LLM aggregators, inference hosts and cloud platforms
Third-party ways to call LLMs: aggregators (one API key, routed to many upstreams, e.g. OpenRouter), inference hosts serving open-weight models (Fireworks, DeepInfra, Groq, Together AI), and cloud AI platforms (Amazon Bedrock, Google Vertex AI, Scaleway, IONOS). Search the same model across providers to compare against the first-party price.
| Provider | Type | HQ | Regions | EU data residency | Models |
|---|---|---|---|---|---|
| Groq | Inference host | US | unknown | unknown | 3 |
| Together AI | Inference host | US | unknown | unknown | 11 |
| OpenRouter | Aggregator | US | unknown | unknown | 40 |
| Fireworks | Inference host | US | unknown | unknown | 8 |
| DeepInfra | Inference host | US | unknown | unknown | 10 |
| Amazon Bedrock | Cloud | US | Global, US, EU, UK | partial | 7 |
| Google Vertex AI | Cloud | US | Global, Regional | unknown | 9 |
| Scaleway | Cloud | France | EU | yes | 9 |
| IONOS AI Model Hub | Cloud | Germany | unknown | unknown | 6 |
| CamoCopy | Inference host | Luxembourg | EU | yes | 3 |
| Requesty | Aggregator | unknown | Global, EU | partial | 20 |
| GreenPT | Inference host | Netherlands | EU, US | yes | 5 |
| Infomaniak AI Services | Cloud | Switzerland | Europe | unknown | 3 |
| SambaNova | Inference host | US | unknown | unknown | 6 |
| Nebius Token Factory | Inference host | Netherlands | EU, US, UK | partial | 8 |
| Novita | Inference host | US | unknown | unknown | 10 |
HQ country is from public company information; regions and EU residency are only filled from the cited source page, otherwise 'unknown'.
Blend input:output
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| OpenRouter Aggregator | Qwen: Qwen3.7 Flash | $0.03 | $0.13 | $0.006 | $0.055 | 1M | unknown |
| Fireworks Inference host | NVIDIA Nemotron 3.5 Lightning 30B A3B | $0.05 | $0.20 | $0.01 | $0.0875 | — | unknown |
| Novita Inference host | OpenAI GPT OSS 120B | $0.05 | $0.25 | — | $0.10 | — | unknown |
| DeepInfra Inference host | Mistral-Small-3.2-24B | $0.075 | $0.20 | — | $0.106 | 125K | unknown |
| DeepInfra Inference host | DeepSeek-V4-Flash | $0.09 | $0.18 | $0.018 | $0.113 | — | unknown |
| Groq Inference host | openai/gpt-oss-20b | $0.075 | $0.30 | — | $0.131 | 131K | unknown |
| DeepInfra Inference host | Llama-3.3-70B-Instruct-Turbo | $0.10 | $0.32 | — | $0.155 | 128K | unknown |
| Google Vertex AI Cloud | gpt-oss-120b | $0.09 | $0.36 | — | $0.158 | — | unknown |
| IONOS AI Model Hub Cloud | Mistral Small 24B Instruct | $0.11 | $0.33 | — | $0.165 | — | unknown |
| OpenRouter Aggregator | DeepSeek: DeepSeek V4 Flash 0731 | $0.016 | $0.64 | $0.016 | $0.172 | 1.048576M | unknown |
| GreenPT Inference host | glm-5.3-flashvariable pricing | €0.11 | €0.44 | €0.022 | €0.193 | 1M | yes |
| OpenRouter Aggregator | DeepSeek: DeepSeek V4.1 Flash | $0.0238 | $0.72 | $0.0054 | $0.198 | 1.048576M | unknown |
| Scaleway Cloud | mistral-small-3.2-24b-instruct-2506 | €0.15 | €0.35 | — | €0.20 | — | yes |
| OpenRouter Aggregator | OpenAI: GPT-6 Luna | $0.10 | $0.50 | $0.01 | $0.20 | 1.05M | unknown |
| OpenRouter Aggregator | Anthropic: Claude Haiku 5.5 | $0.10 | $0.50 | $0.01 | $0.20 | 1M | unknown |
| Amazon Bedrock Cloud | Ministral 14B 3.0variable pricing | $0.20 | $0.20 | — | $0.20 | — | yes |
| Requesty Aggregator | openai/gpt-6-luna | $0.10 | $0.50 | $0.01 | $0.20 | 1.05M | unknown |
| Requesty Aggregator | anthropic/claude-haiku-5-5 | $0.10 | $0.50 | $0.01 | $0.20 | 1M | unknown |
| Novita Inference host | Llama 3.3 70B Instruct | $0.135 | $0.40 | — | $0.201 | — | unknown |
| Amazon Bedrock Cloud | Gemma 4 31Bvariable pricing | $0.14 | $0.40 | — | $0.205 | — | yes |
| Novita Inference host | Gemma 4 31B | $0.14 | $0.40 | — | $0.205 | — | unknown |
| OpenRouter Aggregator | Qwen: Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.23 | 1M | unknown |
| Together AI Inference host | GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | $0.237 | — | unknown |
| OpenRouter Aggregator | Z.ai: GLM 5.3 Flash | $0.15 | $0.50 | $0.03 | $0.237 | 1.048576M | unknown |
| Fireworks Inference host | GLM 5.3 Flash | $0.15 | $0.50 | $0.03 | $0.237 | — | unknown |
| Nebius Token Factory Inference host | GLM-5.3-Flash | $0.15 | $0.50 | — | $0.237 | — | unknown |
| Novita Inference host | GLM 5.3 Flash | $0.15 | $0.50 | $0.03 | $0.237 | — | unknown |
| DeepInfra Inference host | gemma-4-31B-it | $0.20 | $0.40 | — | $0.25 | 256K | unknown |
| Groq Inference host | openai/gpt-oss-120b | $0.15 | $0.60 | — | $0.262 | 131K | unknown |
| Together AI Inference host | gpt-oss-120B | $0.15 | $0.60 | — | $0.262 | — | unknown |
| Fireworks Inference host | OpenAI GPT OSS 120B | $0.15 | $0.60 | $0.015 | $0.262 | — | unknown |
| Scaleway Cloud | gpt-oss-120b | €0.15 | €0.60 | — | €0.262 | — | yes |
| Nebius Token Factory Inference host | gpt-oss-120b | $0.15 | $0.60 | — | $0.262 | — | unknown |
| Amazon Bedrock Cloud | NVIDIA Nemotron 3 Super 120B A12Bvariable pricing | $0.15 | $0.65 | — | $0.275 | — | yes |
| IONOS AI Model Hub Cloud | gpt-oss-120b | $0.17 | $0.71 | — | $0.305 | — | unknown |
| Scaleway Cloud | gemma-4-26b-a4b-it | €0.25 | €0.50 | — | €0.313 | — | yes |
| SambaNova Inference host | gpt-oss-120b | $0.22 | $0.59 | — | $0.313 | — | unknown |
| Infomaniak AI Services Cloud | mistralai/Ministral-3-14B-Instruct-2512 | CHF 0.30 | CHF 0.40 | — | CHF 0.325 | — | unknown |
| IONOS AI Model Hub Cloud | Qwen3-Coder-Next (80B) | $0.17 | $0.89 | — | $0.35 | — | unknown |
| CamoCopy Inference host | pixtral-12b-2409 | €0.35 | €0.35 | — | €0.35 | 128K | yes |
| OpenRouter Aggregator | MiniMax: MiniMax M2.5 | $0.27 | $0.95 | $0.03 | $0.44 | 205K | unknown |
| GreenPT Inference host | deepseek-v4.1-flashvariable pricing | €0.22 | €1.10 | €0.011 | €0.44 | 1M | yes |
| OpenRouter Aggregator | OpenAI: GPT-5.6 Luna | $0.20 | $1.20 | $0.02 | $0.45 | 1.05M | unknown |
| Together AI Inference host | MiniMax M3 | $0.30 | $1.20 | $0.06 | $0.525 | — | unknown |
| Together AI Inference host | DeepSeek V4.1 Flash | $0.30 | $1.20 | $0.006 | $0.525 | — | unknown |
| OpenRouter Aggregator | MiniMax: MiniMax M3 | $0.30 | $1.20 | $0.06 | $0.525 | 1.048576M | unknown |
| OpenRouter Aggregator | MiniMax: MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.525 | 205K | unknown |
| OpenRouter Aggregator | MiniMax: MiniMax M2-her | $0.30 | $1.20 | $0.03 | $0.525 | 66K | unknown |
| Fireworks Inference host | DeepSeek V4.1 Flash | $0.30 | $1.20 | $0.006 | $0.525 | — | unknown |
| Fireworks Inference host | MiniMax M3 | $0.30 | $1.20 | $0.06 | $0.525 | — | unknown |
| Requesty Aggregator | deepseek/deepseek-v4.1-flash | $0.30 | $1.20 | $0.006 | $0.525 | 1M | unknown |
| Nebius Token Factory Inference host | DeepSeek V4.1 Flash | $0.30 | $1.20 | — | $0.525 | — | unknown |
| Nebius Token Factory Inference host | MiniMax-M3 | $0.30 | $1.20 | — | $0.525 | — | unknown |
| Novita Inference host | DeepSeek V4.1 Flash | $0.30 | $1.20 | $0.006 | $0.525 | — | unknown |
| Together AI Inference host | Gemma 4 31B | $0.39 | $0.97 | — | $0.535 | — | unknown |
| Google Vertex AI Cloud | Llama 4 Maverick | $0.35 | $1.15 | — | $0.55 | — | unknown |
| SambaNova Inference host | gemma-4-31B-it | $0.38 | $1.15 | — | $0.573 | — | unknown |
| Novita Inference host | DeepSeek V4 Flash 0731 | $0.44 | $1.32 | $0.028 | $0.66 | — | unknown |
| IONOS AI Model Hub Cloud | Llama 3.3 70B Instruct | $0.71 | $0.71 | — | $0.71 | — | unknown |
| OpenRouter Aggregator | Qwen: Qwen3.8 27B | $0.24 | $2.20 | $0.05 | $0.73 | 1M | unknown |
| Amazon Bedrock Cloud | Mistral Large 3 | $0.50 | $1.50 | — | $0.75 | — | unknown |
| SambaNova Inference host | Meta-Llama-3.3-70B-Instruct | $0.60 | $1.20 | — | $0.75 | — | unknown |
| Amazon Bedrock Cloud | Devstral 2 123Bvariable pricing | $0.40 | $2.00 | — | $0.80 | — | yes |
| Google Vertex AI Cloud | Mistral Medium 3 | $0.40 | $2.00 | — | $0.80 | — | unknown |
| CamoCopy Inference host | llama-3.3-70b | €0.80 | €0.80 | — | €0.80 | 128K | yes |
| OpenRouter Aggregator | Google: Gemini 3.5 Flash Lite | $0.30 | $2.50 | $0.03 | $0.85 | 1.048576M | unknown |
| DeepInfra Inference host | gemini-2.5-flash | $0.30 | $2.50 | — | $0.85 | — | unknown |
| Google Vertex AI Cloud | Gemini 3.5 Flash-Litevariable pricing | $0.30 | $2.50 | $0.03 | $0.85 | — | unknown |
| Requesty Aggregator | google/gemini-3.5-flash-lite | $0.30 | $2.50 | $0.03 | $0.85 | 1.048576M | unknown |
| GreenPT Inference host | minimax-m3 | €0.44 | €2.20 | €0.11 | €0.88 | 1M | yes |
| Scaleway Cloud | deepseek-v4.1-flash | €0.60 | €1.80 | €0.12 | €0.90 | — | yes |
| Scaleway Cloud | llama-3.3-70b-instruct | €0.90 | €0.90 | — | €0.90 | — | yes |
| OpenRouter Aggregator | DeepSeek: DeepSeek V4 Pro 0813 | $0.66 | $1.98 | $0.022 | $0.99 | 1.048576M | unknown |
| IONOS AI Model Hub Cloud | Qwen3.8-27B | $0.45 | $2.70 | — | $1.01 | — | unknown |
| OpenRouter Aggregator | Mistral: Mistral Large 4 | $0.68 | $2.09 | $0.07 | $1.03 | 1.048576M | unknown |
| Requesty Aggregator | mistral/mistral-large-4 | $0.68 | $2.09 | $0.07 | $1.03 | 524K | yes |
| Together AI Inference host | Llama 3.3 70B | $1.04 | $1.04 | — | $1.04 | — | unknown |
| SambaNova Inference host | MiniMax-M3 | $0.60 | $2.40 | $0.06 | $1.05 | — | unknown |
| Novita Inference host | Qwen3.8 27B | $0.42 | $3.00 | $0.085 | $1.06 | — | unknown |
| Nebius Token Factory Inference host | Qwen3.8-27B | $0.45 | $3.00 | — | $1.09 | — | unknown |
| Infomaniak AI Services Cloud | Qwen/Qwen3.5-122B-A10B-FP8 | CHF 0.40 | CHF 3.20 | — | CHF 1.10 | — | unknown |
| CamoCopy Inference host | deepseek-v3.2 | €0.90 | €2.10 | — | €1.20 | 128K | yes |
| OpenRouter Aggregator | Z.ai: GLM 5.3 | $0.03 | $4.80 | $0.029 | $1.22 | 1.048576M | unknown |
| Scaleway Cloud | qwen3.8-27b | €0.60 | €3.30 | €0.12 | €1.27 | — | yes |
| OpenRouter Aggregator | MoonshotAI: Kimi K2.7 Code | $0.671 | $3.35 | $0.18 | $1.34 | 262K | unknown |
| Scaleway Cloud | qwen3.5-397b-a17b | €0.60 | €3.60 | — | €1.35 | — | yes |
| OpenRouter Aggregator | Google: Gemini 3.8 Flash | $0.75 | $3.75 | $0.075 | $1.50 | 1.048576M | unknown |
| OpenRouter Aggregator | Google: Gemini 3.7 Flash | $0.75 | $3.75 | $0.075 | $1.50 | 1.048576M | unknown |
| OpenRouter Aggregator | Google: Gemini 3.6 Flash | $0.75 | $3.75 | $0.075 | $1.50 | 1.048576M | unknown |
| Requesty Aggregator | vertex/gemini-3.8-flash | $0.75 | $3.75 | $0.075 | $1.50 | 1.048576M | unknown |
| IONOS AI Model Hub Cloud | Qwen3.5-397B-A17B | $0.67 | $4.00 | — | $1.50 | — | unknown |
| Groq Inference host | qwen/qwen3.8-27b | $0.80 | $4.00 | — | $1.60 | 131K | unknown |
| DeepInfra Inference host | DeepSeek-V4-Pro | $1.30 | $2.60 | $0.10 | $1.63 | 1.024M | unknown |
| OpenRouter Aggregator | Z.ai: GLM 5.2 | $0.02 | $7.00 | $0.019 | $1.76 | 1.048576M | unknown |
| GreenPT Inference host | glm-5.3variable pricing | €1.10 | €4.40 | €0.275 | €1.93 | 1M | yes |
| Together AI Inference host | DeepSeek V4 Pro 0813 | $1.32 | $3.96 | $0.13 | $1.98 | — | unknown |
| Nebius Token Factory Inference host | DeepSeek-V4-Pro-0813 | $1.32 | $3.96 | — | $1.98 | — | unknown |
| Novita Inference host | DeepSeek V4 Pro 0813 | $1.32 | $3.96 | $0.044 | $1.98 | — | unknown |
| Together AI Inference host | GLM-5.3 | $1.40 | $4.40 | $0.26 | $2.15 | — | unknown |
| Fireworks Inference host | GLM 5.3 | $1.40 | $4.40 | $0.26 | $2.15 | — | unknown |
| Requesty Aggregator | zai/glm-5.3 | $1.40 | $4.40 | $0.26 | $2.15 | 1M | unknown |
| Nebius Token Factory Inference host | GLM-5.3 | $1.40 | $4.40 | — | $2.15 | — | unknown |
| Novita Inference host | GLM 5.3 | $1.40 | $4.40 | $0.26 | $2.15 | — | unknown |
| Together AI Inference host | Qwen3.7-Max | $1.50 | $4.50 | $0.30 | $2.25 | — | unknown |
| DeepInfra Inference host | Qwen3.8-Max | $1.65 | $4.95 | $0.206 | $2.48 | 250K | unknown |
| Amazon Bedrock Cloud | GLM 5.3 | $1.68 | $5.28 | $0.312 | $2.58 | — | unknown |
| Scaleway Cloud | glm-5.3 | €1.80 | €5.50 | — | €2.73 | — | yes |
| Together AI Inference host | Qwen3.8-2.4T-A95B | $2.00 | $6.00 | $0.25 | $3.00 | — | unknown |
| OpenRouter Aggregator | SpaceXAI: Grok 4.7 | $2.00 | $6.00 | $0.50 | $3.00 | 500K | unknown |
| OpenRouter Aggregator | SpaceXAI: Grok 4.6 | $2.00 | $6.00 | $0.50 | $3.00 | 500K | unknown |
| OpenRouter Aggregator | SpaceXAI: Grok 4.5 | $2.00 | $6.00 | $0.30 | $3.00 | 500K | unknown |
| OpenRouter Aggregator | Qwen: Qwen3.8 Max (0902) | $2.00 | $6.00 | $0.25 | $3.00 | 1M | unknown |
| OpenRouter Aggregator | Qwen: Qwen3.8 2.4T A95B | $2.00 | $6.00 | $0.25 | $3.00 | 1.048576M | unknown |
| Fireworks Inference host | Qwen 3.8 Max | $2.00 | $6.00 | $0.25 | $3.00 | — | unknown |
| Google Vertex AI Cloud | Gemini 3.8 FlashPromo until 2026-12-31 | $1.50 | $7.50 | $0.15 | $3.00 | — | unknown |
| Google Vertex AI Cloud | Grok 4.7 | $2.00 | $6.00 | $0.50 | $3.00 | — | unknown |
| Scaleway Cloud | mistral-medium-3.5-128b | €1.50 | €7.50 | — | €3.00 | — | yes |
| Requesty Aggregator | xai/grok-4.7 | $2.00 | $6.00 | $0.50 | $3.00 | 500K | unknown |
| SambaNova Inference host | DeepSeek-V3.1 | $3.00 | $4.50 | — | $3.38 | — | unknown |
| SambaNova Inference host | DeepSeek-V3.2 | $3.00 | $4.50 | — | $3.38 | — | unknown |
| OpenRouter Aggregator | OpenAI: GPT-6.1 Sol | $2.00 | $10.00 | $0.10 | $4.00 | 1.05M | unknown |
| OpenRouter Aggregator | OpenAI: GPT-6 Sol | $2.00 | $10.00 | $0.20 | $4.00 | 1.05M | unknown |
| OpenRouter Aggregator | Anthropic: Claude Sonnet 5.5 | $2.00 | $10.00 | $0.10 | $4.00 | 1M | unknown |
| OpenRouter Aggregator | Anthropic: Claude Sonnet 5 | $2.00 | $10.00 | $0.20 | $4.00 | 1M | unknown |
| OpenRouter Aggregator | Google: Gemini 4 Argon | $2.00 | $10.00 | $0.10 | $4.00 | 1.048576M | unknown |
| Google Vertex AI Cloud | Claude Sonnet 5.5variable pricing | $2.00 | $10.00 | $0.10 | $4.00 | — | unknown |
| Requesty Aggregator | openai/gpt-6.1-sol | $2.00 | $10.00 | $0.10 | $4.00 | 1.05M | unknown |
| Requesty Aggregator | openai/gpt-6-sol | $2.00 | $10.00 | $0.20 | $4.00 | 1.05M | unknown |
| Requesty Aggregator | anthropic/claude-sonnet-5-5 | $2.00 | $10.00 | $0.20 | $4.00 | 1M | unknown |
| Requesty Aggregator | vertex/gemini-4-argon | $2.00 | $10.00 | $0.10 | $4.00 | 1.048576M | unknown |
| OpenRouter Aggregator | MoonshotAI: Kimi K3 | $0.45 | $15.00 | $0.28 | $4.09 | 1.048576M | unknown |
| Requesty Aggregator | bedrock/claude-sonnet-5-5@eu-central-1 | $2.20 | $11.00 | $0.22 | $4.40 | 1M | yes |
| Requesty Aggregator | vertex/gemini-4-argon@eu | $2.20 | $11.00 | $0.11 | $4.40 | 1.048576M | yes |
| OpenRouter Aggregator | OpenAI: GPT-5.6 Terra | $2.00 | $12.00 | $0.20 | $4.50 | 1.05M | unknown |
| Requesty Aggregator | openai/gpt-5.6-terra | $2.00 | $12.00 | $0.20 | $4.50 | 1.05M | unknown |
| Requesty Aggregator | azure/gpt-6.1-sol@germanywestcentral | $2.40 | $12.00 | $0.12 | $4.80 | 1.05M | yes |
| DeepInfra Inference host | Kimi-K3 | $2.85 | $14.25 | $0.285 | $5.70 | — | unknown |
| Together AI Inference host | Kimi K3 | $3.00 | $15.00 | $0.30 | $6.00 | — | unknown |
| Fireworks Inference host | Kimi K3 | $3.00 | $15.00 | $0.30 | $6.00 | — | unknown |
| DeepInfra Inference host | claude-sonnet-5 | $3.00 | $15.00 | — | $6.00 | — | unknown |
| Amazon Bedrock Cloud | Kimi K3 | $3.00 | $15.00 | $0.30 | $6.00 | — | unknown |
| Requesty Aggregator | moonshot/kimi-k3 | $3.00 | $15.00 | $0.30 | $6.00 | 1.048576M | unknown |
| Nebius Token Factory Inference host | Kimi-K3 | $3.00 | $15.00 | — | $6.00 | — | unknown |
| Novita Inference host | Kimi K3 | $3.00 | $15.00 | $0.30 | $6.00 | — | unknown |
| GreenPT Inference host | kimi-k3variable pricing | €3.30 | €16.50 | €0.825 | €6.60 | 1M | yes |
| OpenRouter Aggregator | OpenAI: GPT-5.6 Sol | $4.00 | $20.00 | $0.40 | $8.00 | 1.05M | unknown |
| OpenRouter Aggregator | Anthropic: Claude Opus 5.5 | $4.00 | $20.00 | $0.20 | $8.00 | 1M | unknown |
| Google Vertex AI Cloud | Gemini 4 ArgonPromo until 2026-11-30variable pricing | $4.00 | $20.00 | $0.20 | $8.00 | — | unknown |
| Google Vertex AI Cloud | Claude Opus 5.5variable pricing | $4.00 | $20.00 | $0.20 | $8.00 | — | unknown |
| Requesty Aggregator | anthropic/claude-opus-5-5 | $4.00 | $20.00 | $0.20 | $8.00 | 1M | unknown |
| OpenRouter Aggregator | Anthropic: Claude Opus 5 | $5.00 | $25.00 | $0.50 | $10.00 | 1M | unknown |
| DeepInfra Inference host | claude-opus-5 | $5.00 | $25.00 | — | $10.00 | 976K | unknown |
| Requesty Aggregator | anthropic/claude-opus-5 | $5.00 | $25.00 | $0.50 | $10.00 | 1M | unknown |
| OpenRouter Aggregator | OpenAI: GPT-6 Astra | $10.00 | $50.00 | $1.00 | $20.00 | 1.05M | unknown |
| OpenRouter Aggregator | Anthropic: Claude Fable 5.1 | $10.00 | $50.00 | $0.25 | $20.00 | 1M | unknown |
| OpenRouter Aggregator | Anthropic: Claude Fable 5 | $10.00 | $50.00 | $1.00 | $20.00 | 1M | unknown |
| Requesty Aggregator | openai/gpt-6-astra | $10.00 | $50.00 | $1.00 | $20.00 | 1.05M | unknown |
| Infomaniak AI Services Cloud | google/gemma-4-31B-it | — | CHF 0.40 | — | — | — | unknown |
Per 1M tokens, standard (non-promo) list prices; short-context / peak tier where tiered. USD unless shown with € or CHF: those are as published and not converted. Click a header to sort. 158 models.
* Blended assumes 3 input tokens for every output token: (3×input + output) / 4. Your real mix will differ, so use the cost calculator with your own token counts for a real estimate.