Inception1009 QPS1 models · $0.250 | 1 | Catalog 1.70s | Catalog 1009 c/s | $0.250 | — | Mercury 2 |
Meituan500 QPS4 models · $0.100 | 4 | Catalog 1.50s | Catalog 500 c/s | $0.100 | — | LongCat-Flash-Lite |
Googlecache pricing · 85–90 QPS45 models · $0.250–$2.50 · 3.11s median TTFT · 99.8% success | 45Vision · Image · Video | 3.11sP95 24.80s | 440 c/sP5 252 c/s | $0.250–$2.50 | 99.8%7 days | Gemini 3.7 Flash, Gemini 3.7 Flash, Gemini 3.7 Flash |
Sambanova327.7 QPS6 models · $0.400 | 6 | Catalog 1.08s | Catalog 328 c/s | $0.400 | — | Qwen3 32B |
FriendliAIcache pricing5 models · $0.140–$1.40 · 100.0% success | 5Vision | — | 277 c/sP5 96 c/s | $0.140–$1.40 | 100.0%7 days | GLM-5.2, Gemma 4 31B, Gemma 4 31B |
Togethercache pricing26 models · $0.300–$3.00 · 872ms median TTFT · 100.0% success | 26Vision | 872msP95 8.36s | 147 c/sP5 10 c/s | $0.300–$3.00 | 100.0%7 days | Qwen3.8 Max, DeepSeek-V4-Pro-0813, Kimi K3 |
Novitacache pricing · 32.43–88.84 QPS56 models · $0.100–$3.00 · 2.48s median TTFT · 99.5% success | 56Vision | 2.48sP95 6.51s | 136 c/sP5 14 c/s | $0.100–$3.00 | 99.5%7 days | GLM-5.3, GLM-5.3-Flash, GLM-5.3-Flash |
StepFuncache pricing · 150 QPS1 models · $0.100 · 889ms median TTFT · 100.0% success | 1Vision | 889msP95 1.64s | 135 c/sP5 56 c/s | $0.100 | 100.0%7 days | Step-3.5-Flash, Step-3.5-Flash |
DeepInfracache pricing · 26.95–82.57 QPS58 models · $0.050–$1.65 · 2.07s median TTFT · 98.8% success | 58Vision | 2.07sP95 10.42s | 111 c/sP5 13 c/s | $0.050–$1.65 | 98.8%7 days | GLM-5.3-Flash, Qwen3.8 Max, DeepSeek-V4-Pro-0813 |
OpenAIcache pricing · 50–200 QPS58 models · $0.100–$12.5 · 2.94s median TTFT · 97.0% success | 58Vision · Image · Audio · Video | 2.94sP95 9.43s | 98 c/sP5 13 c/s | $0.100–$12.5 | 97.0%7 days | GPT-5.6 Cyber, GPT-5.6 Cyber, GPT-5.6 Luna |
Azure90–99 QPS11 models · $0.500–$10.0 | 11Vision | Catalog 590ms | Catalog 95 c/s | $0.500–$10.0 | — | GPT-4 Turbo, GPT-4o, GPT-4o |
DeepSeekcache pricing · 100 QPS11 models · $0.140–$1.32 · 1.23s median TTFT · 100.0% success | 11Vision | 1.23sP95 2.71s | 86 c/sP5 7 c/s | $0.140–$1.32 | 100.0%7 days | DeepSeek-V4-Flash-Vision-Exp, DeepSeek-V4-Flash-Vision-Exp, DeepSeek-V4-Pro-0813 |
Moonshot AIcache pricing4 models · $0.950–$3.00 · 3.47s median TTFT · 90.9% success | 4Vision | 3.47sP95 30.55s | 79 c/sP5 15 c/s | $0.950–$3.00 | 90.9%7 days | Kimi K3, Kimi K3, Kimi K3 |
Anthropiccache pricing · 42–100 QPS20 models · $1.00–$10.0 · 2.43s median TTFT · 98.7% success | 20Vision | 2.43sP95 9.67s | 70 c/sP5 4 c/s | $1.00–$10.0 | 98.7%7 days | Claude Opus 5, Claude Opus 5, Claude Sonnet 5 |
Fireworkscache pricing · 122.4 QPS40 models · $0.300–$3.00 · 869ms median TTFT · 100.0% success | 40Vision | 869msP95 4.45s | 64 c/sP5 4 c/s | $0.300–$3.00 | 100.0%7 days | Qwen3.8 Max, Kimi K3, Kimi K3 |
Meta Model APIcache pricing2 models · $0.100–$1.25 · 1.38s median TTFT · 100.0% success | 2Vision | 1.38sP95 3.02s | 56 c/sP5 3 c/s | $0.100–$1.25 | 100.0%7 days | Muse Spark 1.2, Muse Spark 1.2, Muse Spark 1.2 |
MiniMaxcache pricing · 70–100 QPS10 models · $0.300 · 1.38s median TTFT · 100.0% success | 10Vision · Audio · Video | 1.38sP95 2.37s | 55 c/sP5 11 c/s | $0.300 | 100.0%7 days | MiniMax M3, MiniMax M3, MiniMax M3 |
Mistral AI45.89 QPS18 models · $0.150–$1.50 | 18Vision | Catalog 1.70s | Catalog 46 c/s | $0.150–$1.50 | — | Mistral Medium 3.5, Mistral Medium 3.5, Mistral Small 4 |
xAIcache pricing · 76.41–100 QPS24 models · $0.200–$3.00 · 1.27s median TTFT · 62.0% success | 24Vision · Image · Audio · Video | 1.27sP95 1.66s | 32 c/sP5 8 c/s | $0.200–$3.00 | 62.0%7 days | Grok 4.6, Grok 4.6, Grok 4.5 |
ZAIcache pricing · 30 QPS9 models · $0.150–$1.40 · 0.0% success | 9Vision | Catalog 3.00s | Catalog 30 c/s | $0.150–$1.40 | 0.0%7 days | GLM-5.3-Flash, GLM-5.3-Flash, GLM-5.3-Flash |
Xiaomi4 models · $0.435 · 5.60s median TTFT · 100.0% success | 4 | 5.60sP95 17.84s | 8 c/sP5 3 c/s | $0.435 | 100.0%7 days | MiMo-V2.5-Pro |
Fal56 models · 73.7% success | 56Vision · Image · Audio · Video | — | — | — | 73.7%7 days | — |
Replicate39 models · 0.0% success | 39Vision · Image · Audio · Video | — | — | — | 0.0%7 days | — |
Bedrock24 models · $0.300–$0.330 | 24Vision · Audio | — | — | $0.300–$0.330 | — | Nova 2 Sonic, Nova 2 Sonic, Nova 2 Sonic |
Groq11 models | 11Audio | — | — | — | — | — |
Hyperbolic9 models | 9 | — | — | — | — | — |
Lambda7 models | 7 | — | — | — | — | — |
Deepgram6 models | 6Audio | — | — | — | — | — |
Elevenlabs5 models | 5Audio | — | — | — | — | — |
Cartesia4 models | 4Audio | — | — | — | — | — |
Luma Labs4 models | 4 | — | — | — | — | — |
Runway4 models | 4 | — | — | — | — | — |
Assemblyai3 models | 3 | — | — | — | — | — |
Cerebras3 models | 3 | — | — | — | — | — |
Vertex AI3 models | 3 | — | — | — | — | — |
Inworld2 models | 2Audio | — | — | — | — | — |
Poolsidecache pricing2 models · $0.100 | 2 | — | — | $0.100 | — | Laguna S 2.1, Laguna XS 2.1 |
Unisound2 models | 2Vision · Audio | — | — | — | — | U2 |
Cohere1 models | 1 | — | — | — | — | — |
GitHub Copilotcache pricing1 models · $0.200 | 1Vision | — | — | $0.200 | — | MAI-Code-1.1-Flash, MAI-Code-1.1-Flash |
Reve AI1 models · 0.0% success | 1Vision · Image | — | — | — | 0.0%7 days | — |
Rime1 models | 1Audio | — | — | — | — | — |
Sakana AIcache pricing1 models · $0.950 | 1Vision | — | — | $0.950 | — | Sakana Namazu, Sakana Namazu |
Thinking Machines Labcache pricing1 models · $0.300 | 1Vision | — | — | $0.300 | — | Inkling-Small, Inkling-Small, Inkling-Small |
Upstagecache pricing1 models · $0.300 | 1 | — | — | $0.300 | — | Solar Pro 4 |