Models
All models are open-weight. Pricing is what you pay (USD per 1M tokens). The gateway pays less upstream — your margin shows up in nikcli.marginUsd.
Aliases
These are the easy-to-remember names. They resolve to the canonical model.
| Alias | Resolves to | Context | In $/M | Out $/M |
|---|
nikcli-mini | qwen-3.5-flash | 1M | $0.08 | $0.33 |
nikcli-fast | deepseek-v4-flash | 1.05M | $0.14 | $0.28 |
nikseek | deepseek-v4-pro | 128K | $8 | $32 |
nikcli-max | kimi-k2.6 | 256K | $8 | $24 |
nikcli-reason | deepseek-r1-0528 | 164K | $0.63 | $2.69 |
nikcli-coder | devstral-2 | 128K | $8 | $24 |
nikcli-vision | llama-4-scout | 1M | $4 | $12 |
nikcli-free | minimax-2.5-free | 205K | $0 | $0 |
DeepSeek
| Model | Context | In $/M | Out $/M | :thinking |
|---|
deepseek-v4-pro | 128K | $8 | $32 | ✅ |
deepseek-v4-flash | 1.05M | $0.14 | $0.28 | ✅ |
deepseek-v4-flash-free | 1.05M | $0 | $0 | ✅ |
deepseek-v3.2 | 131K | $0.32 | $0.47 | ✅ |
deepseek-v3 | 128K | $5 | $15 | ✅ |
deepseek-r1 | 128K | $5 | $20 | native |
deepseek-r1-0528 | 164K | $0.63 | $2.69 | native |
deepseek-r1-distill-32b | 128K | $4 | $16 | native |
Kimi / Moonshot
| Model | Context | In $/M | Out $/M | :thinking |
|---|
kimi-k2.6 | 256K | $8 | $24 | ✅ |
kimi-k2.5 | 256K | $7 | $21 | ✅ |
GLM (Zhipu)
| Model | Context | In $/M | Out $/M | :thinking |
|---|
glm-5.1 | 200K | $10 | $30 | ✅ |
glm-5 | 200K | $8 | $24 | ✅ |
glm-5.1-free | 200K | $0 | $0 | ✅ |
Qwen
| Model | Context | In $/M | Out $/M | :thinking |
|---|
qwen-3.5-72b | 128K | $12 | $36 | ✅ |
qwen-3.5-32b | 128K | $6 | $18 | ✅ |
qwen-3.5-14b | 128K | $3 | $9 | — |
qwen-3.5-flash | 1M | $0.08 | $0.33 | ✅ |
qwen-3.6-max | 256K | $1.30 | $7.80 | ✅ |
qwq-32b | 128K | $8 | $24 | native |
| Model | Context | In $/M | Out $/M |
|---|
llama-4-scout | 1M | $4 | $12 |
llama-4-maverick | 1M | $6 | $18 |
llama-3.3-70b | 128K | $59 | $79 |
Mistral
| Model | Context | In $/M | Out $/M |
|---|
mistral-medium-3.5 | 256K | $15 | $45 |
mistral-small-4 | 128K | $6 | $18 |
devstral-2 (code) | 128K | $8 | $24 |
Other
| Model | Context | In $/M | Out $/M |
|---|
gemma-4-31b | 256K | $5 | $15 |
gemma-4-26b-a4b | 256K | $4 | $12 |
phi-4-mini | 128K | $1 | $3 |
phi-4 | 128K | $3 | $9 |
minimax-m2.7 | 100K | $8 | $24 |
minimax-m2 | 100K | $6 | $18 |
minimax-2.5 | 205K | $0.19 | $1.44 |
minimax-2.5-free | 205K | $0 | $0 |
The live catalog is at /v1/models — it includes the upstream provider routes per model and reflects what is actually enabled in production.