- Context
- 1.0M
- Input /M
- $0.05/M
- Output /M
- $0.47/M
- Cache read /M
- $0.05/M
- TTFT
- 0.8s
- Throughput
- 31 tps
Relace
UNK
11 models available
Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.
Models served by Relace
11 models
- Context
- 1.0M
- Input /M
- $0.05/M
- Output /M
- $0.47/M
- Cache read /M
- $0.05/M
- TTFT
- 0.8s
- Throughput
- 31 tps
- Context
- 1.0M
- Input /M
- $0.73/M
- Output /M
- $1.47/M
- Cache read /M
- $0.07/M
- TTFT
- 0.7s
- Throughput
- 90 tps
- Context
- 1.0M
- Input /M
- $0.73/M
- Output /M
- $1.47/M
- Cache read /M
- $0.07/M
- TTFT
- 0.7s
- Throughput
- 90 tps
- Context
- 1.0M
- Input /M
- $0.23/M
- Output /M
- $8.40/M
- Cache read /M
- $0.23/M
- TTFT
- 0.9s
- Throughput
- 102 tps
- Context
- 1.0M
- Input /M
- $0.23/M
- Output /M
- $8.40/M
- Cache read /M
- $0.23/M
- TTFT
- 0.9s
- Throughput
- 102 tps
- Context
- 1.0M
- Input /M
- $0.07/M
- Output /M
- $0.53/M
- Cache read /M
- $0.0084/M
- TTFT
- 1.2s
- Throughput
- 122 tps
- Context
- 1.0M
- Input /M
- $0.07/M
- Output /M
- $0.53/M
- Cache read /M
- $0.0084/M
- TTFT
- 1.2s
- Throughput
- 122 tps
- Context
- 1.0M
- Input /M
- $0.79/M
- Output /M
- $2.52/M
- Cache read /M
- $0.08/M
- TTFT
- 2.7s
- Throughput
- 39 tps
- Context
- 1.0M
- Input /M
- $0.79/M
- Output /M
- $2.52/M
- Cache read /M
- $0.08/M
- TTFT
- 2.7s
- Throughput
- 39 tps
MiMo V2.6 Flash
MXFP4
- Context
- 1.0M
- Input /M
- $0.14/M
- Output /M
- $0.29/M
- Cache read /M
- $0.0032/M
- TTFT
- 0.6s
- Throughput
- 88 tps
Prices are per million tokens. TTFT is the observed time to first token. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.
Using Relace via the API
Call a model served by Relace using its displayed model ID, including the provider suffix when selection is supported.
cURL
curl https://nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-flash:relace",
"messages": [{"role": "user", "content": "Hello"}]
}'For models with provider selection, append :relace to the model ID, set "provider": "relace" in the request body, or send an X-Provider: relace header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.
See the API documentation for provider preferences, price-aware routing, and error behavior.