AI/ML API
AggregatorAI/ML API routes one API key to many upstream providers, so you can switch models without new accounts.
Models257
- Cheapest for
- 10 models
- Serves
- 3 model types
Visits in September 2026292K+4.8%Unique visitors 131K
- Apr
- May
- Jun
- Jul
- Aug
- Sep
Models by type
Models on AI/ML API
| Model | Input | Output | vs official | Context |
|---|---|---|---|---|
| GPT-5.1OpenAI | $1.25/1M | $10/1M from $8 at APIMart | ±0% | — |
| GPT-5.1 CodexOpenAI | $1.63/1M | $13/1M from $8 at APIMart | +63% | — |
| GPT-5.1 Codex MaxOpenAI | $2.65/1M | $21.16/1M from $8 at APIMart | +165% | — |
| GPT-5.1 Codex miniOpenAI | $0.325/1M | $2.60/1M from $1.60 at APIMart | +63% | — |
| GPT-5.2 CodexOpenAI | $3.70/1M | $29.62/1M from $11.20 at APIMart | +165% | — |
| GPT-5.4 Image 2OpenAI | $8.46/1M | $15.87/1M from $15 at OpenRouter | +6% | — |
| GPT-5.5 ProOpenAI | $31.74/1M | $190.44/1M from $144 at CometAPI | +6% | — |
| GPT-5.6 TerraOpenAI | $2.12/1M | $12.70/1M from $9.60 at APIMart | +6% | — |
| Granite 4.0 H MicroIBM | $0.018/1M | $0.118/1M from $0.112 at Cloudflare Workers AI | +6% | — |
| Granite 4.2 8BIBM | $0.106/1M | $0.265/1M from $0.25 at Deep Infra | +6% | — |
| Grok 4 Fast Non ReasoningxAI | $1.25/1M | $2.50/1M from $0.50 at Helicone | +400% | — |
| Grok 4 Fast ReasoningxAI | $1.25/1M | $2.50/1M from $0.50 at Helicone | +400% | — |
| Grok 4.1 FastxAI | $1.25/1M | $2.50/1M from $0.475 at Jiekou.AI | +426% | — |
| Grok 4.20 (Non-Reasoning)xAI | $1.25/1M | $2.50/1M from $2 at APIMart | ±0% | — |
| Grok 4.3xAI | $1.25/1M | $2.50/1M from $2 at APIMart | ±0% | — |
| Hermes 3 70B InstructNous Research | $0.741/1M | $0.741/1M from $0.70 at Hugging Face | +6% | — |
| Hermes 4 405BNous Research | $1.06/1M | $3.17/1M from $3 at OpenRouter | +6% | — |
 Hy-MT2-1.8BTencent | $0.047/1M | $0.187/1M from $0.177 at OpenRouter | +6% | — |
| Hy-MT2-30B-A3BTencent | $0.078/1M | $0.312/1M from $0.295 at OpenRouter | +6% | — |
| Hy-MT2-7BTencent | $0.078/1M | $0.312/1M from $0.295 at OpenRouter | +6% | — |
| Hy3Tencent | $0.212/1M | $0.846/1M from $0.33 at OpenRouter | +156% | — |
| Hy4 previewTencent | $0.882/1M | $2.65/1M from $2.25 at OpenRouter | +18% | — |
 Inkling (256K)Thinking Machines | $1.06/1M | $4.28/1M from $1.50 at Venice AI | +186% | — |
| Inkling SmallThinking Machines | $0.614/1M | $1.52/1M from $1.20 at Deep Infra | +27% | — |
| Kimi K2 ThinkingMoonshot AI | $0.635/1M | $2.65/1M from $1.68 at APIMart | +57% | — |
| Kimi K3.1 Pro HighspeedMoonshot AI | $2/1M | $10/1M from $6.13 at Kenari | +6% | — |
 Laguna XS 2.1Poolside | $0.063/1M | $0.127/1M from $0.12 at OpenRouter | +6% | — |
 Ling 3.0 Flash FinInclusionai | $0.063/1M | $0.19/1M from $0.18 at Hugging Face | +6% | — |
| Ling 3.0 Flash VLInclusionai | $0.063/1M | $0.19/1M from $0.18 at Deep Infra | +6% | — |
| Ling-2.6-flashInclusionaiCheapest | $0.013/1M | $0.039/1M | — | — |
| SLlama 3 8B LunarisSao10K | $0.053/1M | $0.053/1M from $0.05 at OpenRouter | +6% | — |
| SLlama 3.1 Euryale 70B v2.2Sao10K | $1.53/1M | $1.53/1M from $0.85 at OpenRouter | +81% | — |
| SLlama 3.3 70B EuryaleSao10KOnly here | $0.688/1M | $0.793/1M | — | — |
 Llama Guard 2 8BMetaCheapest | $0.26/1M | $0.26/1M | — | — |
| AMagnum v4 72BAnthracite Org | $3.17/1M | $5.29/1M from $5 at OpenRouter | +6% | — |
 MiMo-V2.6-Pro-UltraSpeedXiaomi | $4.60/1M | $9.20/1M from $6.96 at CometAPI | +32% | — |
 MiniMax M2MiniMax | $0.30/1M | $1.20/1M from $1 at DevPass (LLM Gateway) | +20% | — |
| MiniMax M2.5 highspeedMiniMax | $0.60/1M | $2.40/1M from $1.15 at AIHubMix | +108% | — |
| MiniMax Text 01 (MiniMax)MiniMaxCheapest | $0.20/1M | $1.10/1M | ±0% | — |
| MiniMax-M2 HerMiniMaxCheapest | $0.30/1M | $1.20/1M | ±0% | — |
| MiniMax-M2.7MiniMax | $0.30/1M | $1.20/1M from $0.60 at EmpirioLabs AI | +100% | — |
 Ministral 14BMistral | $0.37/1M | $0.37/1M from $0.20 at DevPass (LLM Gateway) | +85% | — |
| Mistral 7B Instruct V0.2Mistral | $0.26/1M | $0.26/1M from $0.221 at Cortecs | +18% | — |
| Mistral Medium 3Mistral | $0.423/1M | $2.12/1M from $2 at OpenRouter | +6% | — |
| Mistral Medium 3.1Mistral | $0.423/1M | $2.12/1M from $2 at OpenRouter | +6% | — |
| Mistral Small 3Mistral | $0.053/1M | $0.085/1M from $0.08 at Deep Infra | +6% | — |
| Mistral Small 3.1 24BMistral | $0.371/1M | $0.587/1M from $0.555 at OpenRouter | +6% | — |
| Mistral Small 3.2 24BMistral | $0.079/1M | $0.212/1M from $0.20 at Deep Infra | +6% | — |
| Mixtral 8x22B InstructMistral | $2.12/1M | $6.35/1M from $6 at OpenRouter | +6% | — |
 Morph V3 FastMorph | $0.846/1M | $1.27/1M from $1.20 at OpenRouter | +6% | — |
AI/ML API at a glance
257 models in total: 251 text, 3 moderation, 3 image. The cheapest is Ling-2.6-flash at $0.039 /1M. Grok 4 Fast Non Reasoning has the largest context window, 2M tokens. The most searched is Gemini 4 Argon, with about 2M Google searches a month. The newest is Kimi K3.1 Pro Highspeed, released Oct 23, 2026.
Cheapest
- Ling-2.6-flash$0.039/1M
- SLlama 3 8B Lunaris$0.053/1M
- Mistral Small 3$0.085/1M
Gemma 3 4B IT$0.106/1M- Reka Edge$0.106/1M
Largest context
Most searched
- Gemini 4 Argon2M
- Kimi K3658K
- GPT-6 Astra580K
- Muse Wonder569K
- Claude Opus 5.5405K
Newest
- Kimi K3.1 Pro HighspeedOct 23, 2026
- Mercury 3Oct 19, 2026
- MiniMax-M3.1-FlashOct 17, 2026
Beam 1.0 501B A23BOct 16, 2026- Muse Spark OpenOct 15, 2026