Wan-AI/Wan2.6-T2I | deepinfra | — | — | — |
| Wan-AI/Wan2.6-T2V | deepinfra | — | — | — |
| XiaomiMiMo/MiMo-V2.5-tts | deepinfra | — | — | — |
| XiaomiMiMo/MiMo-V2.5-tts-voicedesign | deepinfra | — | — | — |
| AI21: Jamba Large 1.7 | ai21 | 256,000 | $2.00 per M | $8.00 per M |
| AI21: Jamba Mini 2 | ai21 | 256,000 | $0.20 per M | $0.40 per M |
| Anthropic: Claude Fable 5 | anthropic | 1,000,000 | $10.00 per M | $50.00 per M |
| Anthropic: Claude Fable 5.1 | anthropic | 1,000,000 | $10.00 per M | $50.00 per M |
| Anthropic: Claude Fable 5.1 (batch) | anthropic | 1,000,000 | $5.00 per M | $25.00 per M |
| Anthropic: Claude Fable 5 (batch) | anthropic | 1,000,000 | $5.00 per M | $25.00 per M |
| Anthropic: Claude Fable Latest | anthropic | 1,000,000 | $10.00 per M | $50.00 per M |
| Anthropic Claude Haiku Latest | anthropic | 200,000 | $1.00 per M | $5.00 per M |
| Anthropic: Claude Opus 4.7 | anthropic | 1,000,000 | $5.00 per M | $25.00 per M |
| Anthropic: Claude Opus 4.7 (batch) | anthropic | 1,000,000 | $2.50 per M | $12.50 per M |
| Anthropic: Claude Opus 4.8 | anthropic | 1,000,000 | $5.00 per M | $25.00 per M |
| Anthropic: Claude Opus 4.8 (batch) | anthropic | 1,000,000 | $2.50 per M | $12.50 per M |
| Claude Opus 5 | anthropic | 1,000,000 | $5.00 per M | $25.00 per M |
| Claude Opus 5 (batch) | anthropic | 1,000,000 | $2.50 per M | $12.50 per M |
| Anthropic: Claude Opus Latest | anthropic | 1,000,000 | $5.00 per M | $25.00 per M |
| Anthropic: Claude Sonnet 4.6 | anthropic | 1,000,000 | $3.00 per M | $15.00 per M |
| Anthropic: Claude Sonnet 4.6 (batch) | anthropic | 1,000,000 | $1.50 per M | $7.50 per M |
| Anthropic: Claude Sonnet 5 | anthropic | 1,000,000 | $2.00 per M | $10.00 per M |
| Anthropic: Claude Sonnet 5 (batch) | anthropic | 1,000,000 | $1.00 per M | $5.00 per M |
| Anthropic Claude Sonnet Latest | anthropic | 1,000,000 | $2.00 per M | $10.00 per M |
| Baichuan M2 32B | novita | 131,072 | $0.07 per M | $0.07 per M |
| CoBuddy | novita | 131,072 | $0.28 per M | $1.13 per M |
| ERNIE 4.5 21B A3B | novita | 120,000 | $0.07 per M | $0.28 per M |
| black-forest-labs/FLUX-1-Redux-dev | deepinfra | — | — | — |
| black-forest-labs/FLUX-1-dev | deepinfra | — | — | — |
| black-forest-labs/FLUX-1-schnell | deepinfra | — | — | — |
| black-forest-labs/FLUX-1.1-pro | deepinfra | — | — | — |
| black-forest-labs/FLUX-2-dev | deepinfra | — | — | — |
| black-forest-labs/FLUX-2-klein-4b | deepinfra | — | — | — |
| black-forest-labs/FLUX-2-klein-9b | deepinfra | — | — | — |
| black-forest-labs/FLUX-2-max | deepinfra | — | — | — |
| black-forest-labs/FLUX-2-pro | deepinfra | — | — | — |
| black-forest-labs/FLUX.1-Kontext-dev | deepinfra | — | — | — |
| bosonai/HiggsAudioV2.5 | deepinfra | — | — | — |
| Cohere: Command R (08-2024) | cohere | 128,000 | $0.15 per M | $0.60 per M |
| Cohere: Command R7B (12-2024) | cohere | 128,000 | $0.0375 per M | $0.15 per M |
| Cohere: Embed 5 Fast | cohere | 128,000 | $0.08 per M | — |
| Cohere: Embed 5 Pro | cohere | 128,000 | $0.12 per M | — |
| deepseek-ai/DeepSeek-V3 | deepinfra | 163,840 | $0.32 per M | $0.89 per M |
| deepseek-ai/DeepSeek-V3-0324 | deepinfra | 163,840 | $0.24 per M | $0.90 per M |
| deepseek-ai/DeepSeek-V3.1 | deepinfra | 163,840 | $0.25 per M | $0.95 per M |
| deepseek-ai/DeepSeek-V3.2 | sambanova | 32,768 | $3.00 per M | $4.50 per M |
| DeepSeek OCR 2 | novita | 8,192 | $0.03 per M | $0.03 per M |
| DeepSeek R1 Distill Qwen3 8B 0528 | novita | 128,000 | $0.06 per M | $0.09 per M |
| DeepSeek R1 Turbo | novita | 64,000 | $0.70 per M | $2.50 per M |
| DeepSeek: DeepSeek V4 Flash 0423 | deepseek | 1,048,576 | $0.08358 per M | $0.16716 per M |
| DeepSeek: DeepSeek V4 Flash 0731 | deepseek | 1,310,720 | $0.065 per M | $0.18 per M |
| DeepSeek: DeepSeek V4 Flash 0731 (batch) | deepseek | 1,048,576 | $0.14 per M | $0.28 per M |
| DeepSeek V4 Flash Latest | deepseek | 1,310,720 | $0.04998 per M | $0.09996 per M |
| DeepSeek: DeepSeek V4 Flash Vision Exp | deepseek | 1,048,576 | $0.22 per M | $0.66 per M |
| DeepSeek: DeepSeek V4 Pro 0423 | deepseek | 1,048,576 | $0.819366 per M | $1.638732 per M |
| DeepSeek: DeepSeek V4 Pro 0813 | deepseek | 1,048,576 | $0.57948 per M | $1.73844 per M |
| DeepSeek: DeepSeek V4 Pro 0813 (batch) | deepseek | 1,048,576 | $1.32 per M | $3.96 per M |
| google/embeddinggemma-300m | deepinfra | 2,048 | $0.002 per M | — |
| Google: Nano Banana Pro (Gemini 3 Pro Image) | 131,072 | $2.00 per M | $12.00 per M | |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image) | 131,072 | $0.50 per M | $3.00 per M | |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) | 65,536 | $0.50 per M | $3.00 per M | |
| Google: Gemini 3.1 Flash Lite | 1,048,576 | $0.25 per M | $1.50 per M | |
| Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | 65,536 | $0.25 per M | $1.50 per M | |
| Google: Gemini 3.1 Flash Lite Preview | 1,048,576 | $0.25 per M | $1.50 per M | |
| Google: Gemini 3.1 Flash Lite (batch) | 1,048,576 | $0.125 per M | $0.75 per M | |
| google/gemini-3.1-pro | deepinfra | 1,000,000 | $2.00 per M | $12.00 per M |
| Google: Gemini 3.1 Pro Preview | 1,048,576 | $2.00 per M | $12.00 per M | |
| Google: Gemini 3.1 Pro Preview Custom Tools | 1,048,576 | $2.00 per M | $12.00 per M | |
| Google: Gemini 3.1 Pro Preview (batch) | 1,048,576 | $1.00 per M | $6.00 per M | |
| Google: Gemini 3.5 Flash | 1,048,576 | $1.50 per M | $9.00 per M | |
| Google: Gemini 3.5 Flash Lite | 1,048,576 | $0.30 per M | $2.50 per M | |
| Google: Gemini 3.5 Flash Lite (batch) | 1,048,576 | $0.15 per M | $1.25 per M | |
| Google: Gemini 3.5 Flash (batch) | 1,048,576 | $0.75 per M | $4.50 per M | |
| Google: Gemini 3.6 Flash | 1,048,576 | $0.75 per M | $3.75 per M | |
| Google: Gemini 3.6 Flash (batch) | 1,048,576 | $0.375 per M | $1.875 per M | |
| Google: Gemini 3.7 Flash | 1,048,576 | $0.75 per M | $3.75 per M | |
| Google: Gemini 3.7 Flash (batch) | 1,048,576 | $0.375 per M | $1.875 per M | |
| Google: Gemini 3.8 Flash | 1,048,576 | $0.75 per M | $3.75 per M | |
| Google: Gemini 3.8 Flash (batch) | 1,048,576 | $0.375 per M | $1.875 per M | |
| Google Gemini Flash Latest | 1,048,576 | $0.75 per M | $3.75 per M | |
| Google Gemini Pro Latest | 1,048,576 | $2.00 per M | $12.00 per M | |
| Google: Gemma 4 26B A4B | 262,144 | $0.07 per M | $0.34 per M | |
| Google: Gemma 4 26B A4B (free) | 262,144 | $0.00 per M | $0.00 per M | |
| google/gemma-4-31B-it-Ultra | deepinfra | 131,072 | $0.27 per M | $0.76 per M |
| google/gemma-4-31B-it-turbo | deepinfra | 262,144 | $0.09 per M | $0.34 per M |
| Google: Gemma 4 31B | 262,144 | $0.09 per M | $0.34 per M | |
| Google: Gemma 4 31B (batch) | 262,144 | $0.39 per M | $0.97 per M | |
| Google: Gemma 4 31B (free) | 262,144 | $0.00 per M | $0.00 per M | |
| google/gemma-4-E4B-it | deepinfra | 131,072 | $0.02 per M | $0.10 per M |
| Google: Lyria 3 Clip Preview | 1,048,576 | $0.00 per M | $0.00 per M | |
| Google: Lyria 3 Pro Preview | 1,048,576 | $0.00 per M | $0.00 per M | |
| google/nano-banana-2 | deepinfra | — | — | — |
| google/nano-banana-2-lite | deepinfra | — | — | — |
| google/nano-banana-pro | deepinfra | — | — | — |
| google/veo-3.1 | deepinfra | — | — | — |
| google/veo-3.1-fast | deepinfra | — | — | — |
| hexgrad/Kokoro-82M | deepinfra | — | — | — |
| ibm-granite/granite-4.2-30b | deepinfra | 131,072 | $0.16 per M | $0.65 per M |
| ibm-granite/granite-4.2-3b | deepinfra | 131,072 | $0.03 per M | $0.12 per M |
| Ling 3.0 Flash Sante | novita | 262,144 | $0.075 per M | $0.22 per M |
| Ling 3.0 Flash VL | novita | 262,144 | $0.075 per M | $0.22 per M |
| intfloat/e5-base-v2 | deepinfra | 512 | $0.005 per M | — |
| intfloat/e5-large-v2 | deepinfra | 512 | $0.01 per M | — |
| intfloat/multilingual-e5-large | deepinfra | 512 | $0.01 per M | — |
| intfloat/multilingual-e5-large-instruct | deepinfra | 512 | $0.01 per M | — |
| inworld-ai/realtime-tts-1.5-max | deepinfra | — | — | — |
| inworld-ai/realtime-tts-1.5-mini | deepinfra | — | — | — |
| inworld-ai/realtime-tts-2 | deepinfra | — | — | — |
| meta-llama/Llama-3.3-70B-Instruct-Turbo | deepinfra | 131,072 | $0.10 per M | $0.32 per M |
| meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | deepinfra | 1,048,576 | $0.20 per M | $0.80 per M |
| meta-llama/Llama-4-Scout-17B-16E-Instruct | deepinfra | 327,680 | $0.10 per M | $0.30 per M |
| meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | deepinfra | 131,072 | $0.40 per M | $0.40 per M |
| meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | deepinfra | 131,072 | $0.02 per M | $0.04 per M |
| meta-llama/Meta-Llama-3.3-70B-Instruct | sambanova | 131,072 | $0.60 per M | $1.20 per M |
| Macaron V1 Tall | novita | 262,144 | $0.2475 per M | $1.43 per M |
| Macaron V1 Venti | novita | 1,048,576 | $0.825 per M | $2.475 per M |
| MiniMax: MiniMax M2.7 | minimax | 204,800 | $0.30 per M | $1.20 per M |
| MiniMax M2.7-highspeed | novita | 204,800 | $0.60 per M | $2.40 per M |
| MiniMax: MiniMax M2.7 (free) | minimax | 196,608 | $0.00 per M | $0.00 per M |
| MiniMax: MiniMax M3 | minimax | 1,048,576 | $0.30 per M | $1.20 per M |
| MiniMax: MiniMax M3 (batch) | minimax | 524,288 | $0.30 per M | $1.20 per M |
| MiniMax: MiniMax M3 (free) | minimax | 1,048,576 | $0.00 per M | $0.00 per M |
| mistralai/Mistral-Nemo-Instruct-2407 | deepinfra | 131,072 | $0.019 per M | $0.03 per M |
| mistralai/Mistral-Small-3.2-24B-Instruct-2506 | deepinfra | 128,000 | $0.075 per M | $0.20 per M |
| mistralai/Voxtral-Mini-3B-2507 | deepinfra | — | — | — |
| Mistral: Mistral Medium 3.5 | mistral | 262,144 | $1.50 per M | $7.50 per M |
| Mistral: Mistral Medium 3.5 (batch) | mistral | 32,768 | $0.75 per M | $3.75 per M |
| Mistral: Mistral Small 4 | mistral | 262,144 | $0.15 per M | $0.60 per M |
| Kimi K2 Instruct | novita | 131,072 | $0.57 per M | $2.30 per M |
| MoonshotAI: Kimi K2.6 | moonshot | 262,144 | $0.95 per M | $4.00 per M |
| MoonshotAI: Kimi K2.7 Code | moonshot | 262,144 | $0.66 per M | $3.40 per M |
| MoonshotAI: Kimi K3 | moonshot | 1,048,576 | $3.00 per M | $15.00 per M |
| MoonshotAI: Kimi K3 (batch) | moonshot | 1,048,576 | $3.00 per M | $15.00 per M |
| MoonshotAI Kimi Latest | moonshot | 1,048,576 | $2.55 per M | $12.75 per M |
| Hermes 2 Pro Llama 3 8B | novita | 8,192 | $0.14 per M | $0.14 per M |
| Bunny | novita | 262,144 | $0.00 per M | $0.00 per M |
| nvidia/Cosmos3-Nano | deepinfra | — | — | — |
| nvidia/Cosmos3-Super | deepinfra | — | — | — |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B | deepinfra | 262,144 | $0.085 per M | $0.40 per M |
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | deepinfra | 262,144 | $0.50 per M | $2.20 per M |
| nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b | deepinfra | — | — | — |
| nvidia/Nemotron-Content-Safety-3.5 | deepinfra | 131,072 | $0.20 per M | $0.20 per M |
| nvidia/llama-nemotron-embed-vl-1b-v2 | deepinfra | 10,240 | $0.01 per M | — |
| NVIDIA: Nemotron 3 Nano Omni (free) | nvidia | 256,000 | $0.00 per M | $0.00 per M |
| NVIDIA: Nemotron 3 Super | nvidia | 1,000,000 | $0.085 per M | $0.40 per M |
| NVIDIA: Nemotron 3 Super (free) | nvidia | 262,144 | $0.00 per M | $0.00 per M |
| NVIDIA: Nemotron 3 Ultra | nvidia | 262,144 | $0.625 per M | $3.125 per M |
| NVIDIA: Nemotron 3 Ultra (free) | nvidia | 1,000,000 | $0.00 per M | $0.00 per M |
| NVIDIA: Nemotron 3.5 Content Safety | nvidia | 131,072 | $0.20 per M | $0.20 per M |
| NVIDIA: Nemotron 3.5 Content Safety (free) | nvidia | 128,000 | $0.00 per M | $0.00 per M |
| NVIDIA: Nemotron 3.5 Lightning | nvidia | 262,144 | $0.08 per M | $0.20 per M |
| NVIDIA: Nemotron 3.5 Lightning (free) | nvidia | 1,000,000 | $0.00 per M | $0.00 per M |
| OpenAI: GPT-5.3-Codex | openai | 400,000 | $1.75 per M | $14.00 per M |
| OpenAI: GPT-5.4 | openai | 1,050,000 | $2.50 per M | $15.00 per M |
| OpenAI: GPT-5.4 Image 2 | openai | 272,000 | $8.00 per M | $15.00 per M |
| OpenAI: GPT-5.4 Mini | openai | 400,000 | $0.75 per M | $4.50 per M |
| OpenAI: GPT-5.4 Mini (batch) | openai | 400,000 | $0.375 per M | $2.25 per M |
| OpenAI: GPT-5.4 Nano | openai | 400,000 | $0.20 per M | $1.25 per M |
| OpenAI: GPT-5.4 Nano (batch) | openai | 400,000 | $0.10 per M | $0.625 per M |
| OpenAI: GPT-5.4 Pro | openai | 1,050,000 | $30.00 per M | $180.00 per M |
| OpenAI: GPT-5.4 Pro (batch) | openai | 1,050,000 | $15.00 per M | $90.00 per M |
| OpenAI: GPT-5.4 (batch) | openai | 1,050,000 | $1.25 per M | $7.50 per M |
| OpenAI: GPT-5.5 | openai | 1,050,000 | $5.00 per M | $30.00 per M |
| OpenAI: GPT-5.5 Pro | openai | 1,050,000 | $30.00 per M | $180.00 per M |
| OpenAI: GPT-5.5 Pro (batch) | openai | 1,050,000 | $15.00 per M | $90.00 per M |
| OpenAI: GPT-5.5 (batch) | openai | 1,050,000 | $2.50 per M | $15.00 per M |
| OpenAI: GPT-5.6 Luna | openai | 1,050,000 | $0.20 per M | $1.20 per M |
| OpenAI: GPT-5.6 Luna Pro | openai | 1,050,000 | $0.20 per M | $1.20 per M |
| OpenAI: GPT-5.6 Luna Pro (batch) | openai | 1,050,000 | $0.10 per M | $0.60 per M |
| OpenAI: GPT-5.6 Luna (batch) | openai | 1,050,000 | $0.10 per M | $0.60 per M |
| OpenAI: GPT-5.6 Sol | openai | 1,050,000 | $4.00 per M | $20.00 per M |
| OpenAI: GPT-5.6 Sol Pro | openai | 1,050,000 | $2.00 per M | $10.00 per M |
| OpenAI: GPT-5.6 Sol Pro (batch) | openai | 1,050,000 | $1.00 per M | $5.00 per M |
| OpenAI: GPT-5.6 Sol (batch) | openai | 1,050,000 | $1.00 per M | $5.00 per M |
| OpenAI: GPT-5.6 Terra | openai | 1,050,000 | $2.00 per M | $12.00 per M |
| OpenAI: GPT-5.6 Terra Pro | openai | 1,050,000 | $2.00 per M | $12.00 per M |
| OpenAI: GPT-5.6 Terra Pro (batch) | openai | 1,050,000 | $1.00 per M | $6.00 per M |
| OpenAI: GPT-5.6 Terra (batch) | openai | 1,050,000 | $1.00 per M | $6.00 per M |
| OpenAI: GPT-6 Astra | openai | 1,050,000 | $10.00 per M | $50.00 per M |
| OpenAI: GPT-6 Astra Pro | openai | 1,050,000 | $10.00 per M | $50.00 per M |
| OpenAI: GPT-6 Astra Pro (batch) | openai | 1,050,000 | $5.00 per M | $25.00 per M |
| OpenAI: GPT-6 Astra (batch) | openai | 1,050,000 | $5.00 per M | $25.00 per M |
| OpenAI: GPT Chat Latest | openai | 400,000 | $5.00 per M | $30.00 per M |
| OpenAI GPT Latest | openai | 1,050,000 | $2.00 per M | $10.00 per M |
| OpenAI GPT Mini Latest | openai | 400,000 | $0.75 per M | $4.50 per M |
| openai/gpt-oss-120b | sambanova | 131,072 | $0.22 per M | $0.59 per M |
| openai/gpt-oss-120b-Turbo | deepinfra | 131,072 | $0.15 per M | $0.60 per M |
| openai/gpt-oss-120b-Ultra | deepinfra | 131,072 | $0.20 per M | $0.95 per M |
| openai/whisper-large-v3 | deepinfra | — | — | — |
| openai/whisper-large-v3-turbo | deepinfra | — | — | — |
| PaddleOCR VL | novita | 16,384 | $0.02 per M | $0.02 per M |
| Qwen MT Plus | novita | 16,384 | $0.25 per M | $0.75 per M |
| Qwen3 Omni 30B A3B Thinking | novita | 65,536 | $0.25 per M | $0.97 per M |
| Qwen: Qwen3.5-122B-A10B | alibaba | 262,144 | $0.29 per M | $2.40 per M |
| Qwen: Qwen3.5-27B | alibaba | 262,144 | $0.195 per M | $1.56 per M |
| Qwen: Qwen3.5-35B-A3B | alibaba | 262,144 | $0.3125 per M | $1.25 per M |
| Qwen: Qwen3.5-9B | alibaba | 262,144 | $0.10 per M | $0.15 per M |
| Qwen: Qwen3.5-9B (batch) | alibaba | 262,144 | $0.17 per M | $0.25 per M |
| Qwen: Qwen3.5-Flash | alibaba | 1,000,000 | $0.065 per M | $0.26 per M |
| Qwen: Qwen3.5 Plus 2026-02-15 | alibaba | 1,000,000 | $0.26 per M | $1.56 per M |
| Qwen: Qwen3.5 Plus 2026-04-20 | alibaba | 1,000,000 | $0.30 per M | $1.80 per M |
| Qwen: Qwen3.6 27B | alibaba | 262,144 | $0.30 per M | $2.00 per M |
| Qwen: Qwen3.6 35B A3B | alibaba | 262,144 | $0.10 per M | $0.90 per M |
| Qwen: Qwen3.6 Flash | alibaba | 1,000,000 | $0.1875 per M | $1.125 per M |
| Qwen: Qwen3.6 Max Preview | alibaba | 262,144 | $1.027 per M | $6.162 per M |
| Qwen: Qwen3.6 Plus | alibaba | 1,000,000 | $0.325 per M | $1.95 per M |
| Qwen: Qwen3.7 Flash | alibaba | 1,000,000 | $0.03 per M | $0.13 per M |
| Qwen: Qwen3.7 Max | alibaba | 1,000,000 | $1.475 per M | $4.425 per M |
| Qwen: Qwen3.7 Plus | alibaba | 1,000,000 | $0.32 per M | $1.28 per M |
| Qwen: Qwen3.8 2.4T A95B | alibaba | 1,048,576 | $2.00 per M | $6.00 per M |
| Qwen: Qwen3.8 2.4T A95B (batch) | alibaba | 1,010,000 | $2.00 per M | $6.00 per M |
| Qwen: Qwen3.8 27B | alibaba | 1,000,000 | $0.42 per M | $3.00 per M |
| Qwen: Qwen3.8 Flash | alibaba | 1,000,000 | $0.15 per M | $0.47 per M |
| Qwen: Qwen3.8 Max (0902) | alibaba | 1,000,000 | $2.00 per M | $6.00 per M |
| Llama 3 70B Euryale V2.1 | novita | 8,192 | $1.48 per M | $1.48 per M |
| sentence-transformers/all-MiniLM-L12-v2 | deepinfra | 512 | $0.005 per M | — |
| sentence-transformers/all-MiniLM-L6-v2 | deepinfra | 512 | $0.005 per M | — |
| sentence-transformers/all-mpnet-base-v2 | deepinfra | 512 | $0.005 per M | — |
| sentence-transformers/clip-ViT-B-32 | deepinfra | 77 | $0.005 per M | — |
| sentence-transformers/clip-ViT-B-32-multilingual-v1 | deepinfra | 512 | $0.005 per M | — |
| sentence-transformers/multi-qa-mpnet-base-dot-v1 | deepinfra | 512 | $0.005 per M | — |
| sentence-transformers/paraphrase-MiniLM-L6-v2 | deepinfra | 512 | $0.005 per M | — |
| sesame/csm-1b | deepinfra | — | — | — |
| shibing624/text2vec-base-chinese | deepinfra | 512 | $0.005 per M | — |
| stabilityai/sdxl-turbo | deepinfra | — | — | — |
| thenlper/gte-base | deepinfra | 512 | $0.005 per M | — |
| thenlper/gte-large | deepinfra | 512 | $0.01 per M | — |
| SpaceXAI: Grok 4.20 | xai | 2,000,000 | $1.25 per M | $2.50 per M |
| SpaceXAI: Grok 4.20 Multi-Agent | xai | 2,000,000 | $1.25 per M | $2.50 per M |
| SpaceXAI: Grok 4.3 | xai | 1,000,000 | $1.25 per M | $2.50 per M |
| SpaceXAI: Grok 4.3 (batch) | xai | 1,000,000 | $1.00 per M | $2.00 per M |
| SpaceXAI: Grok 4.5 | xai | 500,000 | $2.00 per M | $6.00 per M |
| SpaceXAI: Grok 4.6 | xai | 500,000 | $2.00 per M | $6.00 per M |
| SpaceXAI: Grok Build 0.1 | xai | 256,000 | $1.00 per M | $2.00 per M |
| xAI: Grok Latest | xai | 500,000 | $2.00 per M | $6.00 per M |
| Z.ai: GLM 5 Turbo | zai | 202,752 | $1.20 per M | $4.00 per M |
| Z.ai: GLM 5.1 | zai | 204,800 | $0.966 per M | $3.036 per M |
| Z.ai: GLM 5.2 | zai | 1,048,576 | $0.966 per M | $3.036 per M |
| Z.ai: GLM 5.2 (free) | zai | 256,000 | $0.00 per M | $0.00 per M |
| Z.ai: GLM 5.3 | zai | 1,310,720 | $1.40 per M | $4.40 per M |
| Z.ai: GLM 5.3 Flash | zai | 1,310,720 | $0.075 per M | $0.25 per M |
| Z.ai: GLM 5.3 Flash (batch) | zai | 1,048,575 | $0.15 per M | $0.50 per M |
| Z.ai: GLM 5V Turbo | zai | 202,752 | $1.20 per M | $4.00 per M |
| Z.ai: GLM Flash Latest | zai | 1,310,720 | $0.075 per M | $0.25 per M |
| Z.ai: GLM Latest | zai | 1,310,720 | $1.15 per M | $3.50 per M |
| AutoGLM Phone 9B Multilingual | novita | 65,536 | $0.035 per M | $0.138 per M |
How to read this catalog
Prices
Per million tokens, input then output. Where several providers serve a model, each figure is the lowest current price among them; the model’s page lists every provider and its price.
Calling a model
Use the id under each name as the model parameter in any OpenAI-compatible client pointed at the gateway. Failover and spend ceilings apply to every model.
Questions
- Is the price shown what I pay?
- Yes, for tokens: inference runs on your own provider key at its list price. Autonomous Relay adds 0%; the plans are a flat $29, $99 or $399 a month per organisation.
- Why does each model show two prices?
- Input tokens, then output tokens, per million. Output usually costs more.
- Why do some models say “No active price”?
- No provider serving it has a current price in the catalog, so none is shown rather than an out-of-date one.
- How do I sort by price or context window?
- The sort menu: lowest price, largest context, or newest. Filters narrow by modality, input price and context length.
- Can I compare models side by side?
- Yes, on the Compare page.