OfoxAI3 Minutes to All LLMs
OfoxAI3 Minutes to All LLMs
OpenAIClaudeGeminiGrokDeepSeekQwenOpenAIClaudeGeminiGrokDeepSeekQwen100+ models, one API key
Qwen, DeepSeek, GLM & Kimi from $0.44/M — plus GPT, Claude & Gemini. Swap one base URL, keep your SDK.
100+
Top Models
99.9%
Uptime
\~300ms
Latency
Coding Models
Reason, refactor, and build agents with one API.Image ModelsGenerate, edit, and refine production-ready visuals.Video ModelsCreate video from text or images, with optional audio.
Authorized partner of leading cloud providers — 100+ models, one API
OpenAIOpenAI
ClaudeClaude
GeminiGemini
DeepSeekDeepSeek
QwenQwen
KimiKimi
DoubaoDoubao
ZhipuGLM
MistralMistral
OpenAIOpenAI
ClaudeClaude
GeminiGemini
DeepSeekDeepSeek
QwenQwen
KimiKimi
DoubaoDoubao
ZhipuGLM
MistralMistral
LLM API Pricing
Frontier models, from $0.44/M
Live prices from our catalog, updated automatically.
MODELPROVIDERCAPABILITIESCONTEXTPRICE / UNIT
OPEN WEIGHTFlagship and value tiers from DeepSeek, Zhipu and Moonshot
[](https://ofox.ai/models/deepseek/deepseek-v4-flash)DeepSeekDeepSeek V4 FlashDeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek, released on 2026-04-24, with 284B total parameters and 13B activated parameters.deepseek/deepseek-v4-flashAzureDeepSeekBaiLianVolcengineFunctionsCaching1M$0.44/$1.32/M
[](https://ofox.ai/models/z-ai/glm-5.2)ZhipuGLM-5.2GLM-5.2 is the flagship reasoning model on Z.ai's international platform (api.z.ai), built on an open-weights MoE architecture with a 1M-token context window.z-ai/glm-5.2ZhipuBaiLianVolcengineFunctionsReasoningCachingWeb+11M$1.4/$4.4/M
[](https://ofox.ai/models/moonshotai/kimi-k3)MoonshotAIKimi K3Kimi K3 is Moonshot AI's flagship model, a 2.8T-parameter MoE released on 2026-07-16 with a 1M-token context window and built-in thinking exposed through reasoning\_content.moonshotai/kimi-k3AzureMoonshotAIVisionFunctionsReasoningCaching+2+11M$3/$15/M
FRONTIERQwen, GPT, Claude & Gemini
[](https://ofox.ai/models/bailian/qwen3.8-max)QwenQwen3.8 MaxQwen3.8 Max is Alibaba Cloud Bailian's flagship model in the Qwen3.8 series, released on 2026-08-03.bailian/qwen3.8-maxBaiLianVisionFunctionsReasoningCaching+3+21M$2/$6/M
[](https://ofox.ai/models/openai/gpt-5.6-sol)OpenAIGPT-5.6 SolGPT-5.6 Sol is the flagship model of OpenAI's GPT-5.6 series, released on 2026-07-09.openai/gpt-5.6-solAzureVisionFunctionsReasoningCaching+2+11M$5/$30/M
[](https://ofox.ai/models/anthropic/claude-fable-5)ClaudeClaude Fable 5Claude Fable 5 is Anthropic's Mythos-class model, released on 2026-06-09 and built for long-horizon agentic autonomy — work that unfolds over extended sessions rather than a single prompt.anthropic/claude-fable-5AnthropicAzureBedrockVisionFunctionsReasoningCaching+2+11M$10/$50/M
[](https://ofox.ai/models/google/gemini-3.6-flash)GeminiGemini 3.6 FlashGemini 3.6 Flash is Google's token-efficient workhorse model, released on 2026-07-21.google/gemini-3.6-flashGoogleCloudVisionFunctionsReasoningCaching+5+41M$1.5/$7.5/M
[](https://ofox.ai/models/openai/gpt-image-2)OpenAIGPT Image 2GPT Image 2 is OpenAI's most recent image generation model, released on 2026-04-21.openai/gpt-image-2AzureVisionCaching—$5/$30/M
[](https://ofox.ai/models/bytedance/seedance-2.5)ByteDanceSeedance 2.5Seedance 2.5 is ByteDance's next-generation multimodal video creation model from the Doubao line, released on 2026-08-07.bytedance/seedance-2.5VolcengineByteDanceVideo—from $0.11/s
Model & Tool Usage Rankings
What builders actually run here
Token share across the whole platform for the 13 weeks ending Jun 28, 2026 — the same numbers as our public leaderboard, not a hand-picked list.
Anonymized, aggregated usage
MODELSFull ranking
#MODEL13-WK TRENDSHARE
01AnthropicClaude Sonnet 4.631.6%\-23.6pp02AnthropicClaude Opus 4.715.9%+7.3pp03AnthropicClaude Opus 4.66.6%\-11.9pp04OpenAIGPT 5.55.6%+10.2pp05DeepSeekDeepSeek V4 Flash5.3%+3.9pp
TOOLSFull ranking
#APP / SDK13-WK TRENDSHARE
01AnthropicClaude Code49.1%\-11.5pp
02OpenAIOpenAI SDK15.8%\-2.0pp
03AnthropicAnthropic SDK14.9%+4.4pp
04OpenAICodex CLI4.0%+6.4pp
05
Go HTTP client2.3%+0.8pp
Multimodal API: Text, Image & Video
Text, image and video — one key
Swap the endpoint and the model id — the key, the balance and the dashboard stay the same. Images from $0.03/image, video from $0.04/s.
IMAGETEXTVIDEO
POST /v1/images/generations{ "model": "bailian/qwen-image-3.0-pro", "prompt": "Robot fox in a wildflower field", "size": "2K", "n": 1}Responsedata\[0\].url
Send request
1 image·Qwen-Image 3.0 Pro·$0.04/imagepreset demo
BaiLianQwen-Image 3.0$0.03/imageBaiLianQwen-Image 3.0 Pro$0.04/imageByteDanceDoubao Seedream 5.0 Pro$0.05/imageGeminiNano Banana Pro$120/M image out
Works with Claude Code, Codex & 10+ Tools
Drop-in for the tools you already use
No SDK migration, no new client. Change one base URL in your existing setup and ofox models show up where you already work.
Claude CodeANTHROPIC\_BASE\_URL
Codex\~/.codex/config.toml
OpenCodebuilt-in providerClineCline & friendscustom OpenAI endpoint
Python · Node · cURLbase\_url
Why OfoxAI
Advantages you can verify
No claims we can't back — check any of these right now.
Platform fee0%012345678901234567890123456789%The price on the card is the price you pay. See all pricesUptime99.9%012345678901234567890123456789012345678901234567890123456789.012345678901234567890123456789%Multi-upstream failover keeps your agents running.Latency\~300ms\~012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789msEdge nodes in Tokyo, Singapore, Frankfurt and North America.TransparencyOpenLive catalog prices, public usage numbers — that's the leaderboard above.Routing, not storageReal-timeProcessed in real time, kept only in short-term operational logs — never reused beyond serving your call.EnterpriseLet's talkTeam usage controls, volume credits up to 7%, global acceleration.
Get Started
Ship with any model in 3 minutes
One base-URL swap. Pay-as-you-go. No platform fee.