Gateway
How OpenRouter compares
Managed gateway. A few model rates from the public models API, fetched with the catalog.
Pricing page · Site · Open in compare
The models API lists hundreds of routes. Three rows are stored as a sample of that feed, not a full mirror.
Regions and compliance
Regions: not published / unverified
Compliance: not published / unverified
Token offerings
anthropic/claude-sonnet-5.5
serverless_api · anthropic/claude-sonnet-5.5 · open-weight not published / unverified
- Input / 1M
- 2openrouter.aichecked 2026-10-20“anthropic/claude-sonnet-5.5 pricing.prompt 0.000002 USD per token ($2 / 1M).”
- Cached input / 1M
- 0.1openrouter.aichecked 2026-10-20“anthropic/claude-sonnet-5.5 pricing.input_cache_read 0.0000001 USD per token ($0.10 / 1M).”
- Output / 1M
- 10openrouter.aichecked 2026-10-20“anthropic/claude-sonnet-5.5 pricing.completion 0.00001 USD per token ($10 / 1M).”
Context not published · tokens/s not published · TTFT not published
Router price from the public models API on the check date. It matched Anthropic's list price that day. It can diverge.
openai/gpt-oss-120b
serverless_api · openai/gpt-oss-120b · open-weight true
- Input / 1M
- 0.15openrouter.aichecked 2026-10-20“openai/gpt-oss-120b pricing.prompt 0.00000015 USD per token ($0.15 / 1M).”
- Cached input / 1M
- 0.075openrouter.aichecked 2026-10-20“openai/gpt-oss-120b pricing.input_cache_read 0.000000075 USD per token ($0.075 / 1M).”
- Output / 1M
- 0.6openrouter.aichecked 2026-10-20“openai/gpt-oss-120b pricing.completion 0.0000006 USD per token ($0.60 / 1M).”
Context not published · tokens/s not published · TTFT not published
x-ai/grok-4.7
serverless_api · x-ai/grok-4.7 · open-weight not published / unverified
- Input / 1M
- 2openrouter.aichecked 2026-10-20“x-ai/grok-4.7 pricing.prompt 0.000002 USD per token ($2 / 1M).”
- Cached input / 1M
- 0.5openrouter.aichecked 2026-10-20“x-ai/grok-4.7 pricing.input_cache_read 0.0000005 USD per token ($0.50 / 1M).”
- Output / 1M
- 6openrouter.aichecked 2026-10-20“x-ai/grok-4.7 pricing.completion 0.000006 USD per token ($6 / 1M).”
Context not published · tokens/s not published · TTFT not published
The same API object has an override at min_prompt_tokens 200000: prompt 0.000004, completion 0.000012, cache read 0.000001.
Compute SKUs
No GPU or node price is seeded.