Models
UClaw provides access to leading AI models through a unified API. All prices shown include UClaw's 15% infrastructure fee covering runtime, streaming, billing, and tool execution.
TIP
Model IDs follow the provider/model-name format. Pass them as config.model when creating or updating an agent.
Highlighted Models
These are the most commonly used models for typical agent workloads:
| Model ID | Name | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
anthropic/claude-sonnet-4 | Claude Sonnet 4 | 1M | $3.45 | $17.25 |
anthropic/claude-opus-4.7 | Claude Opus 4.7 | 1M | $5.75 | $28.75 |
openai/gpt-4.1 | GPT-4.1 | 1M | $2.30 | $9.20 |
openai/gpt-4.1-mini | GPT-4.1 mini | 1M | $0.46 | $1.84 |
openai/gpt-5 | GPT-5 | 400K | $1.44 | $11.50 |
google/gemini-2.5-flash | Gemini 2.5 Flash | 1M | $0.35 | $2.88 |
google/gemini-2.5-pro | Gemini 2.5 Pro | 1M | $1.44 | $11.50 |
deepseek/deepseek-v4-flash | DeepSeek V4 Flash | 1M | $0.16 | $0.32 |
deepseek/deepseek-v4-pro | DeepSeek V4 Pro | 1M | $0.50 | $1.00 |
All Models
Alibaba (Qwen)
| Model ID | Name | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
alibaba/qwen-3-14b | Qwen3-14B | 40K | $0.14 | $0.28 |
alibaba/qwen-3-30b | Qwen3-30B-A3B | 40K | $0.09 | $0.33 |
alibaba/qwen-3-32b | Qwen 3 32B | 128K | $0.18 | $0.74 |
alibaba/qwen-3-235b | Qwen3 235B A22b | 131K | $0.69 | $1.38 |
alibaba/qwen3-max | Qwen3 Max | 262K | $1.38 | $6.90 |
alibaba/qwen3-coder | Qwen3 Coder 480B | 262K | $1.73 | $8.63 |
alibaba/qwen3-coder-30b-a3b | Qwen3 Coder 30B | 262K | $0.17 | $0.69 |
alibaba/qwen3.5-flash | Qwen 3.5 Flash | 1M | $0.12 | $0.46 |
alibaba/qwen3.5-plus | Qwen 3.5 Plus | 1M | $0.46 | $2.76 |
alibaba/qwen3.6-max-preview | Qwen 3.6 Max Preview | 240K | $1.50 | $8.97 |
Anthropic (Claude)
| Model ID | Name | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
anthropic/claude-3-haiku | Claude 3 Haiku | 200K | $0.29 | $1.44 |
anthropic/claude-3.5-haiku | Claude 3.5 Haiku | 200K | $0.92 | $4.60 |
anthropic/claude-haiku-4.5 | Claude Haiku 4.5 | 200K | $1.15 | $5.75 |
anthropic/claude-sonnet-4 | Claude Sonnet 4 | 1M | $3.45 | $17.25 |
anthropic/claude-sonnet-4.5 | Claude Sonnet 4.5 | 1M | $3.45 | $17.25 |
anthropic/claude-sonnet-4.6 | Claude Sonnet 4.6 | 1M | $3.45 | $17.25 |
anthropic/claude-opus-4 | Claude Opus 4 | 200K | $17.25 | $86.25 |
anthropic/claude-opus-4.5 | Claude Opus 4.5 | 200K | $5.75 | $28.75 |
anthropic/claude-opus-4.6 | Claude Opus 4.6 | 1M | $5.75 | $28.75 |
anthropic/claude-opus-4.7 | Claude Opus 4.7 | 1M | $5.75 | $28.75 |
anthropic/claude-opus-4.8 | Claude Opus 4.8 | 1M | $5.75 | $28.75 |
DeepSeek
| Model ID | Name | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
deepseek/deepseek-r1 | DeepSeek-R1 | 128K | $1.55 | $6.21 |
deepseek/deepseek-v3 | DeepSeek V3 0324 | 163K | $0.89 | $0.89 |
deepseek/deepseek-v3.1 | DeepSeek-V3.1 | 163K | $0.64 | $1.93 |
deepseek/deepseek-v3.2 | DeepSeek V3.2 | 128K | $0.32 | $0.48 |
deepseek/deepseek-v4-flash | DeepSeek V4 Flash | 1M | $0.16 | $0.32 |
deepseek/deepseek-v4-pro | DeepSeek V4 Pro | 1M | $0.50 | $1.00 |
Google (Gemini & Gemma)
| Model ID | Name | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
google/gemini-2.0-flash | Gemini 2.0 Flash | 1M | $0.17 | $0.69 |
google/gemini-2.0-flash-lite | Gemini 2.0 Flash Lite | 1M | $0.09 | $0.35 |
google/gemini-2.5-flash | Gemini 2.5 Flash | 1M | $0.35 | $2.88 |
google/gemini-2.5-flash-lite | Gemini 2.5 Flash Lite | 1M | $0.12 | $0.46 |
google/gemini-2.5-pro | Gemini 2.5 Pro | 1M | $1.44 | $11.50 |
google/gemini-3-flash | Gemini 3 Flash | 1M | $0.58 | $3.45 |
google/gemini-3-pro-preview | Gemini 3 Pro Preview | 1M | $2.30 | $13.80 |
google/gemma-4-26b-a4b-it | Gemma 4 26B | 262K | $0.15 | $0.46 |
google/gemma-4-31b-it | Gemma 4 31B | 262K | $0.16 | $0.46 |
MiniMax
| Model ID | Name | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
minimax/minimax-m2 | MiniMax M2 | 205K | $0.35 | $1.38 |
minimax/minimax-m2.1 | MiniMax M2.1 | 204K | $0.35 | $1.38 |
minimax/minimax-m2.5 | MiniMax M2.5 | 204K | $0.35 | $1.38 |
minimax/minimax-m2.7 | MiniMax M2.7 | 204K | $0.35 | $1.38 |
Moonshot AI (Kimi)
| Model ID | Name | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
moonshotai/kimi-k2 | Kimi K2 Instruct | 131K | $0.66 | $2.65 |
moonshotai/kimi-k2-thinking | Kimi K2 Thinking | 262K | $0.69 | $2.88 |
moonshotai/kimi-k2-turbo | Kimi K2 Turbo | 256K | $1.32 | $9.20 |
moonshotai/kimi-k2.5 | Kimi K2.5 | 262K | $0.69 | $3.45 |
moonshotai/kimi-k2.6 | Kimi K2.6 | 262K | $1.09 | $4.60 |
OpenAI (GPT & o-series)
| Model ID | Name | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
openai/gpt-4o | GPT-4o | 128K | $2.88 | $11.50 |
openai/gpt-4o-mini | GPT-4o mini | 128K | $0.17 | $0.69 |
openai/gpt-4.1 | GPT-4.1 | 1M | $2.30 | $9.20 |
openai/gpt-4.1-mini | GPT-4.1 mini | 1M | $0.46 | $1.84 |
openai/gpt-4.1-nano | GPT-4.1 nano | 1M | $0.12 | $0.46 |
openai/gpt-5 | GPT-5 | 400K | $1.44 | $11.50 |
openai/gpt-5-mini | GPT-5 mini | 400K | $0.29 | $2.30 |
openai/gpt-5-nano | GPT-5 nano | 400K | $0.06 | $0.46 |
openai/gpt-5-pro | GPT-5 pro | 400K | $17.25 | $138.00 |
openai/gpt-5.4 | GPT 5.4 | 1M | $2.88 | $17.25 |
openai/gpt-5.4-mini | GPT 5.4 Mini | 400K | $0.86 | $5.18 |
openai/gpt-5.4-nano | GPT 5.4 Nano | 400K | $0.23 | $1.44 |
openai/gpt-5.5 | GPT 5.5 | 1M | $5.75 | $34.50 |
openai/o1 | o1 | 200K | $17.25 | $69.00 |
openai/o3 | o3 | 200K | $2.30 | $9.20 |
openai/o3-mini | o3-mini | 200K | $1.27 | $5.06 |
openai/o4-mini | o4-mini | 200K | $1.27 | $5.06 |
ZAI (GLM)
| Model ID | Name | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
zai/glm-4.5 | GLM-4.5 | 128K | $0.69 | $2.53 |
zai/glm-4.5-air | GLM 4.5 Air | 128K | $0.23 | $1.27 |
zai/glm-4.6 | GLM 4.6 | 200K | $0.69 | $2.53 |
zai/glm-4.7 | GLM 4.7 | 131K | $2.59 | $3.16 |
zai/glm-4.7-flash | GLM 4.7 Flash | 200K | $0.08 | $0.46 |
zai/glm-5 | GLM 5 | 202K | $1.15 | $3.68 |
zai/glm-5.1 | GLM 5.1 | 202K | $1.61 | $5.06 |
Pricing Notes
- All prices shown include UClaw's 15% infrastructure fee
- Context window sizes are in tokens (K = thousands, M = millions)
- Some models support prompt caching — repeated context is charged at a reduced cache read rate
- Prices may change as upstream providers adjust their rates
See the Pricing page for a full explanation of pay-as-you-go billing and the billing FAQ.