IoTeX AI Gateway provides access to models from multiple leading AI providers. The model list is updated regularly as new models become available.
Text Models (26 models)
Prices are per 1M tokens.
| Model | Provider | Input | Output |
|---|
deepseek-ai/DeepSeek-R1-0528 | DeepSeek | $0.50 | $2.15 |
deepseek-ai/DeepSeek-V3-0324 | DeepSeek | $0.27 | $0.88 |
gemini-2.5-flash | Google | $0.30 | $2.50 |
gemini-2.5-flash-lite | Google | $0.10 | $0.40 |
gemini-3-flash-preview | Google | $0.50 | $3.00 |
gemini-3-pro-preview | Google | $2.00 | $12.00 |
google/gemma-3-12b-it | Google | $0.03 | $0.10 |
google/gemma-3-27b-it | Google | $0.04 | $0.15 |
meta-llama/Llama-3.3-70B-Instruct | Meta | $0.23 | $0.40 |
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | Meta | $0.15 | $0.60 |
mistralai/Mistral-Nemo-Instruct-2407 | Mistral | $0.02 | $0.04 |
moonshotai/Kimi-K2-Instruct-0905 | Moonshot | $0.40 | $2.00 |
moonshotai/Kimi-K2.5 | Moonshot | $0.45 | $2.25 |
gpt-4o-mini | OpenAI | $0.15 | $0.60 |
openai/gpt-3.5-turbo | OpenAI | $0.50 | $1.50 |
openai/gpt-4.1-nano | OpenAI | $0.10 | $0.40 |
openai/gpt-4o-mini | OpenAI | $0.15 | $0.60 |
openai/gpt-oss-120b | OpenAI | $0.04 | $0.19 |
openai/gpt-oss-20b | OpenAI | $0.03 | $0.14 |
openrouter/sonoma-sky-alpha | OpenRouter | Free | - |
Qwen/Qwen2.5-7B-Instruct | Qwen | $0.04 | $0.10 |
Qwen/Qwen3-235B-A22B-Instruct-2507 | Qwen | $0.13 | $0.60 |
Qwen/Qwen3-30B-A3B | Qwen | $0.08 | $0.29 |
Qwen/Qwen3-Coder-480B-A35B-Instruct | Qwen | $0.40 | $1.60 |
x-ai/grok-code-fast-1 | xAI | $0.20 | $1.50 |
zai-org/GLM-5 | ZAI | $0.80 | $2.56 |
Audio Models (3 models)
Whisper models are billed by audio duration. Tokens are calculated based on audio file length.
| Model | Provider | Price/min | Price/1M tokens |
|---|
openai/whisper-large-v3 | OpenAI | $0.0030 | $15.00 |
openai/whisper-large-v3-turbo | OpenAI | $0.0015 | $7.50 |
whisper-1 | OpenAI | $0.0060 | $30.00 |
Image Models (1 model)
| Model | Provider | Price/req |
|---|
black-forest-labs/FLUX-1.1-pro | Black Forest Labs | $0.04 |
This list may not reflect the latest additions. Call the /v1/models endpoint for the most up-to-date list.
Query Models Programmatically
curl https://gateway.iotex.ai/v1/models
