Anthropic has suspended access to Fable 5 to comply with a US government export-control directive, so we've disabled claude-fable-5 on RedRoute. Requests to it now time out and are not billed — you won't be charged for any failed call. All other models are unaffected. We'll re-enable routing as soon as access is restored.
Claude Fable 5 and new voice models are live
Anthropic's Fable 5 — the tier above Opus, with a 1M-token context — is now routable as claude-fable-5. Voice joins the catalog too: realtime speech-to-speech (gpt-realtime-2025-08-28 over /v1/realtime), whisper-1 transcription, and text-to-speech — all on your existing key.
Gemini 3.1 Pro Preview is live
Google's Gemini 3.1 Pro Preview joins the catalog for advanced reasoning, autonomous coding, and multimodal tasks with a 1M-token context window. Call gemini-3.1-pro-preview with your existing RedRoute key.
Set an auto logout timer in /profile
Choose how long a session stays signed in — 5 / 10 / 30 minutes, 1 hour, 1 day, never, or a custom duration. Your session is invalidated automatically when it expires.
Referrals are now available
Earn $10 Duo credit per paid referral and a $50 top-up bonus every 5 paid referrals. Find your code in /profile.
Compare models side by side in /chat
Run the same prompt across frontier models, compare answer quality and cost, then keep the model that wins for your workflow.
Image and audio tools are live
Create images from /images and generate text-to-speech from /Audio using the same RedRoute key and account balance.
Video studio is available in /studio
Submit video generation jobs, track progress, and view completed clips from the developer console.
New model catalog and pricing pages
Browse chat, image, and audio models in /models, then use /compare to see official vs RedRoute effective rates.
developer console
RedRoute models — GPT-5.5, Claude Opus 4.8, DeepSeek V4 Flash, DeepSeek V4 Pro, MiniMax M3, GLM-5.1, Qwen3.7 Max, image generation, and audio
// catalog
Models we route
Same official endpoints. Same response shapes. Lower bill. GPT-5.5, Claude Opus 4.8, DeepSeek V4 Flash, DeepSeek V4 Pro, MiniMax M3, GLM-5.1, Qwen3.7 Max, image gen, and audio.
claude-fable-5chat
Anthropic Fable 5. Top-tier model above Opus with 1M context, multimodal understanding, and frontier reasoning.
★4.468 community ratings
context1000Ktokens
input$10.00/ 1M tok
output$50.00/ 1M tok
save up to 40%
with builder
official API$10.00 / $50.00input / output per 1M tok
RedRoute effective$6.00 / $30.00input / output per 1M tok
claude-fable-5
gpt-5.5chat
OpenAI frontier model. Strong at coding, agentic loops, and long-form reasoning.
★4.812 community ratings
context272Ktokens
input$5.00/ 1M tok
output$30.00/ 1M tok
save up to 75.5%
with builder
official API$5.00 / $30.00input / output per 1M tok
RedRoute effective$1.23 / $7.35input / output per 1M tok
gpt-5.5
claude-opus-4-8chat
Anthropic Opus 4.8. Best-in-class for nuanced writing and tool use.
★4.162 community ratings
context200Ktokens
input$5.00/ 1M tok
output$25.00/ 1M tok
save up to 75.5%
with builder
official API$5.00 / $25.00input / output per 1M tok
RedRoute effective$1.23 / $6.13input / output per 1M tok
claude-opus-4-8
gpt-4o-audio-previewchat
GPT-4o with audio input and output through chat completions. Built for voice assistants and speech-aware apps.
★4.765 community ratings
context128Ktokens
input$2.50/ 1M tok
output$10.00/ 1M tok
save up to 75.5%
with builder
official API$2.50 / $10.00input / output per 1M tok
RedRoute effective$0.61 / $2.45input / output per 1M tok
gpt-4o-audio-preview
gpt-realtime-2025-08-28chat
OpenAI realtime speech-to-speech model. Streams audio and text both ways over the /v1/realtime WebSocket.
★4.117 community ratings
context32Ktokens
input$4.00/ 1M tok
output$16.00/ 1M tok
save up to 75.5%
with builder
official API$4.00 / $16.00input / output per 1M tok
RedRoute effective$0.98 / $3.92input / output per 1M tok
gpt-realtime-2025-08-28
deepseek-v4-flashchat
DeepSeek V4 Flash. 1M context with low-cost thinking and non-thinking modes.
★4.443 community ratings
context1000Ktokens
input$0.14/ 1M tok
output$0.28/ 1M tok
save up to 40%
with builder
official API$0.14 / $0.28input / output per 1M tok
RedRoute effective$0.08 / $0.17input / output per 1M tok
deepseek-v4-flash
deepseek-v4-prochat
DeepSeek V4 Pro. 1M context, 384K max output, tools, JSON, and thinking mode.
★4.451 community ratings
context1000Ktokens
input$0.43/ 1M tok
output$0.87/ 1M tok
save up to 40%
with builder
official API$0.43 / $0.87input / output per 1M tok
RedRoute effective$0.26 / $0.52input / output per 1M tok
deepseek-v4-pro
MiniMax-M3chat
MiniMax M3. Agentic model built for tool use, coding, reasoning, and long context.
★4.830 community ratings
context1000Ktokens
input$0.58/ 1M tok
output$2.32/ 1M tok
save up to 10.5%
with Top-up Small
official API$0.58 / $2.32input / output per 1M tok
RedRoute effective$0.52 / $2.08input / output per 1M tok
MiniMax-M3
glm-5.1chat
GLM-5.1. Long-horizon autonomous coding model for sustained engineering tasks.
★4.712 community ratings
context198Ktokens
input$0.69/ 1M tok
output$3.45/ 1M tok
save up to 10.5%
with Top-up Small
official API$0.69 / $3.45input / output per 1M tok
RedRoute effective$0.62 / $3.09input / output per 1M tok
glm-5.1
qwen3.7-maxchat
Qwen3.7 Max. Alibaba flagship model with 1M context, tools, and strong reasoning.
★4.267 community ratings
context1000Ktokens
input$1.66/ 1M tok
output$4.97/ 1M tok
save up to 10.5%
with Top-up Small
official API$1.66 / $4.97input / output per 1M tok
RedRoute effective$1.49 / $4.45input / output per 1M tok
qwen3.7-max
gemini-3.5-flashchat
Frontier model routed through RedRoute.
★4.239 community ratings
context0tokens
input$2.25/ 1M tok
output$13.50/ 1M tok
save up to 75.5%
with builder
official API$2.25 / $13.50input / output per 1M tok
RedRoute effective$0.55 / $3.31input / output per 1M tok
gemini-3.5-flash
gemini-3.1-pro-previewchat
Google Gemini 3.1 Pro Preview for advanced reasoning, agent workflows, autonomous coding, and complex multimodal tasks.
★4.753 community ratings
context1000Ktokens
input$3.00/ 1M tok
output$18.00/ 1M tok
save up to 75.5%
with builder
official API$3.00 / $18.00input / output per 1M tok
RedRoute effective$0.73 / $4.41input / output per 1M tok
gemini-3.1-pro-preview
gpt-image-2image
High-fidelity image generation. DALL·E 3 quality with prompt adherence.
★4.743 community ratings
relative cost5¢per image
per image5¢flat
save up to 75.5%
with builder
official API5¢per image
RedRoute effective1.2¢per image
gpt-image-2
gpt-image-1-miniimage
Lightweight, fast image generation for thumbnails and concept work.
★4.163 community ratings
relative cost2¢per image
per image2¢flat
save up to 75.5%
with builder
official API2¢per image
RedRoute effective0.5¢per image
gpt-image-1-mini
gpt-4o-mini-ttsaudio
Fast, natural-sounding text-to-speech with multiple voice options.
★4.663 community ratings
relative cost30¢per request
per request30¢per request
save up to 75.5%
with builder
official API30¢per request
RedRoute effective7.3¢per request
gpt-4o-mini-tts
gemini-2.5-flash-preview-ttsaudio
Cost-effective, natural TTS with multiple voice options.
★4.541 community ratings
relative cost$0.75/ 1M tok
base cost$0.75/ 1M tok
save up to 75.5%
with builder
official API$0.75 / $15.00input / output per 1M tok
RedRoute effective$0.18 / $3.67input / output per 1M tok
gemini-2.5-flash-preview-tts
whisper-1audio
Whisper speech-to-text. Transcribes audio files and translates speech into English via /v1/audio/transcriptions.
★4.460 community ratings
relative cost$30.00/ 1M tok
base cost$30.00/ 1M tok
save up to 75.5%
with builder
official API$30.00 / $30.00input / output per 1M tok
RedRoute effective$7.35 / $7.35input / output per 1M tok
whisper-1
gemini-3-pro-image-previewimage
Image generation model routed through RedRoute.
★4.225 community ratings
relative cost5¢per image
per image5¢flat
save up to 75.5%
with builder
official API5¢per image
RedRoute effective1.2¢per image
gemini-3-pro-image-preview
gemini-2.5-flash-imageimage
Image generation model routed through RedRoute.
★4.524 community ratings
relative cost2¢per image
per image2¢flat
save up to 75.5%
with builder
official API2¢per image
RedRoute effective0.5¢per image
gemini-2.5-flash-image
gemini-3.1-flash-image-previewimage
Image generation model routed through RedRoute.
★4.542 community ratings
relative cost2¢per image
per image2¢flat
save up to 75.5%
with builder
official API2¢per image
RedRoute effective0.5¢per image
gemini-3.1-flash-image-preview
claude-opus-4-7chat
Frontier model routed through RedRoute.
★4.247 community ratings
context0tokens
input$5.00/ 1M tok
output$25.00/ 1M tok
save up to 75.5%
with builder
official API$5.00 / $25.00input / output per 1M tok
RedRoute effective$1.23 / $6.13input / output per 1M tok
claude-opus-4-7
claude-sonnet-4-6chat
Frontier model routed through RedRoute.
★4.521 community ratings
context0tokens
input$3.00/ 1M tok
output$15.00/ 1M tok
save up to 75.5%
with builder
official API$3.00 / $15.00input / output per 1M tok
RedRoute effective$0.73 / $3.67input / output per 1M tok
claude-sonnet-4-6
claude-opus-4-6chat
Frontier model routed through RedRoute.
★4.332 community ratings
context0tokens
input$5.00/ 1M tok
output$25.00/ 1M tok
save up to 75.5%
with builder
official API$5.00 / $25.00input / output per 1M tok
RedRoute effective$1.23 / $6.13input / output per 1M tok
claude-opus-4-6
gpt-5-search-apisearch
Frontier model routed through RedRoute.
★4.114 community ratings
context0tokens
input$10.00/ 1M tok
output$80.00/ 1M tok
save up to 75.5%
with builder
official API$10.00 / $80.00input / output per 1M tok
RedRoute effective$2.45 / $19.60input / output per 1M tok
gpt-5-search-api
deepseek-v3-searchsearch
Frontier model routed through RedRoute.
★4.350 community ratings
context0tokens
input$4.00/ 1M tok
output$16.00/ 1M tok
save up to 75.5%
with builder
official API$4.00 / $16.00input / output per 1M tok
RedRoute effective$0.98 / $3.92input / output per 1M tok
deepseek-v3-search
gpt-4o-search-previewsearch
Frontier model routed through RedRoute.
★4.348 community ratings
context0tokens
input$20.00/ 1M tok
output$80.00/ 1M tok
save up to 75.5%
with builder
official API$20.00 / $80.00input / output per 1M tok
RedRoute effective$4.90 / $19.60input / output per 1M tok
gpt-4o-search-preview
gpt-4o-mini-search-previewsearch
Frontier model routed through RedRoute.
★4.829 community ratings
context0tokens
input$1.12/ 1M tok
output$4.48/ 1M tok
save up to 75.5%
with builder
official API$1.12 / $4.48input / output per 1M tok
RedRoute effective$0.27 / $1.10input / output per 1M tok
gpt-4o-mini-search-preview
gpt-4o-search-preview-2025-03-11search
Frontier model routed through RedRoute.
★4.622 community ratings
context0tokens
input$20.00/ 1M tok
output$80.00/ 1M tok
save up to 75.5%
with builder
official API$20.00 / $80.00input / output per 1M tok
RedRoute effective$4.90 / $19.60input / output per 1M tok
gpt-4o-search-preview-2025-03-11
No models match that filter.
Pricing is the official API rate — that's what RedRoute meters against.
Plans give you that credit at 50–80% off.
All endpoints live at https://redroute.pro/v1.