DeepSeek V3
DeepSeekText Generation
General-purpose chat + coding model with strong tool-use reliability. Default workhorse for most coding-agent loops.
66K contextFunction calling
deepseek
in $0.289 · out $1.18/ 1M tokens
Catalog
17 models. One base URL.
Browse every model qlaud routes to. Customer-facing prices include our 7% markup. Models with multiple hosts can be requested with :nitro for the fastest tool-verified host or :floor for the cheapest live host.
Showing all 17 models
DeepSeek R1
DeepSeekText Generation
Reasoning-tuned variant with separate chain-of-thought stream. Translates into Anthropic thinking blocks; rendered natively in Claude Code.
66K contextFunction callingReasoning
deepseek
in $0.589 · out $2.34/ 1M tokens
Claude Opus 4.7
AnthropicText Generation
Frontier coding model — 87.6% on SWE-bench Verified. Best agentic-loop reliability. Routed via Anthropic native API: cache_control markers, image content blocks, and thinking blocks all preserved verbatim — Claude Code customers see ~75% input-cost reduction from prompt cache without changing client code.
200K contextFunction callingReasoningVision
anthropic
in $5.35 · out $26.75/ 1M tokens
Claude Sonnet 4.6
AnthropicText Generation
Mid-tier Anthropic model. Strong tool use + vision; the default Claude Code CLI uses this slug. Native-passthrough route preserves prompt cache + image + thinking blocks.
200K contextFunction callingVision
anthropic
in $3.21 · out $16.05/ 1M tokens
Gemini 2.5 Pro
GoogleText Generation
Frontier multimodal — text, vision, code. 2M-token context, strong reasoning. Routed via Google AI Studio native passthrough.
2M contextFunction callingReasoningVision
google-ai-studio
in $1.34 · out $10.70/ 1M tokens
Grok 4
xAIText Generation
xAI frontier model — strong on reasoning + math + code. 256K context. Routed via xAI native passthrough.
256K contextFunction callingReasoning
grok
in $3.21 · out $16.05/ 1M tokens
Qwen 3 Coder
AlibabaText Generation
Qwen 3 Coder — Alibaba's strongest open-source coding model. 128K context, OpenAI-compat tool use. Cost-effective frontier coder.
128K contextFunction calling
alibaba-cloud
in $0.428 · out $1.71/ 1M tokens
Kimi K2
MoonshotText Generation
Moonshot Kimi K2 — agentic-coding specialist. Strong tool-use, 128K context, very fast. Excellent fallback in coding rotations.
128K contextFunction calling
moonshot
in $0.642 · out $2.68/ 1M tokens
MiniMax M2.7
MiniMaxText Generation
MiniMax M2.7 — frontier coding model. ~80% on SWE-bench Verified, strong tool-use, 200K context. Cheaper alternative to Sonnet 4.6 when prompt cache is not the bottleneck.
200K contextFunction callingReasoning
minimaxi
in $0.321 · out $1.28/ 1M tokens
GPT Image 1
OpenAIImage Generation
OpenAI image generation — high-fidelity, prompt-faithful, strong at typography in images. Default for /v1/images/generations.
0 context
openai
in $0.0000 · out $0.0000/ 1M tokens
Eleven v3 (English)
ElevenLabsText-to-Speech
World-class TTS — natural prosody, expressive voices, 30+ languages. Default for /v1/audio/speech when ElevenLabs is the preferred TTS provider.
0 context
elevenlabs
in $0.0000 · out $0.0000/ 1M tokens
GPT-4o TTS
OpenAIText-to-Speech
OpenAI text-to-speech via gpt-4o-mini-tts. Cheaper baseline; good prosody on standard English. Fallback when ElevenLabs is not preferred.
0 context
openai
in $0.0000 · out $0.0000/ 1M tokens
Deepgram Nova-3
DeepgramSpeech-to-Text
Best-in-class real-time speech-to-text — low latency, strong accent coverage, speaker diarization. Default for /v1/audio/transcriptions when Deepgram is preferred.
0 context
deepgram
in $0.0000 · out $0.0000/ 1M tokens
Whisper Large v3
OpenAISpeech-to-Text
OpenAI Whisper — strong multilingual transcription, batch-mode. Fallback when Deepgram is not preferred.
0 context
openai
in $0.0000 · out $0.0000/ 1M tokens
Perplexity Sonar Pro
PerplexityWeb Search
Web-grounded answer engine — citations, freshness, structured search. Used for /v1/search and any task that needs live-web context.
200K context
perplexity
in $3.21 · out $16.05/ 1M tokens
OpenAI text-embedding-3-large
OpenAIEmbeddings
Default embeddings — 3072-dim, strong retrieval quality. Used for /v1/embeddings.
8K context
openai
in $0.139 · out $0.0000/ 1M tokens
Claude 3.5 Sonnet (Claude Code default — routed to Sonnet 4.6)
AnthropicText Generation
Backwards-compatible alias for the slug Claude Code CLI ships with as default. Routed to Anthropic Sonnet 4.6 via native passthrough — same Anthropic model, same prompt cache, same agentic UX.
200K contextFunction callingVision
anthropic
in $3.21 · out $16.05/ 1M tokens
Provider coverage
DeepSeekGroqOpenAIAnthropicMistralCerebrasxAICloudflare Workers AIOpenRouterMiniMaxElevenLabsDeepgramPerplexityCartesiaGoogle AI StudioxAI GrokAlibaba QwenMoonshot Kimi
All routed through Cloudflare AI Gateway. We add new providers as Cloudflare adds them to its supported list.
JSON catalog
Want the full machine-readable catalog? It's public and edge-cached:
curl https://api.qlaud.ai/v1/catalog