| Grok 4.20 Beta Reasoning (0309) (xAI) | xai | 1,000,000 | - Input
- Input (>200k ctx)
- Input (cached read, >200k ctx)
- Input (cached read)
…3 more prices |
| SpaceXAI: Grok 4.6 | xai | 500,000 | - Input
$2.00 per 1M tokens medium- Input (>200k ctx)
$4.00 per 1M tokens medium- Input (cached read, >200k ctx)
$1.00 per 1M tokens medium- Input (cached read)
$0.50 per 1M tokens medium
…3 more prices |
| Grok 4.20 Beta Non-Reasoning (0309) (xAI) | xai | 1,000,000 | - Input
- Input (>200k ctx)
- Input (cached read, >200k ctx)
- Input (cached read)
…3 more prices |
| GLM-4.6V FlashX (Z AI) | z-ai | 128,000 | - Input
- Input (cached read)
- Output
|
| GLM-4.5 X (Z AI) | z-ai | 128,000 | |
| GLM-4.5 AirX (Z AI) | z-ai | 128,000 | |
| GLM-4 32B (0414-128k) (Z AI) | z-ai | 128,000 | |
| Mistral: Ministral 3 14B 2512 | mistral | 262,144 | - Input
$0.20 per 1M tokens medium- Input (cached read)
$0.02 per 1M tokens medium- Output
$0.20 per 1M tokens medium
|
| Mistral: Codestral 2508 | mistral | 256,000 | - Input
- Input (cached read)
- Output
|
| Mistral: Mistral Small 4 | mistral | 262,144 | - Input
$0.10 per 1M tokens unverified · disputed- Input (cached read)
$0.015 per 1M tokens unverified · disputed- Output
$0.30 per 1M tokens unverified · disputed
|
| Mistral: Devstral 2 2512 | mistral | 262,144 | - Input
$0.40 per 1M tokens medium- Input (cached read)
$0.04 per 1M tokens medium- Output
$2.00 per 1M tokens medium
|
| Mistral Large | mistral | 128,000 | - Input
$0.50 per 1M tokens unverified · disputed- Input (cached read)
$0.05 per 1M tokens medium- Output
$1.50 per 1M tokens unverified · disputed
|
| Mistral: Ministral 3 3B 2512 | mistral | 131,072 | - Input
- Input (cache write)
- Input (cached read)
$0.01 per 1M tokens unverified · disputed- Output
|
| Mistral: Ministral 3 8B 2512 | mistral | 262,144 | - Input
$0.10 per 1M tokens unverified · disputed- Input (cached read)
- Output
$0.10 per 1M tokens unverified · disputed
|
| GLM-4.7 (Cerebras) | cerebras | 200,000 | |
| Gemma 4 31B IT (Cerebras) | cerebras | 131,072 | |
| Qwen3 235B A22B Instruct 2507 (Cerebras) | cerebras | 262,000 | |
| Llama 3.3 70B Instruct (Cerebras) | cerebras | 128,000 | |
| Perplexity: Sonar | perplexity | 127,072 | - Input
$1.00 per 1M tokens medium- Output
$1.00 per 1M tokens medium- Per request
$12.00 per 1K requests low- Web search (context size: high)
…2 more prices |
| Perplexity: Sonar Reasoning Pro | perplexity | 128,000 | - Input
$2.00 per 1M tokens medium- Output
$8.00 per 1M tokens medium- Per request
$14.00 per 1K requests low- Web search (context size: high)
…2 more prices |
| Perplexity: Sonar Pro | perplexity | 200,000 | - Input
$3.00 per 1M tokens medium- Output
$15.00 per 1M tokens medium- Per request
$14.00 per 1K requests low- Web search (context size: high)
…2 more prices |
| Kimi K2.6 (Runware) | runware | 262,144 | - Input
- Input (cached read)
- Output
|
| GLM-5.2 (Runware) | runware | 1,024,000 | - Input
- Input (cached read)
- Output
|
| DeepSeek V4 Flash (Runware) | runware | 1,048,576 | - Input
- Input (cached read)
- Output
|
| Kimi K3 (Runware) | runware | 1,048,576 | - Input
- Input (cached read)
- Output
|