Skip to content
NewTry RouterPlus with free creditsTry playground →
RouterPlus
Book a demo

Inference.net API

Open in consoleI need inference
  • 58Models
  • 11Labs
  • 1.05MMax context
  • $0.027/ $0.10From, per 1M in / out

Pricing

ModelLabContextInput / 1MCached / 1MOutput / 1MProviders
Kimi K3.1 Promoonshotai/kimi-k3.1-proMoonshot AI1.05M$2.00$0.20$10.005
Claude Opus 4.7claude-opus-4-7Anthropic1M$5.00$0.50$25.002
Claude Opus 4.8claude-opus-4-8Anthropic1M$5.00$0.50$25.002
Claude Sonnet 4.6claude-sonnet-4-6Anthropic1M$3.00$0.30$15.002
Gemini 3.1 Flash-Litegoogle/gemini-3.1-flash-liteGoogle1M$0.25$0.025$1.502
Gemini 3.5 Flashgoogle/gemini-3.5-flashGoogle1M$1.50$0.15$9.002
Claude Opus 5.5claude-opus-5-5Anthropic1M$4.00$0.20$20.003
GPT-6 Lunagpt-6-lunaOpenAI1.05M$0.10$0.01$0.502
Schematron V2 Smallinference-net/schematron-v2-smallInference.net128K$0.05$0.05$0.231
Schematron V2 Turboinference-net/schematron-v2-turboInference.net128K$0.03$0.03$0.151
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashDeepSeek1.05M$0.30$0.007$1.009
GPT-6 Astragpt-6-astraOpenAI1.05M$10.00$1.00$50.002
GLM 5.3 Flashz-ai/glm-5.3-flashZ.ai1.05M$0.10$0.03$0.4512
GLM 5.3z-ai/glm-5.3Z.ai1.05M$0.90$0.15$3.0012
Gemini 3.7 Flashgoogle/gemini-3.7-flashGoogle1M$1.50$0.15$7.502
Grok 4.6x-ai/grok-4.6xAI5K$2.00$0.50$6.001
DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731DeepSeek1.05M$0.53$0.017$1.589
Claude Opus 5claude-opus-5Anthropic1M$5.00$0.50$25.003
Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-liteGoogle1.05M$0.30$0.03$2.501
Gemini 3.6 Flashgoogle/gemini-3.6-flashGoogle1.05M$1.50$0.15$7.501
Kimi K3moonshotai/kimi-k3Moonshot AI1.05M$3.00$0.30$15.0010
Kimi K3 Fastmoonshotai/kimi-k3-fastMoonshot AI1.05M$4.50$0.45$22.501
GPT-5.6 Lunagpt-5.6-lunaOpenAI1.05M$0.20$0.02$1.202
GPT-5.6 Solgpt-5.6-solOpenAI1.05M$5.00$0.50$30.002
GPT-5.6 Terragpt-5.6-terraOpenAI1.05M$2.00$0.20$12.002
Grok 4.5x-ai/grok-4.5xAI5K$2.00$0.30$6.001
GLM 5.2z-ai/glm-5.2Z.ai1.05M$1.30$0.20$4.408
GLM 5.2 Fastz-ai/glm-5.2-fastZ.ai1M$2.60$0.40$8.801
Claude Fable 5claude-fable-5Anthropic1M$10.00$1.00$50.003
Qwen3.7 Plusqwen/qwen3.7-plusQwen1M$0.40$0.08$1.601
DeepSeek V4 Flashdeepseek/deepseek-v4-flashDeepSeek1M$0.23$0.0028$0.622
DeepSeek V4 Prodeepseek/deepseek-v4-proDeepSeek1.05M$2.10$0.0036$4.204
GPT-5.5gpt-5.5OpenAI1.05M$5.00$0.50$30.001
Kimi K2.6moonshotai/kimi-k2.6Moonshot AI262K$1.25$0.21$5.305
Nemotron 3 Supernvidia/nemotron-3-super-120b-a12bNVIDIA262K$0.102–$0.481
GPT-5.4gpt-5.4OpenAI1.05M$2.50$0.25$15.001
Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-previewGoogle1.05M$2.00$0.20$12.001
GLM 5z-ai/glm-5Z.ai205K$0.95$0.20$2.552
Claude Opus 4.6claude-opus-4-6Anthropic1M$5.00$0.50$25.001
Kimi K2.5moonshotai/kimi-k2.5Moonshot AI262K$0.80$0.13$3.951
Gemini 3 Flash Previewgoogle/gemini-3-flash-previewGoogle1.05M$0.50$0.05$3.001
Claude Haiku 4.5claude-haiku-4-5Anthropic2K$1.00$0.10$5.003
GPT-5 minigpt-5-miniOpenAI4K$0.25$0.025$2.001
GPT-5 nanogpt-5-nanoOpenAI4K$0.05$0.005$0.401
Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-liteGoogle1.05M$0.10$0.01$0.401
Gemini 2.5 Flashgoogle/gemini-2.5-flashGoogle1M$0.30$0.03$2.502
Gemini 2.5 Progoogle/gemini-2.5-proGoogle1M$1.25$0.125$10.002
Qwen3 14Bqwen/qwen3-14bQwen131K$0.2275–$0.911
Qwen3 30B A3Bqwen/qwen3-30b-a3bQwen41K$0.12–$0.501
GPT-4.1gpt-4.1OpenAI1.05M$2.00$0.50$8.001
GPT-4.1 minigpt-4.1-miniOpenAI1.05M$0.40$0.10$1.602
GPT-4.1 nanogpt-4.1-nanoOpenAI1.05M$0.10$0.025$0.401
Gemma 3 4Bgoogle/gemma-3-4b-itGoogle131K$0.05–$0.101
Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instructMeta131K$0.13–$0.402
Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instructMeta60K$0.027–$0.2011
Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instructMeta131K$0.05–$0.331
GPT-4o minigpt-4o-miniOpenAI128K$0.15$0.075$0.602
GPT-4ogpt-4oOpenAI128K$2.50$1.25$10.002

Inference.net's price, USD, as of November 5, 2026. Live prices

Quickstart

OpenAI-compatible
curl https://api.routerplus.com/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5.3",
    "messages": [{ "role": "user", "content": "Hello" }],
    "max_tokens": 1024,
    "provider": { "only": ["inference-net"] }
  }'

FAQ

How do I send a request to Inference.net?

Routing tries providers cheapest first, by input plus output price, so Inference.net serves a model where it is the cheapest and otherwise as a fallback. To send a request to Inference.net first, name it in provider.only or provider.order as "inference-net" or "inference-net-chat".

How much does Inference.net cost on RouterPlus?

You pay Inference.net's own price for the model. Inference.net's lowest input price is $0.027 per million tokens (Llama 3.2 1B Instruct) and its lowest output price is $0.10 per million tokens (Gemma 3 4B). Prices as of November 5, 2026.

Which models does Inference.net serve?

Kimi K3.1 Pro, Claude Opus 4.7, Claude Opus 4.8, Claude Sonnet 4.6, Gemini 3.1 Flash-Lite, Gemini 3.5 Flash, Claude Opus 5.5, GPT-6 Luna, Schematron V2 Small, Schematron V2 Turbo, DeepSeek V4.1 Flash, GPT-6 Astra, GLM 5.3 Flash, GLM 5.3, Gemini 3.7 Flash, Grok 4.6, DeepSeek V4 Flash 0731, Claude Opus 5, Gemini 3.5 Flash Lite, Gemini 3.6 Flash, Kimi K3, Kimi K3 Fast, GPT-5.6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, Grok 4.5, GLM 5.2, GLM 5.2 Fast, Claude Fable 5, Qwen3.7 Plus, DeepSeek V4 Flash, DeepSeek V4 Pro, GPT-5.5, Kimi K2.6, Nemotron 3 Super, GPT-5.4, Gemini 3.1 Pro Preview, GLM 5, Claude Opus 4.6, Kimi K2.5, Gemini 3 Flash Preview, Claude Haiku 4.5, GPT-5 mini, GPT-5 nano, Gemini 2.5 Flash Lite, Gemini 2.5 Flash, Gemini 2.5 Pro, Qwen3 14B, Qwen3 30B A3B, GPT-4.1, GPT-4.1 mini, GPT-4.1 nano, Gemma 3 4B, Llama 3.3 70B Instruct, Llama 3.2 1B Instruct, Llama 3.2 3B Instruct, GPT-4o mini and GPT-4o.

Does Inference.net keep my prompts?

Inference.net declares no prompt retention in its RouterPlus listing, per its published policy.

Route to Inference.net with one key

Open in consoleI need inference