Token Router
Every model, one endpoint
Anthropic-compatible and OpenAI-compatible, so your existing tools work unchanged. Bring your own provider keys and routing is free, or run on managed credits. Tokens bill at provider list price with no markup, and prompts and responses are never stored.
- 13
- models
- 8
- vendors
- 1.0M
- largest context
- $0.037
- from, per M input
13 of 13 models · prices are provider list price per million tokens · some models cost more past a context threshold, shown under the rate
| Model | Vendor | Context | Input | Output | Images |
|---|---|---|---|---|---|
| Qwen3.5 397B | Alibabaopen | 262K | $0.45 | $3 | no |
| Claude Haiku 4.5 | Anthropic | 200K | $1 | $5 | yes |
| Claude Opus 4.8 | Anthropic | 200K | $5 | $25 | yes |
| Claude Sonnet 5 | Anthropic | 200K | $3 | $15 | yes |
| DeepSeek V4 Flash | DeepSeekopen | 128K | $0.09 | $0.18 | no |
| Gemini 3.1 Flash-Lite | 1,048K | $0.3 | $2.5 | yes | |
| Gemini 3.1 Pro | 1,048K | $2$4 past 200K | $12$18 past 200K | yes | |
| Gemini 3.6 Flash | 1,048K | $1.5 | $7.5 | yes | |
| Kimi K2.7 Code | Moonshotopen | 256K | $0.74 | $3.5 | no |
| GPT-5.6 Luna | OpenAI | 400K | $1 | $6 | yes |
| GPT-5.6 Terra | OpenAI | 400K | $2.5 | $15 | yes |
| gpt-oss 120B | OpenAI (open weights)open | 131K | $0.037 | $0.17 | no |
| GLM-5.2 | Z.aiopen | 128K | $0.93 | $3 | no |
Then see what the spend shipped
Every request through the rail is metered per engineer at these prices, then tied back to the pull requests it produced. Routing is the door; the attribution is the product.
See live demo