Synthetic can use either subscription or usage-based pricing. Choose the plan that works best for you.
Small requests with less than 2048 input tokens and less than 2048 output tokens only count as 0.2 requests. And tool call messages count for even less: only 0.1 requests (up to 12x your five hour limit)
All always-on models are included in your subscription. There's no additional charge for using any of these models.
With your subscription, all always-on models are included for one flat monthly price. No per-token billing—just simple, predictable pricing.
Switch to "Pay per Use" to see token-based pricing for when you don't need a subscription.
Here's the list of all always-on models included in your subscription:
| Model | Context length | Status |
|---|---|---|
| deepseek-ai/DeepSeek-R1-0528 | 128k tokens | ✓ Included |
| deepseek-ai/DeepSeek-V3 | 128k tokens | ✓ Included |
| deepseek-ai/DeepSeek-V3-0324 | 128k tokens | ✓ Included |
| deepseek-ai/DeepSeek-V3.2 | 159k tokens | ✓ Included |
| meta-llama/Llama-3.3-70B-Instruct | 128k tokens | ✓ Included |
| MiniMaxAI/MiniMax-M2.1 | 192k tokens | ✓ Included |
| moonshotai/Kimi-K2-Instruct-0905 | 256k tokens | ✓ Included |
| moonshotai/Kimi-K2-Thinking | 256k tokens | ✓ Included |
| moonshotai/Kimi-K2.5 | 256k tokens | ✓ Included |
| nvidia/Kimi-K2.5-NVFP4 | 256k tokens | ✓ Included |
| openai/gpt-oss-120b | 128k tokens | ✓ Included |
| Qwen/Qwen3-235B-A22B-Thinking-2507 | 256k tokens | ✓ Included |
| Qwen/Qwen3-Coder-480B-A35B-Instruct | 256k tokens | ✓ Included |
| zai-org/GLM-4.7 | 198k tokens | ✓ Included |
Low-rank adapters — called "LoRAs" — are small, efficient fine-tunes that run on top of existing models. They can modify a model to be much more effective at specific tasks.
All LoRAs for the following base models are included in your subscription:
| Model | Context length | Status |
|---|---|---|
| meta-llama/Llama-3.2-1B-Instruct | 128k tokens | ✓ Included |
| meta-llama/Llama-3.2-3B-Instruct | 128k tokens | ✓ Included |
| meta-llama/Meta-Llama-3.1-8B-Instruct | 128k tokens | ✓ Included |
| meta-llama/Meta-Llama-3.1-70B-Instruct | 128k tokens | ✓ Included |
Embedding models convert text to special numerical coordinates, placing more-similar text closer to each other and less-similar text more distant: these coordinates are referred to as "embeddings". Embedding models are often used by AI-enabled tools for tasks like codebase indexing or search.
The following embedding models are included in your subscription. There's no additional charge for using embeddings, and embeddings requests don't count against your subscription rate limit.
| Model | Context length | Status |
|---|---|---|
| nomic-ai/nomic-embed-text-v1.5 | 8k tokens | ✓ Included |