My Models Directory134 of 134
Model / Provider | Capabilities | Context (In/Out) | Quota % | Price / 1M |
|---|---|---|---|---|
Claude Fable 5 neon•claude-fable-5 | 262k/16k | 15%Active Tier | FREE | |
Claude Opus 4 8 neon•claude-opus-4-8 | 262k/16k | 15%Active Tier | FREE | |
Claude Opus 5 neon•claude-opus-5 | 262k/16k | 15%Active Tier | FREE | |
Claude Sonnet 5 neon•claude-sonnet-5 | 262k/16k | 15%Active Tier | FREE | |
Deepgram Aura 2 EN (Cloudflare TTS) cloudflare•cf-tts-aura-2-en | 2k/1 | 8%Free Tier 10k Neurons/day | $0.00in / $0.01 out | |
FLUX.1 Schnell (Cloudflare Edge) cloudflare•cf-img-flux-1-schnell | 1k/1 | 14%Free Tier 10k Neurons/day | $0.00in / $0.00 out | |
Gemini 3 1 Pro neon•gemini-3-1-pro | 1M/8k | 15%Active Tier | FREE | |
Gemini 3 5 Flash neon•gemini-3-5-flash | 1M/8k | 15%Active Tier | FREE | |
Gemini 3 5 Flash Lite neon•gemini-3-5-flash-lite | 1M/8k | 15%Active Tier | FREE | |
Gemini 3 6 Flash neon•gemini-3-6-flash | 1M/8k | 15%Active Tier | FREE | |
Glm 5 2 openai•glm-5-2 | 131k/8k | 15%Active Tier | $2.50in / $10.00 out | |
Google Gemma 4 31B It nvidia•google-gemma-4-31b-it | 262k/8k | 15%Active Tier | $0.35in / $1.20 out | |
Gpt 5 6 Luna neon•gpt-5-6-luna | 131k/16k | 15%Active Tier | FREE | |
Gpt 5 6 Sol neon•gpt-5-6-sol | 131k/16k | 15%Active Tier | FREE | |
Gpt 5 6 Terra neon•gpt-5-6-terra | 131k/16k | 15%Active Tier | FREE | |
Gpt Oss 120B openai•gpt-oss-120b | 1M/8k | 15%Active Tier | $2.50in / $10.00 out | |
Kimi K3 openai•kimi-k3 | 131k/8k | 15%Active Tier | $2.50in / $10.00 out | |
Llama 4 Maverick neon•llama-4-maverick | 131k/8k | 15%Active Tier | FREE | |
Meta Llama 3 3 70B Instruct openai•meta-llama-3-3-70b-instruct | 131k/8k | 15%Active Tier | $2.50in / $10.00 out | |
Minimaxai Minimax M3 nvidia•minimaxai-minimax-m3 | 1M/8k | 15%Active Tier | $0.35in / $1.20 out | |
Nvidia Nemotron 3 Nano Omni 30B A3B Reasoning nvidia•nvidia-nemotron-3-nano-omni-30b-a3b-reasoning | 131k/16k | 15%Active Tier | $0.35in / $1.20 out | |
Nvidia Nemotron 3 Super 120B A12B nvidia•nvidia-nemotron-3-super-120b-a12b | 1M/16k | 15%Active Tier | $0.35in / $1.20 out | |
Nvidia Nemotron 3 Ultra 550B A55B nvidia•nvidia-nemotron-3-ultra-550b-a55b | 1M/16k | 15%Active Tier | $0.35in / $1.20 out | |
Openai Gpt Oss 120B nvidia•openai-gpt-oss-120b | 1M/8k | 15%Active Tier | $0.35in / $1.20 out | |
Qwen3 Next 80B A3B Instruct openai•qwen3-next-80b-a3b-instruct | 131k/8k | 15%Active Tier | $2.50in / $10.00 out | |
Qwen35 122B A10B openai•qwen35-122b-a10b | 131k/8k | 15%Active Tier | $2.50in / $10.00 out | |
Stepfun Ai Step 3 7 Flash nvidia•stepfun-ai-step-3-7-flash | 262k/8k | 15%Active Tier | $0.35in / $1.20 out | |
Thinkingmachines Inkling nvidia•thinkingmachines-inkling | 262k/16k | 15%Active Tier | $0.35in / $1.20 out | |
Whisper Large v3 Turbo (Cloudflare STT) cloudflare•cf-stt-whisper-large-v3-turbo | 30k/4k | 11%Free Tier 10k Neurons/day | $0.00in / $0.00 out | |
Z Ai Glm 5.2 nvidia•z-ai-glm-5.2 | 131k/8k | 15%Active Tier | $0.35in / $1.20 out | |
cf-deepseek-ai-deepseek-r1-distill-qwen-32b cloudflare•cf-deepseek-ai-deepseek-r1-distill-qwen-32b | 131k/16k | 15%Active Tier | FREE | |
cf-google-gemma-4-26b-a4b-it cloudflare•cf-google-gemma-4-26b-a4b-it | 262k/8k | 15%Active Tier | FREE | |
cf-meta-llama-4-scout-17b-16e-instruct cloudflare•cf-meta-llama-4-scout-17b-16e-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-moonshotai-kimi-k2-6 cloudflare•cf-moonshotai-kimi-k2-6 | 131k/8k | 15%Active Tier | FREE | |
cf-moonshotai-kimi-k2-7-code cloudflare•cf-moonshotai-kimi-k2-7-code | 131k/8k | 15%Active Tier | FREE | |
cf-nvidia-nemotron-3-120b-a12b nvidia•cf-nvidia-nemotron-3-120b-a12b | 1M/8k | 15%Active Tier | $0.35in / $1.20 out | |
cf-openai-gpt-oss-120b cloudflare•cf-openai-gpt-oss-120b | 1M/8k | 15%Active Tier | FREE | |
cf-qwen-qwq-32b cloudflare•cf-qwen-qwq-32b | 131k/16k | 15%Active Tier | FREE | |
cf-zai-org-glm-4-7-flash cloudflare•cf-zai-org-glm-4-7-flash | 131k/8k | 15%Active Tier | FREE | |
cf-zai-org-glm-5-2 cloudflare•cf-zai-org-glm-5-2 | 131k/8k | 15%Active Tier | FREE | |
Agency Smoke openai•agency-smoke | 131k/8k | 15%Active Tier | $2.50in / $10.00 out | |
Claude Haiku 4 5 neon•claude-haiku-4-5 | 262k/16k | 15%Active Tier | FREE | |
Claude Opus 4 1 neon•claude-opus-4-1 | 262k/16k | 15%Active Tier | FREE | |
Claude Opus 4 5 neon•claude-opus-4-5 | 262k/16k | 15%Active Tier | FREE | |
Claude Opus 4 6 neon•claude-opus-4-6 | 262k/16k | 15%Active Tier | FREE | |
Claude Opus 4 7 neon•claude-opus-4-7 | 262k/16k | 15%Active Tier | FREE | |
Claude Sonnet 4 5 neon•claude-sonnet-4-5 | 262k/16k | 15%Active Tier | FREE | |
Claude Sonnet 4 6 neon•claude-sonnet-4-6 | 262k/16k | 15%Active Tier | FREE | |
Gemini 3 1 Flash Lite neon•gemini-3-1-flash-lite | 1M/8k | 15%Active Tier | FREE | |
Gemini 3 Flash neon•gemini-3-flash | 1M/8k | 15%Active Tier | FREE | |
Gemma 3 12B openai•gemma-3-12b | 131k/8k | 15%Active Tier | $2.50in / $10.00 out | |
Gpt 5 neon•gpt-5 | 131k/16k | 15%Active Tier | FREE | |
Gpt 5 1 neon•gpt-5-1 | 131k/16k | 15%Active Tier | FREE | |
Gpt 5 2 neon•gpt-5-2 | 131k/16k | 15%Active Tier | FREE | |
Gpt 5 3 Codex neon•gpt-5-3-codex | 131k/16k | 15%Active Tier | FREE | |
Gpt 5 4 neon•gpt-5-4 | 131k/16k | 15%Active Tier | FREE | |
Gpt 5 4 Mini neon•gpt-5-4-mini | 131k/16k | 15%Active Tier | FREE | |
Gpt 5 4 Nano neon•gpt-5-4-nano | 131k/16k | 15%Active Tier | FREE | |
Gpt 5 5 neon•gpt-5-5 | 131k/16k | 15%Active Tier | FREE | |
Gpt 5 5 Pro neon•gpt-5-5-pro | 131k/16k | 15%Active Tier | FREE | |
Gpt 5 Mini neon•gpt-5-mini | 131k/16k | 15%Active Tier | FREE | |
Gpt 5 Nano neon•gpt-5-nano | 131k/16k | 15%Active Tier | FREE | |
Gpt Oss 20B openai•gpt-oss-20b | 131k/8k | 15%Active Tier | $2.50in / $10.00 out | |
Inkling openai•inkling | 262k/8k | 15%Active Tier | $2.50in / $10.00 out | |
Meta Llama 3 1 8B Instruct openai•meta-llama-3-1-8b-instruct | 131k/8k | 15%Active Tier | $2.50in / $10.00 out | |
Meta Llama 3.1 70B Instruct[Legacy] nvidia•meta-llama-3.1-70b-instruct | 131k/8k | 15%Active Tier | $0.35in / $1.20 out | |
Meta Llama 3.1 8B Instruct[Legacy] nvidia•meta-llama-3.1-8b-instruct | 131k/8k | 15%Active Tier | $0.35in / $1.20 out | |
Openai Gpt Oss 20B nvidia•openai-gpt-oss-20b | 131k/8k | 15%Active Tier | $0.35in / $1.20 out | |
Poolside Laguna Xs 2 1 nvidia•poolside-laguna-xs-2-1 | 131k/8k | 15%Active Tier | $0.35in / $1.20 out | |
cf-aisingapore-gemma-sea-lion-v4-27b-it cloudflare•cf-aisingapore-gemma-sea-lion-v4-27b-it | 131k/8k | 15%Active Tier | FREE | |
cf-google-gemma-2b-it-lora[Legacy] cloudflare•cf-google-gemma-2b-it-lora | 131k/8k | 15%Active Tier | FREE | |
cf-google-gemma-7b-it-lora[Legacy] cloudflare•cf-google-gemma-7b-it-lora | 131k/8k | 15%Active Tier | FREE | |
cf-ibm-granite-granite-4-0-h-micro cloudflare•cf-ibm-granite-granite-4-0-h-micro | 131k/8k | 15%Active Tier | FREE | |
cf-jami-aisingapore-gemma-sea-lion-v4-27b-it cloudflare•cf-jami-aisingapore-gemma-sea-lion-v4-27b-it | 131k/8k | 15%Active Tier | FREE | |
cf-jami-deepseek-ai-deepseek-r1-distill-qwen-32b cloudflare•cf-jami-deepseek-ai-deepseek-r1-distill-qwen-32b | 131k/16k | 15%Active Tier | FREE | |
cf-jami-google-gemma-2b-it-lora[Legacy] cloudflare•cf-jami-google-gemma-2b-it-lora | 131k/8k | 15%Active Tier | FREE | |
cf-jami-google-gemma-4-26b-a4b-it cloudflare•cf-jami-google-gemma-4-26b-a4b-it | 262k/8k | 15%Active Tier | FREE | |
cf-jami-google-gemma-7b-it-lora[Legacy] cloudflare•cf-jami-google-gemma-7b-it-lora | 131k/8k | 15%Active Tier | FREE | |
cf-jami-ibm-granite-granite-4-0-h-micro cloudflare•cf-jami-ibm-granite-granite-4-0-h-micro | 131k/8k | 15%Active Tier | FREE | |
cf-jami-meta-llama-3-1-8b-instruct-fp8 cloudflare•cf-jami-meta-llama-3-1-8b-instruct-fp8 | 131k/8k | 15%Active Tier | FREE | |
cf-jami-meta-llama-3-2-11b-vision-instruct cloudflare•cf-jami-meta-llama-3-2-11b-vision-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-jami-meta-llama-3-2-1b-instruct cloudflare•cf-jami-meta-llama-3-2-1b-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-jami-meta-llama-3-2-3b-instruct cloudflare•cf-jami-meta-llama-3-2-3b-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-jami-meta-llama-3-3-70b-instruct-fp8-fast cloudflare•cf-jami-meta-llama-3-3-70b-instruct-fp8-fast | 131k/8k | 15%Active Tier | FREE | |
cf-jami-meta-llama-4-scout-17b-16e-instruct cloudflare•cf-jami-meta-llama-4-scout-17b-16e-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-jami-meta-llama-llama-2-7b-chat-hf-lora[Legacy] cloudflare•cf-jami-meta-llama-llama-2-7b-chat-hf-lora | 131k/8k | 15%Active Tier | FREE | |
cf-jami-mistral-mistral-7b-instruct-v0-2-lora[Legacy] cloudflare•cf-jami-mistral-mistral-7b-instruct-v0-2-lora | 131k/8k | 15%Active Tier | FREE | |
cf-jami-mistralai-mistral-small-3-1-24b-instruct cloudflare•cf-jami-mistralai-mistral-small-3-1-24b-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-jami-moonshotai-kimi-k2-6 cloudflare•cf-jami-moonshotai-kimi-k2-6 | 131k/8k | 15%Active Tier | FREE | |
cf-jami-moonshotai-kimi-k2-7-code cloudflare•cf-jami-moonshotai-kimi-k2-7-code | 131k/8k | 15%Active Tier | FREE | |
cf-jami-nvidia-nemotron-3-120b-a12b nvidia•cf-jami-nvidia-nemotron-3-120b-a12b | 1M/8k | 15%Active Tier | $0.35in / $1.20 out | |
cf-jami-openai-gpt-oss-120b cloudflare•cf-jami-openai-gpt-oss-120b | 1M/8k | 15%Active Tier | FREE | |
cf-jami-openai-gpt-oss-20b cloudflare•cf-jami-openai-gpt-oss-20b | 131k/8k | 15%Active Tier | FREE | |
cf-jami-qwen-qwen2-5-coder-32b-instruct cloudflare•cf-jami-qwen-qwen2-5-coder-32b-instruct | 33k/8k | 15%Active Tier | FREE | |
cf-jami-qwen-qwen3-30b-a3b-fp8 cloudflare•cf-jami-qwen-qwen3-30b-a3b-fp8 | 131k/8k | 15%Active Tier | FREE | |
cf-jami-qwen-qwq-32b cloudflare•cf-jami-qwen-qwq-32b | 131k/16k | 15%Active Tier | FREE | |
cf-jami-zai-org-glm-4-7-flash cloudflare•cf-jami-zai-org-glm-4-7-flash | 131k/8k | 15%Active Tier | FREE | |
cf-jami-zai-org-glm-5-2 cloudflare•cf-jami-zai-org-glm-5-2 | 131k/8k | 15%Active Tier | FREE | |
cf-meta-llama-3-1-8b-instruct-fp8 cloudflare•cf-meta-llama-3-1-8b-instruct-fp8 | 131k/8k | 15%Active Tier | FREE | |
cf-meta-llama-3-2-11b-vision-instruct cloudflare•cf-meta-llama-3-2-11b-vision-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-meta-llama-3-2-1b-instruct cloudflare•cf-meta-llama-3-2-1b-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-meta-llama-3-2-3b-instruct cloudflare•cf-meta-llama-3-2-3b-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-meta-llama-3-3-70b-instruct-fp8-fast cloudflare•cf-meta-llama-3-3-70b-instruct-fp8-fast | 131k/8k | 15%Active Tier | FREE | |
cf-meta-llama-llama-2-7b-chat-hf-lora[Legacy] cloudflare•cf-meta-llama-llama-2-7b-chat-hf-lora | 131k/8k | 15%Active Tier | FREE | |
cf-mistral-mistral-7b-instruct-v0-2-lora[Legacy] cloudflare•cf-mistral-mistral-7b-instruct-v0-2-lora | 131k/8k | 15%Active Tier | FREE | |
cf-mistralai-mistral-small-3-1-24b-instruct cloudflare•cf-mistralai-mistral-small-3-1-24b-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-openai-gpt-oss-20b cloudflare•cf-openai-gpt-oss-20b | 131k/8k | 15%Active Tier | FREE | |
cf-qwen-qwen2-5-coder-32b-instruct cloudflare•cf-qwen-qwen2-5-coder-32b-instruct | 33k/8k | 15%Active Tier | FREE | |
cf-qwen-qwen3-30b-a3b-fp8 cloudflare•cf-qwen-qwen3-30b-a3b-fp8 | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-aisingapore-gemma-sea-lion-v4-27b-it cloudflare•cf-yrka-aisingapore-gemma-sea-lion-v4-27b-it | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-deepseek-ai-deepseek-r1-distill-qwen-32b cloudflare•cf-yrka-deepseek-ai-deepseek-r1-distill-qwen-32b | 131k/16k | 15%Active Tier | FREE | |
cf-yrka-google-gemma-2b-it-lora[Legacy] cloudflare•cf-yrka-google-gemma-2b-it-lora | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-google-gemma-4-26b-a4b-it cloudflare•cf-yrka-google-gemma-4-26b-a4b-it | 262k/8k | 15%Active Tier | FREE | |
cf-yrka-google-gemma-7b-it-lora[Legacy] cloudflare•cf-yrka-google-gemma-7b-it-lora | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-ibm-granite-granite-4-0-h-micro cloudflare•cf-yrka-ibm-granite-granite-4-0-h-micro | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-meta-llama-3-1-8b-instruct-fp8 cloudflare•cf-yrka-meta-llama-3-1-8b-instruct-fp8 | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-meta-llama-3-2-11b-vision-instruct cloudflare•cf-yrka-meta-llama-3-2-11b-vision-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-meta-llama-3-2-1b-instruct cloudflare•cf-yrka-meta-llama-3-2-1b-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-meta-llama-3-2-3b-instruct cloudflare•cf-yrka-meta-llama-3-2-3b-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-meta-llama-3-3-70b-instruct-fp8-fast cloudflare•cf-yrka-meta-llama-3-3-70b-instruct-fp8-fast | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-meta-llama-4-scout-17b-16e-instruct cloudflare•cf-yrka-meta-llama-4-scout-17b-16e-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-meta-llama-llama-2-7b-chat-hf-lora[Legacy] cloudflare•cf-yrka-meta-llama-llama-2-7b-chat-hf-lora | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-mistral-mistral-7b-instruct-v0-2-lora[Legacy] cloudflare•cf-yrka-mistral-mistral-7b-instruct-v0-2-lora | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-mistralai-mistral-small-3-1-24b-instruct cloudflare•cf-yrka-mistralai-mistral-small-3-1-24b-instruct | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-moonshotai-kimi-k2-6 cloudflare•cf-yrka-moonshotai-kimi-k2-6 | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-moonshotai-kimi-k2-7-code cloudflare•cf-yrka-moonshotai-kimi-k2-7-code | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-nvidia-nemotron-3-120b-a12b nvidia•cf-yrka-nvidia-nemotron-3-120b-a12b | 1M/8k | 15%Active Tier | $0.35in / $1.20 out | |
cf-yrka-openai-gpt-oss-120b cloudflare•cf-yrka-openai-gpt-oss-120b | 1M/8k | 15%Active Tier | FREE | |
cf-yrka-openai-gpt-oss-20b cloudflare•cf-yrka-openai-gpt-oss-20b | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-qwen-qwen2-5-coder-32b-instruct cloudflare•cf-yrka-qwen-qwen2-5-coder-32b-instruct | 33k/8k | 15%Active Tier | FREE | |
cf-yrka-qwen-qwen3-30b-a3b-fp8 cloudflare•cf-yrka-qwen-qwen3-30b-a3b-fp8 | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-qwen-qwq-32b cloudflare•cf-yrka-qwen-qwq-32b | 131k/16k | 15%Active Tier | FREE | |
cf-yrka-zai-org-glm-4-7-flash cloudflare•cf-yrka-zai-org-glm-4-7-flash | 131k/8k | 15%Active Tier | FREE | |
cf-yrka-zai-org-glm-5-2 cloudflare•cf-yrka-zai-org-glm-5-2 | 131k/8k | 15%Active Tier | FREE |
Evals & Speed Matrix
Model | P50 Latency | Success % | GPQAscience | AIMEmath | SWEcode 2x | Terminalagent 2x | MMMUvision | Weighted |
|---|---|---|---|---|---|---|---|---|
FLUX.1 Schnell (Cloudflare Edge) | 1100ms(1 t/s) | 99.8% | N/A | N/A | N/A | N/A | 82.5% | 82.5% |
Gpt 5 4 | 220ms(120 t/s) | 99.9% | 89.6% | 95.0% | 57.7% | 88.5% | 85.2% | 80.3% |
cf-moonshotai-kimi-k2-7-code | 220ms(120 t/s) | 99.9% | 80.0% | 86.5% | 62.3% | 85.1% | N/A | 76.9% |
cf-moonshotai-kimi-k2-6 | 220ms(120 t/s) | 99.9% | 83.2% | 93.3% | 58.6% | 81.4% | 76.0% | 76.1% |
Glm 5 2 | 220ms(120 t/s) | 99.9% | 81.5% | 85.0% | 60.1% | 82.0% | 68.4% | 74.2% |
Z Ai Glm 5.2 | 220ms(120 t/s) | 99.9% | 81.5% | 85.0% | 60.1% | 82.0% | 68.4% | 74.2% |
cf-zai-org-glm-5-2 | 220ms(120 t/s) | 99.9% | 81.5% | 85.0% | 60.1% | 82.0% | 68.4% | 74.2% |
Nvidia Nemotron 3 Ultra 550B A55B | 480ms(65 t/s) | 99.9% | 85.0% | 89.1% | 52.0% | 78.5% | 74.2% | 72.8% |
Llama 4 Maverick | 220ms(120 t/s) | 99.9% | 84.1% | 88.0% | 50.1% | 70.8% | 80.0% | 70.6% |
Minimaxai Minimax M3 | 220ms(120 t/s) | 99.9% | 82.0% | 86.4% | 48.2% | 72.3% | 81.5% | 70.1% |
Gemini 3 5 Flash | 95ms(210 t/s) | 99.9% | 81.2% | 84.5% | 45.8% | 76.2% | 79.4% | 69.9% |
Gemini 3 1 Pro | 220ms(120 t/s) | 99.9% | 79.0% | 94.2% | 54.2% | 65.4% | 75.1% | 69.6% |
Nvidia Nemotron 3 Super 120B A12B | 220ms(120 t/s) | 99.9% | 80.1% | 84.5% | 46.2% | 71.0% | N/A | 66.5% |
cf-zai-org-glm-4-7-flash | 95ms(210 t/s) | 99.9% | 68.4% | 78.2% | 45.1% | 68.5% | 61.2% | 62.1% |
Gpt Oss 120B | 220ms(120 t/s) | 99.9% | 76.5% | 85.0% | 41.8% | 55.4% | N/A | 59.3% |
Openai Gpt Oss 120B | 220ms(120 t/s) | 99.9% | 76.5% | 85.0% | 41.8% | 55.4% | N/A | 59.3% |
cf-openai-gpt-oss-120b | 220ms(120 t/s) | 99.9% | 76.5% | 85.0% | 41.8% | 55.4% | N/A | 59.3% |
cf-meta-llama-4-scout-17b-16e-instruct | 220ms(120 t/s) | 99.9% | 73.5% | 76.2% | 35.4% | 58.1% | 74.1% | 58.7% |
Google Gemma 4 31B It | 220ms(120 t/s) | 99.9% | 70.1% | 88.3% | 39.5% | 52.0% | N/A | 56.9% |
cf-google-gemma-4-26b-a4b-it | 220ms(120 t/s) | 99.9% | 70.1% | 88.3% | 39.5% | 52.0% | N/A | 56.9% |
cf-deepseek-ai-deepseek-r1-distill-qwen-32b | 480ms(65 t/s) | 99.9% | 69.0% | 90.5% | 34.0% | 42.5% | N/A | 52.1% |
cf-qwen-qwq-32b | 220ms(120 t/s) | 99.9% | 68.5% | 89.1% | 32.4% | 41.2% | N/A | 50.8% |
Gpt Oss 20B | 220ms(120 t/s) | 99.9% | 62.0% | 86.4% | 28.0% | 30.1% | N/A | 44.1% |
Openai Gpt Oss 20B | 220ms(120 t/s) | 99.9% | 62.0% | 86.4% | 28.0% | 30.1% | N/A | 44.1% |
cf-openai-gpt-oss-20b | 220ms(120 t/s) | 99.9% | 62.0% | 86.4% | 28.0% | 30.1% | N/A | 44.1% |
cf-aisingapore-gemma-sea-lion-v4-27b-it | 220ms(120 t/s) | 99.9% | 65.0% | 68.0% | 24.5% | 38.0% | N/A | 43.0% |
Meta Llama 3 3 70B Instruct | 220ms(120 t/s) | 99.9% | 64.2% | 61.5% | 25.1% | 35.4% | N/A | 41.1% |
cf-meta-llama-3-3-70b-instruct-fp8-fast | 220ms(120 t/s) | 99.9% | 64.2% | 61.5% | 25.1% | 35.4% | N/A | 41.1% |
cf-qwen-qwen2-5-coder-32b-instruct | 220ms(120 t/s) | 99.9% | 55.0% | 51.2% | 36.0% | 28.0% | N/A | 39.0% |
cf-qwen-qwen3-30b-a3b-fp8 | 95ms(210 t/s) | 99.9% | 60.5% | 74.0% | 18.2% | 29.5% | N/A | 38.3% |
cf-meta-llama-3-2-11b-vision-instruct | 220ms(120 t/s) | 99.9% | 42.0% | 32.1% | 9.4% | 12.0% | 55.0% | 24.6% |
cf-ibm-granite-granite-4-0-h-micro | 220ms(120 t/s) | 99.9% | 45.0% | 35.2% | 14.5% | 18.0% | N/A | 24.2% |
cf-meta-llama-3-2-3b-instruct | 95ms(210 t/s) | 99.9% | 35.0% | 24.5% | 8.0% | 10.5% | N/A | 16.1% |
Agency Smoke | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gemini 3 6 Flash | 95ms(210 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gemini 3 5 Flash Lite | 95ms(210 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gemini 3 1 Flash Lite | 95ms(210 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gemini 3 Flash | 95ms(210 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gemma 3 12B | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Claude Opus 5 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Claude Sonnet 5 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Claude Fable 5 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Claude Opus 4 8 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Claude Opus 4 7 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Claude Opus 4 6 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Claude Opus 4 5 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Claude Sonnet 4 6 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Claude Sonnet 4 5 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Claude Haiku 4 5 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Claude Opus 4 1 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gpt 5 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gpt 5 1 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gpt 5 2 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gpt 5 4 Mini | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gpt 5 4 Nano | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gpt 5 Mini | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gpt 5 Nano | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gpt 5 5 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gpt 5 5 Pro | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gpt 5 6 Sol | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gpt 5 6 Terra | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gpt 5 6 Luna | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Gpt 5 3 Codex | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Meta Llama 3 1 8B Instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Qwen3 Next 80B A3B Instruct | 95ms(210 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Qwen35 122B A10B | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Kimi K3 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Inkling | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Meta Llama 3.1 8B Instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Meta Llama 3.1 70B Instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Nvidia Nemotron 3 Nano Omni 30B A3B Reasoning | 95ms(210 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Stepfun Ai Step 3 7 Flash | 95ms(210 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Thinkingmachines Inkling | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Poolside Laguna Xs 2 1 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-google-gemma-4-26b-a4b-it | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-google-gemma-4-26b-a4b-it | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-zai-org-glm-4-7-flash | 95ms(210 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-zai-org-glm-4-7-flash | 95ms(210 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-zai-org-glm-5-2 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-zai-org-glm-5-2 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-openai-gpt-oss-120b | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-openai-gpt-oss-120b | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-moonshotai-kimi-k2-6 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-moonshotai-kimi-k2-6 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-moonshotai-kimi-k2-7-code | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-moonshotai-kimi-k2-7-code | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-mistralai-mistral-small-3-1-24b-instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-mistralai-mistral-small-3-1-24b-instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-mistralai-mistral-small-3-1-24b-instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-nvidia-nemotron-3-120b-a12b | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-nvidia-nemotron-3-120b-a12b | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-nvidia-nemotron-3-120b-a12b | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-qwen-qwen3-30b-a3b-fp8 | 95ms(210 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-qwen-qwen3-30b-a3b-fp8 | 95ms(210 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-meta-llama-4-scout-17b-16e-instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-meta-llama-4-scout-17b-16e-instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-aisingapore-gemma-sea-lion-v4-27b-it | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-aisingapore-gemma-sea-lion-v4-27b-it | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-deepseek-ai-deepseek-r1-distill-qwen-32b | 480ms(65 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-deepseek-ai-deepseek-r1-distill-qwen-32b | 480ms(65 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-google-gemma-2b-it-lora | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-google-gemma-2b-it-lora | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-google-gemma-2b-it-lora | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-google-gemma-7b-it-lora | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-google-gemma-7b-it-lora | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-google-gemma-7b-it-lora | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-ibm-granite-granite-4-0-h-micro | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-ibm-granite-granite-4-0-h-micro | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-meta-llama-llama-2-7b-chat-hf-lora | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-meta-llama-llama-2-7b-chat-hf-lora | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-meta-llama-llama-2-7b-chat-hf-lora | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-meta-llama-3-1-8b-instruct-fp8 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-meta-llama-3-1-8b-instruct-fp8 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-meta-llama-3-1-8b-instruct-fp8 | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-meta-llama-3-2-11b-vision-instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-meta-llama-3-2-11b-vision-instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-meta-llama-3-2-1b-instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-meta-llama-3-2-1b-instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-meta-llama-3-2-1b-instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-meta-llama-3-2-3b-instruct | 95ms(210 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-meta-llama-3-2-3b-instruct | 95ms(210 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-meta-llama-3-3-70b-instruct-fp8-fast | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-meta-llama-3-3-70b-instruct-fp8-fast | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-mistral-mistral-7b-instruct-v0-2-lora | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-mistral-mistral-7b-instruct-v0-2-lora | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-mistral-mistral-7b-instruct-v0-2-lora | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-openai-gpt-oss-20b | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-openai-gpt-oss-20b | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-qwen-qwen2-5-coder-32b-instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-qwen-qwen2-5-coder-32b-instruct | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-yrka-qwen-qwq-32b | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
cf-jami-qwen-qwq-32b | 220ms(120 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |
Deepgram Aura 2 EN (Cloudflare TTS) | 340ms(1 t/s) | 100.0% | N/A | N/A | N/A | N/A | N/A | N/A |
Whisper Large v3 Turbo (Cloudflare STT) | 420ms(1 t/s) | 99.9% | N/A | N/A | N/A | N/A | N/A | N/A |