Offerings
Every active offering: a model as served by one host, with its current canonical price. Sort by clicking a column header; filter with the row below. Prices are USD per 1M tokens unless the unit toggle is set to per 1M characters (an approximation using a measured, blended tokens-per-character ratio).
Showing tier-tagged and vendor-direct models. Show all offerings, including the long tail
| Model | Vendor | Host | Variant | Input ↑ | Output | Cache read | Cache write | Batch in | Batch out | Context | Tokenizer | Latency / throughput soon | Last change | Confidence | Source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Codestral (latest) | mistral | mistral | – | 0.000000 | 0.000000 | – | – | – | – | 256000 | mistral | – | – | medium | litellm |
| Meta: Llama 4 Maverick | meta | meta | – | 0.000000 | 0.000000 | – | – | – | – | 1048576 | llama3 | – | – | medium | modelsdev |
| Meta: Llama 3.3 70B Instruct | meta | meta | – | 0.000000 | 0.000000 | – | – | – | – | 128000 | llama3 | – | – | medium | modelsdev |
| Meta: Llama 3.3 70B Instruct | meta | nvidia | – | 0.000000 | 0.000000 | – | – | – | – | 128000 | llama3 | – | – | medium | modelsdev |
| Llama 3.3 Nemotron Super 49B v1.5 | nvidia | nvidia | – | 0.000000 | 0.000000 | – | – | – | – | 131072 | llama3 | – | – | medium | modelsdev |
| Qwen3 Coder 480B A35B Instruct | alibaba | nvidia | – | 0.000000 | 0.000000 | – | – | – | – | 262144 | qwen2 | – | – | medium | modelsdev |
| OpenAI: GPT-5 Nano | openai | openai | unknown | 0.025000 | 0.200000 | 0.002500 | – | – | – | 400000 | o200k | – | – | high | openrouter |
| OpenAI: GPT-5 Nano | openai | openai | – | 0.025000 | 0.200000 | 0.002500 | – | – | – | 400000 | o200k | – | – | high | openrouter |
| Nova Micro (US) | amazon | aws-bedrock | – | 0.035000 | 0.140000 | 0.008750 | – | – | – | 128000 | – | – | – | medium | litellm |
| Nova Micro (US) | amazon | amazon | – | 0.035000 | 0.140000 | – | – | – | – | 128000 | – | – | – | medium | litellm |
| Nova Micro (US) | amazon | aws-bedrock | – | 0.035000 | 0.140000 | 0.008750 | – | – | – | 128000 | – | – | – | medium | litellm |
| Nova Micro (US) | amazon | aws-bedrock | – | 0.037000 | 0.148000 | 0.009250 | – | – | – | 128000 | – | – | – | medium | litellm |
| Nova Micro (US) | amazon | aws-bedrock | – | 0.046000 | 0.184000 | 0.011500 | – | – | – | 128000 | – | – | – | medium | litellm |
| OpenAI: GPT-5 Nano | openai | openrouter | – | 0.050000 | 0.400000 | 0.005000 | – | 0.025000 | 0.200000 | 400000 | o200k | – | – | high | openrouter |
| OpenAI: GPT-6 Luna | openai | openai | unknown | 0.050000 | 0.250000 | 0.005000 | 0.062500 | – | – | 1050000 | o200k | – | – | high | openrouter |
| OpenAI: GPT-5 Nano | openai | azure | unknown | 0.050000 | 0.400000 | 0.010000 | – | – | – | 400000 | o200k | – | – | high | openrouter |
| OpenAI: GPT-5 Nano | openai | openai | unknown | 0.050000 | 0.400000 | 0.005000 | – | – | – | 400000 | o200k | – | – | high | openrouter |
| Google: Gemini 2.5 Flash Lite | unknown | 0.050000 | 0.200000 | 0.005000 | 0.041667 | – | – | 1048576 | gemini | – | – | high | openrouter | ||
| OpenAI: GPT-5 Nano | openai | azure | – | 0.050000 | 0.400000 | 0.005000 | – | 0.025000 | 0.200000 | 400000 | o200k | – | – | medium | litellm |
| OpenAI: GPT-5 Nano | openai | azure | – | 0.050000 | 0.400000 | 0.005000 | – | 0.025000 | 0.200000 | 400000 | o200k | – | – | medium | litellm |
| OpenAI: GPT-5 Nano | openai | openai | – | 0.050000 | 0.400000 | 0.005000 | – | 0.025000 | 0.200000 | 400000 | o200k | – | – | medium | litellm |
| OpenAI: GPT-5 Nano | openai | openai | – | 0.050000 | 0.400000 | 0.005000 | – | 0.025000 | 0.200000 | 400000 | o200k | – | – | medium | litellm |
| Meta: Llama 4 Maverick | meta | lambda | – | 0.050000 | 0.100000 | – | – | – | – | 1048576 | llama3 | – | – | medium | litellm |
| Meta: Llama 4 Scout | meta | lambda | – | 0.050000 | 0.100000 | – | – | – | – | 131072 | llama3 | – | – | medium | litellm |
| OpenAI: GPT-6 Luna | openai | openai | batch | 0.050000 | 0.250000 | 0.005000 | 0.062500 | – | – | 1050000 | o200k | – | – | high | official-openai |
| OpenAI: GPT-6 Luna | openai | openai | flex | 0.050000 | 0.250000 | 0.005000 | 0.062500 | – | – | 1050000 | o200k | – | – | high | official-openai |
| OpenAI: GPT-6 Luna | openai | openai | – | 0.050000 | 0.250000 | 0.005000 | 0.062500 | – | – | 1050000 | o200k | – | – | high | openrouter |
| OpenAI: GPT-5 Nano | openai | azure | – | 0.050000 | 0.400000 | 0.010000 | – | – | – | 400000 | o200k | – | – | high | openrouter |
| OpenAI: GPT-5 Nano | openai | openai | – | 0.050000 | 0.400000 | 0.005000 | – | – | – | 400000 | o200k | – | – | high | openrouter |
| Google: Gemini 2.5 Flash Lite | – | 0.050000 | 0.200000 | 0.005000 | 0.041667 | – | – | 1048576 | gemini | – | – | high | openrouter | ||
| OpenAI: GPT-5 Nano | openai | azure | unknown | 0.055000 | 0.440000 | 0.011000 | – | – | – | 400000 | o200k | – | – | high | openrouter |
| OpenAI: GPT-5 Nano | openai | azure | – | 0.055000 | 0.440000 | 0.011000 | – | – | – | 400000 | o200k | – | – | high | openrouter |
| Nova Lite (APAC) | amazon | aws-bedrock | – | 0.060000 | 0.240000 | 0.015000 | – | – | – | 300000 | – | – | – | medium | litellm |
| Nova Lite (APAC) | amazon | amazon | – | 0.060000 | 0.240000 | – | – | – | – | 300000 | – | – | – | medium | litellm |
| Nova Lite (APAC) | amazon | aws-bedrock | – | 0.060000 | 0.240000 | 0.015000 | – | – | – | 300000 | – | – | – | medium | litellm |
| Nova Lite (APAC) | amazon | aws-bedrock | – | 0.063000 | 0.252000 | 0.015750 | – | – | – | 300000 | – | – | – | medium | litellm |
| Nova Lite (APAC) | amazon | aws-bedrock | – | 0.064000 | 0.256000 | 0.016000 | 0.064000 | – | – | 300000 | – | – | – | medium | modelsdev |
| Microsoft: Phi 4 | microsoft | openrouter | – | 0.070000 | 0.140000 | – | – | – | – | 16384 | – | – | – | high | openrouter |
| Microsoft: Phi 4 | microsoft | deepinfra | – | 0.070000 | 0.140000 | – | – | – | – | 16384 | – | – | – | high | openrouter |
| Microsoft: Phi 4 | microsoft | deepinfra | – | 0.070000 | 0.140000 | – | – | – | – | 16384 | – | – | – | medium | litellm |
| Nova Lite (APAC) | amazon | aws-bedrock | – | 0.078000 | 0.312000 | 0.019500 | – | – | – | 300000 | – | – | – | medium | litellm |
| Qwen: Qwen3 235B A22B | alibaba | deepinfra | – | 0.090000 | 0.550000 | – | – | – | – | 128000 | qwen2 | – | – | medium | litellm |
| Qwen: Qwen3 235B A22B | alibaba | novita | – | 0.090000 | 0.580000 | – | – | – | – | 128000 | qwen2 | – | – | medium | litellm |
| OpenAI: GPT-6 Luna | openai | openrouter | – | 0.100000 | 0.500000 | 0.010000 | 0.125000 | 0.050000 | 0.250000 | 1050000 | o200k | – | – | high | openrouter |
| Google: Gemini 2.5 Flash Lite | openrouter | – | 0.100000 | 0.400000 | 0.010000 | 0.083333 | 0.050000 | 0.200000 | 1048576 | gemini | – | – | high | openrouter | |
| Meta: Llama 4 Scout | meta | openrouter | – | 0.100000 | 0.300000 | – | – | – | – | 131072 | llama3 | – | – | high | openrouter |
| OpenAI: GPT-6 Luna | openai | openai | unknown | 0.100000 | 0.500000 | 0.010000 | 0.125000 | – | – | 1050000 | o200k | – | – | high | openrouter |
| OpenAI: GPT-6 Luna | openai | azure | unknown | 0.100000 | 0.500000 | 0.010000 | 0.125000 | – | – | 1050000 | o200k | – | – | high | openrouter |
| Google: Gemini 2.5 Flash Lite | google-vertex | unknown | 0.100000 | 0.400000 | 0.010000 | 0.083333 | – | – | 1048576 | gemini | – | – | high | openrouter | |
| Google: Gemini 2.5 Flash Lite | google-vertex | unknown | 0.100000 | 0.400000 | 0.010000 | 0.083333 | – | – | 1048576 | gemini | – | – | high | openrouter |