43 models across 16 providers. OpenAI-compatible, at each provider's listed price.
Sign up in the console. Access is immediate, with no waitlist.
Point any OpenAI- or Anthropic-compatible client at api.routerplus.com with your RouterPlus key.
Set the model field to any catalog ID. Switching models is a one-field change.
curl https://api.routerplus.com/v1/chat/completions \
-H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4.1-flash",
"messages": [{ "role": "user", "content": "Hello" }]
}'| Family | Models | Newest | Lowest input | Lowest output | Providers |
|---|---|---|---|---|---|
| Particle | 1 | Particle-1October 27, 2026 | $0.2125 | $0.85 | 1 |
| Ultramarine | 1 | Ultramarine 1 FlashSeptember 29, 2026 | $0.15 | $0.50 | 1 |
 Kimi | 6 | Kimi K3.1 ProOctober 24, 2026 | $0.39 | $1.80 | 11 |
 DeepSeek | 8 | DeepSeek V4.1 Flash 1017October 17, 2026 | $0.06 | $0.18 | 14 |
 GLM | 6 | GLM 5.3 FlashAugust 26, 2026 | $0.05 | $0.20 | 15 |
 Qwen | 13 | Qwen3.8 MaxSeptember 3, 2026 | $0.039 | $0.382 | 11 |
 Gemma 4 | 3 | Gemma 4 12BMay 23, 2026 | $0.12 | $0.35 | 5 |
 Muse Spark | 1 | Muse Spark OpenOctober 15, 2026 | $1.25 | $4.25 | 2 |
 gpt-oss | 2 | gpt-oss-120bAugust 5, 2025 | $0.03 | $0.14 | 2 |
 MiniMax M3 | 2 | MiniMax M3.1 FlashOctober 19, 2026 | $0.15 | $0.60 | 3 |
USD per 1M tokens, as of November 5, 2026.
Run where your users are.
Set the bar for production traffic. We hold it.
The gateway does not store prompts or completions; it records usage metadata.
Connect supported provider accounts. They keep billing you directly, with no RouterPlus inference fee.
| Key | How you pay | Inference fee |
|---|---|---|
| RouterPlus key | Prepaid credits at the listed model rate. Each response includes its cost. | Listed rate |
| Your provider key (BYOK) | Your provider bills you directly. | 0% |
Tell us the model, throughput and region you need. RouterPlus shops the requirement across its provider network and replies with committed capacity, a better quote or a backup provider.
An inference API runs a trained language model for you: you send a request with a prompt, and the API returns the model's output. You pay per token instead of running GPUs yourself.
43 models from Particle, Ultramarine, Kimi, DeepSeek, GLM, Qwen, Gemma 4, Muse Spark, gpt-oss and MiniMax M3, served by 16 providers. Each model page lists every provider and its price.
Prices start at $0.03 per million input tokens (gpt-oss-20b) and $0.14 per million output tokens (gpt-oss-20b). Marketplace calls use prepaid credits at the listed model rates, with the cost included in each billed response. With your own provider key, the provider bills you directly and RouterPlus charges a 0% inference fee.
Yes. Existing OpenAI- or Anthropic-compatible clients connect by changing the base URL to https://api.routerplus.com/v1 and using your RouterPlus key. To switch models, change the model field.
Sign up in the console and you get API access right away. There is no waitlist or approval step.
The gateway does not store prompts or completions; it records usage metadata. The provider serving your request applies its own data policy.
Yes. Send the model, throughput and region you need, and RouterPlus shops the requirement across its provider network and replies with committed capacity, a better quote or a backup provider.