69 models live

GPT, behind one base URL.

A GPT proxy behind one endpoint. Keep the SDK you already use, add one key, and call every GPT model in the live catalog — free to start, at the real upstream rate.

69 models
ModelKindContextText inputText outputCache readCache writeAudio inputAudio outputImage output
gpt-3-5-turbochat4k$1$2
gpt-3-5-turbo-16kchat16k$3$4
gpt-3-5-turbo-instructchat4k$1.5$2
gpt-4chat8k$30$60
gpt-4-1chat1M$2$8$0.5
gpt-4-1-minichat1M$0.4$1.6$0.1
gpt-4-1-nanochat1M$0.1$0.4$0.025
gpt-4-turbochat128k$10$30
gpt-4-turbo-previewchat128k$10$30
gpt-4ochat128k$2.5$10$1.25
gpt-4o-minichat128k$0.15$0.6$0.075
gpt-4o-mini-search-previewchat128k$0.15$0.6$0.075
gpt-4o-mini-transcribetranscription128k$1.25$5$1.25
gpt-4o-mini-ttsspeech$2.5$10$12
gpt-4o-search-previewchat128k$2.5$10$1.25
gpt-4o-transcribetranscription128k$2.5$10$2.5
gpt-4o-transcribe-diarizetranscription16k$2.5$10$2.5
gpt-5chat400k$1.25$10$0.13
gpt-5-1chat400k$1.25$10$0.13
gpt-5-1-chat-latestchat128k$1.25$10$0.13
gpt-5-1-codexchat400k$1.25$10$0.13
gpt-5-1-codex-maxchat400k$1.25$10$0.13
gpt-5-1-codex-minichat400k$0.25$2$0.03
gpt-5-2chat400k$1.75$14$0.17
gpt-5-2-chatchat128k$1.75$14$0.17
gpt-5-2-chat-latestchat128k$1.75$14$0.17
gpt-5-2-codexchat400k$1.75$14$0.17
gpt-5-2-prochat400k$21$168
gpt-5-3-chat-latestchat128k$1.75$14$0.17
gpt-5-3-codexchat400k$1.75$14$0.17
gpt-5-4chat1.1M$2.5$15$0.25
gpt-5-4-image-2image272k$8$15$2$30
gpt-5-4-minichat400k$0.75$4.5$0.075
gpt-5-4-nanochat400k$0.2$1.25$0.02
gpt-5-4-prochat1.1M$30$180
gpt-5-5chat1.1M$5$30$0.5
gpt-5-5-prochat1.1M$30$180
gpt-5-6-lunachat1.1M$0.1$0.6$0.01$0.13
gpt-5-6-luna-prochat1.1M$0.1$0.6$0.01$0.13
gpt-5-6-solchat1.1M$5$30$0.5$6.25
gpt-5-6-sol-prochat1.1M$5$30$0.5$6.25
gpt-5-6-terrachat1.1M$1$6$0.1$1.25
gpt-5-6-terra-prochat1.1M$1$6$0.1$1.25
gpt-5-chat-latestchat128k$1.25$10$0.13
gpt-5-codexchat272k$1.25$10$0.13
gpt-5-imageimage400k$10$10$1.25$40
gpt-5-image-miniimage400k$2.5$2$0.25$8
gpt-5-minichat400k$0.25$2$0.025
gpt-5-nanochat400k$0.05$0.4$0.005
gpt-5-prochat400k$15$120
gpt-5-search-apichat272k$1.25$10$0.13
gpt-audiochat128k$2.5$10$32$64
gpt-audio-1-5chat128k$2.5$10$40$80
gpt-audio-minichat128k$0.6$2.4$0.6$2.4
gpt-image-1image$0.011
gpt-image-1-5image$0.13
gpt-image-1-miniimage$2$0.2$8
gpt-image-2image$5$10$1.25$30
gpt-live-transcribetranscription$0.00028
gpt-oss-120bchat131k$0.03$0.17$0.03
gpt-oss-20bchat131k$0.03$0.13$0.03
gpt-oss-safeguard-20bchat131k$0.075$0.3$0.037
gpt-realtimerealtime32k$4$16$0.4$32$64$0.000005
gpt-realtime-1-5realtime32k$4$16$4$32$64$0.000005
gpt-realtime-2realtime32k$4$16$0.4$32$64$0.000005
gpt-realtime-2-1realtime128k$4$24$0.4$32$64$0.000005
gpt-realtime-2-1-minirealtime128k$0.6$2.4$0.06$10$20$0.0000008
gpt-realtime-minirealtime128k$0.6$2.4$0.06$10$20$0.0000008
gpt-transcribetranscription$0.000075

Questions

Straight answers.

GPT keys, pricing, and the basics.

01Is this a GPT reverse proxy?

In effect, yes. Your request hits our gateway, we route it upstream to a provider serving GPT, and the response comes back the way your client expects.

02Do I need my own provider account?

No. We run the upstream accounts. One SilvR key covers GPT and the rest of the catalog.

03Can I use GPT for free?

Yes. Every account starts on the free plan with a daily allowance you can spend on any model in the catalog, GPT included.