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 QPS50 models · $0.250–$2.50 · 2.80s median TTFT · 100.0% success | 50Vision · Image · Video | 2.80sP95 8.58s | 366 c/sP5 167 c/s | $0.250–$2.50 | 100.0%7 days | Gemini 3.8 Flash, Gemini 3.8 Flash, Gemini 3.8 Flash |
Sambanova327.7 QPS6 models · $0.400 | 6 | Catalog 1.08s | Catalog 328 c/s | $0.400 | — | Qwen3 32B |
Mistral AIcache pricing · 45.89 QPS19 models · $0.150–$1.50 · 1.56s median TTFT · 100.0% success | 19Vision | 1.56sP95 2.98s | 311 c/sP5 68 c/s | $0.150–$1.50 | 100.0%7 days | Mistral Large 4, Mistral Large 4, Mistral Medium 3.5 |
Anthropiccache pricing · 42–100 QPS25 models · $0.100–$10.0 · 3.10s median TTFT · 100.0% success | 25Vision | 3.10sP95 14.61s | 227 c/sP5 23 c/s | $0.100–$10.0 | 100.0%7 days | Claude Haiku 5.5, Claude Haiku 5.5, Claude Sonnet 5.5 |
Togethercache pricing26 models · $0.300–$3.00 · 2.42s median TTFT · 100.0% success | 26Vision | 2.42sP95 3.03s | 202 c/sP5 145 c/s | $0.300–$3.00 | 100.0%7 days | Qwen3.8 Max, DeepSeek-V4-Pro-0813, Kimi K3 |
MiniMaxcache pricing · 70–100 QPS10 models · $0.300 · 1.15s median TTFT · 100.0% success | 10Vision · Audio · Video | 1.15sP95 2.72s | 152 c/sP5 78 c/s | $0.300 | 100.0%7 days | MiniMax M3, MiniMax M3, MiniMax M3 |
StepFuncache pricing · 150 QPS1 models · $0.100 | 1 | Catalog 300ms | Catalog 150 c/s | $0.100 | — | Step-3.5-Flash |
Fireworkscache pricing · 122.4 QPS42 models · $0.220–$3.00 | 42Vision | Catalog 660ms | Catalog 122 c/s | $0.220–$3.00 | — | Ember-1, Ember-1, DeepSeek-V4.1-Flash |
DeepSeekcache pricing · 100 QPS12 models · $0.280–$1.32 · 100.0% success | 12Vision | Catalog 300ms | Catalog 100 c/s | $0.280–$1.32 | 100.0%7 days | DeepSeek-V4.1-Flash, DeepSeek-V4.1-Flash, DeepSeek-V4-Pro-0813 |
Azure90–99 QPS12 models · $0.500–$10.0 | 12Vision | Catalog 590ms | Catalog 95 c/s | $0.500–$10.0 | — | Parse, GPT-4 Turbo, GPT-4o |
Novitacache pricing · 32.43–88.84 QPS58 models · $0.100–$3.00 · 4.18s median TTFT · 99.4% success | 58Vision | 4.18sP95 13.75s | 79 c/sP5 8 c/s | $0.100–$3.00 | 99.4%7 days | DeepSeek-V4.1-Flash, DeepSeek-V4.1-Flash, Qwen3.8 Flash |
OpenAIcache pricing · 50–200 QPS66 models · $0.100–$12.5 · 4.00s median TTFT · 100.0% success | 66Vision · Image · Audio · Video | 4.00sP95 8.85s | 65 c/sP5 27 c/s | $0.100–$12.5 | 100.0%7 days | GPT-Rosalind, GPT-Rosalind, GPT-6.1 Sol |
DeepInfracache pricing · 85–97 QPS122 models · $0.019–$10.0 · 2.44s median TTFT · 98.4% success | 122Vision | 2.44sP95 24.81s | 59 c/sP5 5 c/s | $0.019–$10.0 | 98.4%7 days | DeepSeek-V4.1-Flash, DeepSeek-V4.1-Flash, Step 3.7 Flash |
Xiaomicache pricing6 models · $0.140–$0.435 · 4.66s median TTFT · 98.7% success | 6Vision | 4.66sP95 8.38s | 53 c/sP5 6 c/s | $0.140–$0.435 | 98.7%7 days | MiMo-V2.6-Flash, MiMo-V2.6-Flash, MiMo-V2.6-Flash |
ZAIcache pricing · 30 QPS9 models · $0.150–$1.40 · 9.25s median TTFT · 100.0% success | 9Vision | 9.25sP95 12.63s | 52 c/sP5 15 c/s | $0.150–$1.40 | 100.0%7 days | GLM-5.3-Flash, GLM-5.3-Flash, GLM-5.3-Flash |
xAIcache pricing · 76.41–100 QPS25 models · $0.200–$3.00 · 2.28s median TTFT · 100.0% success | 25Vision · Image · Audio · Video | 2.28sP95 2.87s | 38 c/sP5 15 c/s | $0.200–$3.00 | 100.0%7 days | Grok 4.7, Grok 4.7, Grok 4.6 |
Meta Model APIcache pricing3 models · $0.100–$1.25 · 1.52s median TTFT · 98.6% success | 3Vision | 1.52sP95 4.61s | 9 c/sP5 3 c/s | $0.100–$1.25 | 98.6%7 days | Muse Spark 1.3, Muse Spark 1.3, Muse Spark 1.3 |
Fal59 models | 59Vision · Image · Audio · Video | — | — | — | — | — |
Replicate39 models | 39Vision · Image · Audio · Video | — | — | — | — | — |
Bedrock24 models · $0.300–$0.330 | 24Vision · Audio | — | — | $0.300–$0.330 | — | Nova 2 Sonic, Nova 2 Sonic, Nova 2 Sonic |
Higgsfield18 models | 18Vision · Video | — | — | — | — | — |
Groq11 models | 11Audio | — | — | — | — | — |
Hyperbolic9 models | 9 | — | — | — | — | — |
FriendliAIcache pricing8 models · $0.140–$1.40 | 8Vision | — | — | $0.140–$1.40 | — | GLM-5.3-Flash, GLM-5.3-Flash, GLM-5.3-Flash |
Lambda7 models | 7 | — | — | — | — | — |
Deepgram6 models | 6Audio | — | — | — | — | — |
Cartesia5 models | 5Audio | — | — | — | — | — |
Elevenlabs5 models | 5Audio | — | — | — | — | — |
Moonshot AIcache pricing5 models · $0.950–$3.00 | 5Vision | — | — | $0.950–$3.00 | — | Kimi K2.8 Preview, Kimi K2.8 Preview, Kimi K2.8 Preview |
Luma Labs4 models | 4 | — | — | — | — | — |
Runway4 models | 4 | — | — | — | — | — |
Assemblyai3 models | 3 | — | — | — | — | — |
Cerebras3 models | 3 | — | — | — | — | — |
Vertex AI3 models | 3 | — | — | — | — | — |
Cohere2 models | 2Vision | — | — | — | — | Parse |
Inworld2 models | 2Audio | — | — | — | — | — |
Poolsidecache pricing2 models · $0.100 | 2 | — | — | $0.100 | — | Laguna S 2.1, Laguna XS 2.1 |
Unisound2 models | 2Vision · Audio | — | — | — | — | U2 |
Upstagecache pricing2 models · $0.100–$0.300 | 2 | — | — | $0.100–$0.300 | — | Solar Mini 4, Solar Pro 4 |
BytePlus1 models | 1Vision · Audio · Video | — | — | — | — | — |
GitHub Copilotcache pricing1 models · $0.200 | 1Vision | — | — | $0.200 | — | MAI-Code-1.1-Flash, MAI-Code-1.1-Flash |
OpenRouter1 models | 1Vision · Video | — | — | — | — | — |
Reve AI1 models | 1Vision · Image | — | — | — | — | — |
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 |