Compatible API
Works with the official OpenAI SDKs and most tools that support a custom base URL.
An OpenAI-compatible gateway for chat, images, audio and embeddings. Keep your SDK, change the base URL, and pay per token from your Yeap balance. Activate it and get $5 of free credit.
Models
300 models from 24 providers behind one OpenAI-compatible API. List prices in USD per 1M tokens.
Free OpenRouter models, refreshed automatically every few hours.
baidu/ernie-5.5-flash-preview:freecohere/north-mini-code:freegoogle/gemma-4-26b-a4b-it:freegoogle/gemma-4-31b-it:freethinkingmachines/inkling-2-small:freemistralai/mistral-moderation-2603nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freenvidia/nemotron-3-ultra-550b-a55b:freenvidia/nemotron-3.5-lightning:freenvidia/nemotron-3.5-super-vl:freedots-studio/dots-3-note-preview:freeinclusionai/ling-3.2-flash:freeliquid/lfm-3-1.7b:freeparticle-ai/particle-1:freerecursive/flint-v1.0:free| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
x-ai/grok-3 | $2.70 | $13.50 |
x-ai/grok-3-deepersearch | $2.70 | $13.50 |
x-ai/grok-3-deepsearch | $2.70 | $13.50 |
x-ai/grok-3-reasoning | $2.70 | $13.50 |
x-ai/grok-3-search | $2.70 | $13.50 |
x-ai/grok-4 | $2.70 | $13.50 |
x-ai/grok-4-0709 | $2.70 | $13.50 |
x-ai/grok-4-1-thinking-1129 | $1.80 | $9 |
x-ai/grok-4-auto | $2.70 | $13.50 |
x-ai/grok-4-fast | $0.18 | $0.45 |
x-ai/grok-4-mini-thinking-tahoe | $1.80 | $9 |
x-ai/grok-4.1 | $1.80 | $9 |
x-ai/grok-4.1-fast | $0.18 | $0.45 |
x-ai/grok-4.1-thinking | $1.80 | $9 |
x-ai/grok-4.2 | $1.13 | $2.25 |
x-ai/grok-4.2-fast | $1.13 | $2.25 |
x-ai/grok-4.3 | $1.13 | $2.25 |
x-ai/grok-4.5 | $1.80 | $5.40 |
x-ai/grok-4.5-high | $1.80 | $5.40 |
x-ai/grok-4.5-low | $1.80 | $5.40 |
x-ai/grok-4.5-medium | $1.80 | $5.40 |
x-ai/grok-4.6 | $1.80 | $5.40 |
x-ai/grok-4.6-high | $1.80 | $5.40 |
x-ai/grok-4.6-max | $1.80 | $5.40 |
x-ai/grok-4.6-xhigh | $1.80 | $5.40 |
x-ai/grok-4.7 | $1.80 | $5.40 |
x-ai/grok-420-agents | $1.13 | $2.25 |
x-ai/grok-420-thinking | $1.13 | $2.25 |
x-ai/grok-code-fast-1 | $0.18 | $1.35 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
anthropic/claude-3-5-haiku-20241022 | $0.72 | $3.60 |
anthropic/claude-3-5-sonnet-20240620 | $2.70 | $13.50 |
anthropic/claude-3-5-sonnet-20241022 | $2.70 | $13.50 |
anthropic/claude-3-7-sonnet-20250219 | $2.70 | $13.50 |
anthropic/claude-3-opus-20240229 | $13.50 | $67.50 |
anthropic/claude-3-sonnet-20240229 | $2.70 | $13.50 |
anthropic/claude-haiku-4.5 | $0.9 | $4.50 |
anthropic/claude-opus-4-20250514 | $13.50 | $67.50 |
anthropic/claude-opus-4-7-max | $4.50 | $22.50 |
anthropic/claude-opus-4.1 | $13.50 | $67.50 |
anthropic/claude-opus-4.5 | $4.50 | $22.50 |
anthropic/claude-opus-4.6 | $4.50 | $22.50 |
anthropic/claude-opus-4.7 | $4.50 | $22.50 |
anthropic/claude-opus-4.7-high | $4.50 | $22.50 |
anthropic/claude-opus-4.7-low | $4.50 | $22.50 |
anthropic/claude-sonnet-4-20250514 | $2.70 | $13.50 |
anthropic/claude-sonnet-4.5 | $2.70 | $13.50 |
anthropic/claude-sonnet-4.6 | $2.70 | $13.50 |
anthropic/claude-sonnet-5 | $1.80 | $9 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
deepseek-ai/DeepSeek-V3 | $1 | $4 |
deepseek-ai/DeepSeek-V3-0324 | $1 | $4 |
deepseek-ai/DeepSeek-V3.1 | $1.70 | $4.21 |
deepseek-ai/DeepSeek-V3.2-Exp | $1 | $4 |
deepseek/deepseek-chat | $0.288 | $0.801 |
deepseek/deepseek-flash | $0.006 | $0.5 |
deepseek/deepseek-v3-1-250821 | $0.504 | $1.51 |
deepseek/deepseek-v3.1-0821 | $0.504 | $1.51 |
deepseek/deepseek-v3.1-terminus | $0.243 | $0.9 |
deepseek/deepseek-v3.1-think | $0.504 | $1.51 |
deepseek/deepseek-v3.2-think | $0.252 | $0.378 |
deepseek/deepseek-v4-flash-0731 | $0.5 | $1.50 |
deepseek/deepseek-v4-pro | $0.1879 | $0.3758 |
deepseek/deepseek-v4.1-flash | $0.0459 | $0.5103 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
bytedance/doubao-seedance-1-0-pro-250528 | $0.549 per request | |
bytedance/doubao-seedance-1-0-pro-fast-251015 | $0.216 per request | |
bytedance/doubao-seedance-1-5-pro-251215 | $0.531 per request | |
bytedance/doubao-seedream-3-0-t2i-250415 | $0.027 per request | |
bytedance/doubao-seedream-4-0 | $0.027 per request | |
bytedance/doubao-seedream-4-0-250828 | $0.027 per request | |
bytedance/doubao-seedream-4-0-4k | $0.027 per request | |
bytedance/doubao-seedream-4-5 | $0.036 per request | |
bytedance/doubao-seedream-4-5-251128 | $0.036 per request | |
bytedance/doubao-seedream-4-5-4k | $0.036 per request | |
bytedance/doubao-seedream-5-0 | $0.0315 per request | |
bytedance/doubao-seedream-5-0-260128 | $0.0315 per request | |
bytedance/doubao-seedream-5-0-4k | $0.0315 per request | |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
meta-llama/Meta-Llama-3.1-405B-Instruct | $2 | $8 |
meta-llama/llama-2-13b | $0.675 | $0.9 |
meta-llama/llama-2-70b | $1.75 | $2.30 |
meta-llama/llama-3-sonar-large-32k-chat | $0.9 | $0.9 |
meta-llama/llama-3.1-405b | $3.15 | $3.15 |
meta-llama/llama-3.1-405b-instruct | $3.15 | $3.15 |
meta-llama/llama-3.1-405b-instruct:free | $0.2 | $0.02 |
meta-llama/llama-3.1-70b-instruct | $2 | $8 |
meta-llama/llama-3.2-90b-vision-instruct | $2 | $8 |
meta-llama/llama-3.2-90b-vision-instruct:free | $0.2 | $0.2 |
meta-llama/llama-4-maverick | $0.315 | $0.9 |
meta-llama/llama-4-scout | $0.09 | $0.27 |
meta-llama/meta-llama-3-3-70b-instruct | $0.792 | $0.792 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
z-ai/glm-4-airx | $1.27 | $1.27 |
z-ai/glm-4-long | $0.126 | $0.126 |
z-ai/glm-4.5-x | $1.98 | $8.01 |
z-ai/glm-4.7 | $0.54 | $1.98 |
z-ai/glm-5 | $0.9 | $2.88 |
z-ai/glm-5.1 | $1.26 | $3.96 |
z-ai/glm-5.2 | $0.0054 | $6.12 |
z-ai/z-image-turbo | $0.0135 per request | |
zai-org/glm-4.5 | $1.60 | $6.40 |
zai-org/glm-4.5-air | $1 | $4 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
moonshotai/kimi-k2-0711-preview | $0.54 | $2.25 |
moonshotai/kimi-k2-0905-preview | $0.54 | $2.25 |
moonshotai/kimi-k2-250905 | $0.54 | $2.25 |
moonshotai/kimi-k2-instruct-0905 | $0.54 | $2.25 |
moonshotai/kimi-k2.5 | $0.4788 | $2.99 |
moonshotai/kimi-k2.6 | $6.50 | $27 |
moonshotai/kimi-k2.7-code | $6.50 | $27 |
moonshotai/kimi-k3 | $20 | $100 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
dots-studio/dots-3-note-preview:freeFree | Free | Free |
inclusionai/ling-3.2-flash:freeFree | Free | Free |
liquid/lfm-3-1.7b:freeFree | Free | Free |
nousresearch/hermes-3-llama-3.1-405b:free | $0.2 | $0.2 |
other/dolphin3.0-r1-mistral-24b | $1.31 | $2.62 |
particle-ai/particle-1:freeFree | Free | Free |
recursive/flint-v1.0:freeFree | Free | Free |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
qwen/qwen-image-plus | $0.027 per request | |
qwen/qwen-max | $1.44 | $5.76 |
qwen/qwen-plus | $0.234 | $0.702 |
qwen/qwen-turbo | $0.045 | $0.18 |
qwen/qwen-vl-max | $0.72 | $2.88 |
qwen/qwen2.5-32b-instruct | $0.63 | $2.52 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
mistralai/codestral-embed | $0.135 | $0 |
mistralai/mistral-large | $1.80 | $5.40 |
mistralai/mistral-moderation-2603Free | Free | Free |
mistralai/mistral-small-2603 | $0.135 | $0.54 |
mistralai/pixtral-large-2411 | $1.80 | $5.40 |
other/mixtral-8x22b-instruct-v0.1 | $1.80 | $5.40 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
google/gemini-2.0-flash | $0.135 | $0.54 |
google/gemini-2.5-flash | $0.27 | $2.25 |
google/gemini-2.5-flash-lite-preview-09-2025 | $0.09 | $0.36 |
google/gemini-2.5-flash-preview-09-2025 | $0.27 | $2.25 |
google/gemini-2.5-pro-preview-05-06 | $1.13 | $9 |
google/gemini-2.5-pro-preview-06-05 | $1.13 | $9 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeFree | Free | Free |
nvidia/nemotron-3-ultra-550b-a55b:freeFree | Free | Free |
nvidia/nemotron-3.5-lightning:freeFree | Free | Free |
nvidia/nemotron-3.5-super-vl:freeFree | Free | Free |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
openai/gpt-5 | $1.13 | $9 |
openai/gpt-5-codex | $1.13 | $9 |
openai/gpt-5.1 | $1.13 | $9 |
openai/gpt-5.1-codex | $1.13 | $9 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
deepseek/deepseek-v3 | $0.243 | $0.99 |
qwen/qwen3-235b-a22b-2507-thinking-2507 | $0.126 | $0.72 |
qwen/qwen3-coder-plus | $0.9 | $4.50 |
qwen/qwen3-max | $1.08 | $5.40 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
microsoft/phi-3-medium-128k-instruct | $1.65 | $6.60 |
microsoft/phi-3-medium-128k-instruct:free | $0.2 | $0.2 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
baidu/ernie-5.5-flash-preview:freeFree | Free | Free |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
cohere/north-mini-code:freeFree | Free | Free |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
deepseek/deepseek-v3-0324 | $0.243 | $0.99 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
thinkingmachines/inkling-2-small:freeFree | Free | Free |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
qwen/qwen3-32b | $0.072 | $0.252 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
z-ai/glm-4.6 | $0.45 | $1.80 |
Prices are list prices for the default group and may change with upstream pricing. Your console shows the exact price for your group.
Capabilities
Works with the official OpenAI SDKs and most tools that support a custom base URL.
Chat and completions, image generation, audio transcription and embeddings.
Create keys per project with their own spend limits.
Try prompts and models in the browser before writing code.
Every request is logged with model, tokens and cost.
Pay from the same balance as your other Yeap products.
Models from OpenAI GPT, Anthropic Claude, Google Gemini, xAI Grok, DeepSeek, Qwen and more. See the model list and prices on this page, or call GET /v1/models for the current list.
You pay per token, priced per 1M input and output tokens; some image and video models are billed per request. Charges come from your Yeap account balance, and current prices are listed on this page.
Yes. New LLM API activations get $5 of credit once your email is verified. Claim it on the LLM account page in the console; it is valid for 30 days.
Yes. Every model is served through the same OpenAI-compatible endpoint at https://llm.yeap.cloud/v1, so you only change the model name.
Yes. Set stream to true and responses arrive as server-sent events.
Each API key can have its own spend limit. Usage logs record every request with the model, tokens and cost.
Sign up, activate the LLM API in the console and transfer balance to it, or turn on auto-transfer. Then create a key and set your base URL to https://llm.yeap.cloud/v1.