Models
Every model the Morse Inference API serves. Want a model listed here? Reach out
| Model | Input | Output | Cached input | Context | Max output | Tiers | Open weights | Capabilities |
|---|---|---|---|---|---|---|---|---|
| Kimi K3 | $3/M | $15/M | $0.30/M | 1M | 1M | |||
| GLM 5.2 | $1.40/M | $4.40/M | $0.26/M | 1M | 1M | |||
| DeepSeek V4 Pro | $1.32/M | $3.96/M | $0.13/M | 1M | 1M | |||
| GLM 5.3 | $4.40/M | $0.26/M | 1M | 1M | ||||
| GLM 5.3 Flash | $0.15/M | $0.50/M | $0.03/M | 1M | 1M | |||
| DeepSeek V4.1 Flash | $0.30/M | $1.20/M | $0.006/M | 1M | 1M | |||
| DeepSeek V4.1 Flash 1017 | $1.20/M | $0.006/M | 1M | 943.7K | ||||
| Kimi K3.1 Pro | $10/M | $0.20/M | 1M | 1M | ||||
| MiniMax M3.1 Flash | $0.15/M | $0.60/M | $0.01/M | 1M | 943.7K | |||
| MiMo V2.6 Pro | $0.43/M | $0.87/M | $0.004/M | 1M | 943.7K | |||
| MiMo V2.6 Flash | $0.14/M | $0.28/M | $0.003/M | 1M | 943.7K | |||
| Hy4 Preview | $0.83/M | $2.50/M | $0.04/M | 1M | 131K | |||
| GLM 4.7 | $0.60/M | $2.20/M | $0.11/M | 202.7K | 131K | |||
| Qwen3.5 397B A17B | $0.60/M | $3.60/M | $0.60/M | 262.1K | 81.9K | |||
| Qwen3.5 35B A3B | $0.25/M | $2/M | $0.25/M | 262.1K | 81.9K | |||
| Qwen3.6 27B | $0.60/M | $3.60/M | $0.60/M | 262.1K | 81.9K | |||
| MiniMax M3 | $0.30/M | $1.20/M | $0.06/M | 524.2K | 131K | |||
| Nemotron 3 Ultra | $0.63/M | $2.75/M | $0.13/M | 262.1K | 16.3K | |||
| Nemotron 3.5 Lightning | $0.07/M | $0.20/M | $0.04/M | 262.1K | 32.7K | |||
| Nemotron 3.5 Super VL | $0.19/M | $0.63/M | $0.03/M | 262.1K | 235.9K | |||
| gpt-oss-120b | $0.21/M | $0.05/M | 131K | 117.9K | ||||
| gpt-oss-20b | $0.04/M | $0.17/M | $0.04/M | 131K | 117.9K | |||
| Qwen3.5 9B | $0.13/M | $0.19/M | $0.13/M | 262.1K | 81.9K | |||
| Granite 4.2 8B | $0.07/M | $0.31/M | $0.02/M | 131K | 117.9K | |||
| Ling 3.0 Flash VL | $0.07/M | $0.23/M | $0.01/M | 131K | 32.7K | |||
| Muse Glimmer 30B | $0.38/M | $1.50/M | $0.05/M | 131K | 16.3K | |||
| Llama 4 Scout | $0.13/M | $0.38/M | $0.13/M | 327.6K | 16.3K | |||
| Kimi K2.6 | $4/M | $0.16/M | 262.1K | 262.1K | ||||
| DeepSeek V4 Flash 0731 | $1.32/M | $0.03/M | 1M | 393.2K | ||||
| Qwen3.8 27B | $0.50/M | $3/M | $0.10/M | 262.1K | 262.1K | |||
| Qwen3.8 Max | $2/M | $6/M | $0.25/M | 1M | 131K | |||
| Kimi K2.7 Code | $0.95/M | $4/M | $0.19/M | 262.1K | 262.1K | |||
| DeepSeek R1 | $0.88/M | $3.13/M | $0.88/M | 64K | 16K | |||
| DeepSeek R1 0528 | $0.55/M | $2.19/M | $0.35/M | 163.8K | 32.7K | |||
| DeepSeek V3 | $0.32/M | $1.10/M | $0.32/M | 163.8K | 16.3K | |||
| DeepSeek V3.1 | $0.56/M | $1.68/M | $0.13/M | 163.8K | 147.4K | |||
| DeepSeek V3.2 | $0.28/M | $0.42/M | $0.13/M | 163.8K | 147.4K | |||
| DeepSeek V4 Flash 0423 | $0.14/M | $0.28/M | $0.02/M | 1M | 393.2K | |||
| DeepSeek V4 Flash Vision Exp | $0.55/M | $1.65/M | $0.02/M | 1M | 262.1K | |||
| DeepSeek V4 Pro 0423 | $1.63/M | $3.25/M | $0.13/M | 1M | 393.2K | |||
| Gemma 3 12B | $0.06/M | $0.19/M | $0.06/M | 131K | 16.3K | |||
| Gemma 3 27B | $0.10/M | $0.20/M | $0.10/M | 131K | 16.3K | |||
| Gemma 3 4B | $0.06/M | $0.13/M | $0.06/M | 131K | 16.3K | |||
| Gemma 4 26B A4B | $0.15/M | $0.60/M | $0.07/M | 262.1K | 16.3K | |||
| Gemma 4 31B | $0.25/M | $0.50/M | $0.25/M | 262.1K | 16.3K | |||
| Ling 3.0 Flash Fin | $0.09/M | $0.28/M | $0.02/M | 262.1K | 32.7K | |||
| Ling 3.1 Flash | $0.38/M | $1.13/M | $0.07/M | 1M | 262.1K | |||
| Llama 3.1 8B | $0.03/M | $0.05/M | $0.03/M | 131K | 16.3K | |||
| Llama 3.3 70B | $0.13/M | $0.40/M | $0.13/M | 131K | 16.3K | |||
| WizardLM-2 8x22B | $0.78/M | $0.78/M | $0.78/M | 65.5K | 8K | |||
| MiniMax M2.5 | $0.38/M | $1.50/M | $0.04/M | 204.8K | 131.1K | |||
| MiniMax M2.7 | $0.38/M | $1.50/M | $0.07/M | 204.8K | 131K | |||
| Mistral Nemo | $0.04/M | $0.04/M | $0.04/M | 131K | 16.3K | |||
| Mistral Small 3 2501 | $0.10/M | $0.30/M | $0.10/M | 32.7K | 8.1K | |||
| Mistral Small 3.2 | $0.10/M | $0.30/M | $0.10/M | 128K | 16.3K | |||
| Kimi K2 | $0.60/M | $2.50/M | $0.57/M | 131K | 98.3K | |||
| Kimi K2 0905 | $0.75/M | $3.13/M | $0.75/M | 262.1K | 98.3K | |||
| Kimi K2 Thinking | $0.75/M | $3.13/M | $0.19/M | 262.1K | 98.3K | |||
| Kimi K2.5 | $0.75/M | $3.75/M | $0.13/M | 262.1K | 262.1K | |||
| Nemotron 3 Super | $0.09/M | $0.50/M | $0.09/M | 262.1K | 32.7K | |||
| Qwen2.5 72B Instruct | $0.45/M | $0.50/M | $0.45/M | 32.7K | 8.1K | |||
| Qwen2.5 7B Instruct | $0.13/M | $0.25/M | $0.13/M | 32.7K | 8.1K | |||
| Qwen3 14B | $0.35/M | $1.40/M | $0.35/M | 40.9K | 16.3K | |||
| Qwen3 235B A22B Instruct 2507 | $0.23/M | $0.92/M | $0.23/M | 262.1K | 16.3K | |||
| Qwen3 30B A3B | $0.20/M | $0.80/M | $0.20/M | 40.9K | 16.3K | |||
| Qwen3 32B | $0.16/M | $0.64/M | $0.16/M | 40.9K | 16.3K | |||
| Qwen3 Coder 480B A35B | $0.38/M | $1.25/M | $0.13/M | 262.1K | 65.5K | |||
| Qwen3 Next 80B A3B Instruct | $0.15/M | $1.20/M | $0.15/M | 262.1K | 16.3K | |||
| Qwen3 VL 235B A22B | $0.40/M | $1.60/M | $0.40/M | 262.1K | 16.3K | |||
| Qwen3 VL 30B A3B | $0.20/M | $0.80/M | $0.20/M | 262.1K | 16.3K | |||
| Qwen3.5 122B A10B | $0.40/M | $3.20/M | $0.40/M | 262.1K | 65.5K | |||
| Qwen3.5 27B | $0.30/M | $2.40/M | $0.30/M | 262.1K | 65.5K | |||
| Qwen3.6 35B A3B | $0.38/M | $2.25/M | $0.38/M | 262.1K | 65.5K | |||
| Llama 3.1 70B Euryale v2.2 | $1.06/M | $1.06/M | $1.06/M | 131K | 16.3K | |||
| Step 3.7 Flash | $0.20/M | $1.15/M | $0.04/M | 262.1K | 256K | |||
| Hy3 | $0.17/M | $0.72/M | $0.04/M | 262.1K | 262.1K | |||
| Inkling-Small | $0.56/M | $1.50/M | $0.13/M | 524.2K | 131K | |||
| GLM 4.5 Air | $0.20/M | $1.10/M | $0.03/M | 131K | 98.3K | |||
| GLM 4.5V | $0.60/M | $1.80/M | $0.11/M | 65.5K | 16.3K | |||
| GLM 4.6 | $0.60/M | $2.20/M | $0.11/M | 202.7K | 131K | |||
| GLM 4.6V | $0.30/M | $0.90/M | $0.06/M | 131K | 32.7K | |||
| GLM 4.7 Flash | $0.09/M | $0.50/M | $0.01/M | 200K | 128K | |||
| GLM 5 | $1/M | $3.20/M | $0.20/M | 202.8K | 131K | |||
| GLM 5.1 | $1.40/M | $4.40/M | $0.26/M | 204.8K | 131K | |||
| DeepSeek V4.1 Flash 1017 Uncensored | $0.38/M | $1.50/M | $0.007/M | 1M | 393.2K |
Prices are per million tokens. A model served on more than one tier shows its default tier's price, and how many others it has. Pick a tier to see that tier's. The tiers say who can read a prompt on its way: no one but you on E2EE, only attested hardware on TEE, and only the provider's hardware on Private.See where a prompt goes