Models & pricing · RedRouter Docs

Use the exact model ID below. RedRouter does not substitute a different model.

Prices

Model	Input / 1M	Cached input / 1M	Output / 1M
GLM 5.3 Flash RR `glm-5.3-flash-rr` Available	$0.20/M	$0.08/M	$0.80/M
GLM 5.3 RR (experimental) `glm-5.3-rr` Available	$1.40/M	$0.35/M	$2.50/M
Qwen 3.8 27B RR `qwen3.8-27b-rr` Available	$0.55/M	$0.08/M	$2.40/M
DeepSeek V4.1 Flash RR `deepseek-v4.1-flash-rr` Available	$1.15/M	$0.115/M	$2.30/M
DeepSeek V4.1 Flash (1017) `deepseek-v4.1-flash-1017` Available	$0.15/M	$0.005/M	$0.57/M
DeepSeek V4.1 Flash (0910) `deepseek-v4.1-flash-0910` Available	$0.04/M	$0.008/M	$0.15/M
GLM 5.3 Flash `glm-5.3-flash` Available	$0.06/M	$0.035/M	$0.23/M
GLM 5.3 `glm-5.3` Available	$0.08/M	$0.08/M	$1.60/M
Qwen 3.8 27B `qwen3.8-27b` Available	$0.04/M	$0.005/M	$0.35/M

Prices are USD per million tokens. Cache reads use the cached rate only when reported. Unreported cache reads use the input rate. Zero Data Retention adds 20% to every rate, except on monthly plans.

Model limits

Model	Context tokens	Max output	Default output	Tools	Response format
`glm-5.3-flash-rr`	1048576	8192	1024	Yes	Yes
`glm-5.3-rr`	1048576	8192	1024	Yes	No
`qwen3.8-27b-rr`	1010000	8192	1024	Yes	Yes
`deepseek-v4.1-flash-rr`	1048576	8192	1024	Yes	Yes
`deepseek-v4.1-flash-1017`	1048576	8192	1024	Yes	Yes
`deepseek-v4.1-flash-0910`	262144	8192	1024	Yes	Yes
`glm-5.3-flash`	1048576	8192	1024	Yes	Yes
`glm-5.3`	1048576	8192	1024	Yes	Yes
`qwen3.8-27b`	1048576	8192	1024	Yes	Yes

Output limits above the model maximum are capped. Request bodies are limited to 1048576 bytes.

Try this model

curl -X POST 'https://redrouter.org/v1/chat/completions' \
  -H "Authorization: Bearer $REDROUTER_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "messages": [
    {
      "content": "Hello",
      "role": "user"
    }
  ],
  "model": "glm-5.3-flash-rr"
}'

Read the full catalog response for checkpoint facts and accepted fields.