# Keystroke models

> Models available through Keystroke. Use a model ID below as the `model` string when building agents.

```ts
defineAgent({
  slug: "my-agent",
  model: "openai/gpt-5.6-luna", // any Model ID from this page
});
```

## Model selection guide

Any catalog ID works as `model`. These are current options grouped by capability. At the same capability level, OpenAI and Grok are usually cheaper than the Anthropic peer. Approximate list prices are USD per 1M tokens (input / output); use the tables below for live rates.

| Capability | Model IDs | Approx. $/1M in/out | Notes |
| --- | --- | --- | --- |
| Everyday | `openai/gpt-5.6-luna`, `xai/grok-4.5`, `anthropic/claude-sonnet-5` | Luna ~$1/$6 · Grok ~$2/$6 · Sonnet 5 ~$2/$10 | Routine agents, tools, high volume |
| Stronger | `openai/gpt-5.6-terra`, `anthropic/claude-opus-4.8` | Terra ~$2.50/$15 · Opus 4.8 ~$5/$25 | More capability on harder everyday work |
| Hardest | `openai/gpt-5.6-sol`, `anthropic/claude-fable-5` | Sol ~$5/$30 · Fable 5 ~$10/$50 | Difficult reasoning and long-horizon tasks |
| Budget | `deepseek/deepseek-v4-flash` | ~$0.14/$0.28 | Simple / one-off calls |
| Alt coding | `zai/glm-5.2` | ~$1.40/$4.40 | Coding and long-context work |

Model ids change as providers ship new generations — check this page when picking an id. Last reviewed July 2026.

- **Cloud**: hosted workers route through the platform LLM proxy automatically; no provider keys needed.
- **Local / self-hosted**: set `AI_GATEWAY_API_KEY` to use every model below, or set per-vendor keys (`ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, `GEMINI_API_KEY`, ...) for direct access to models in the pi-ai registry.
- **Copy Model IDs exactly** — use the string in the Model ID column as-is. Do not infer IDs from display names or normalize version numbers (e.g. use `openai/gpt-5.6-luna`, not `openai/gpt-5-6-luna`).
- Prices are usage rates in USD per 1M tokens. Tiered, cache, and web-search pricing are omitted here.

241 models, last updated 2026-07-12.

## Language models

### alibaba

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `alibaba/qwen-3-14b` | Qwen3-14B | 41K | $0.12 | $0.24 | reasoning, tool-use |
| `alibaba/qwen-3-235b` | Qwen3 235B A22B | 262K | $0.22 | $0.88 | tool-use, reasoning |
| `alibaba/qwen-3-30b` | Qwen3-30B-A3B | 41K | $0.12 | $0.50 | reasoning, tool-use |
| `alibaba/qwen-3-32b` | Qwen 3 32B | 128K | $0.16 | $0.64 | reasoning, tool-use, implicit-caching |
| `alibaba/qwen-3.6-max-preview` | Qwen 3.6 Max Preview | 240K | $1.30 | $7.80 | reasoning, tool-use |
| `alibaba/qwen3-235b-a22b-thinking` | Qwen3 VL 235B A22B Thinking | 131K | $0.40 | $4.00 | vision, reasoning, tool-use, file-input |
| `alibaba/qwen3-coder` | Qwen3 Coder 480B A35B Instruct | 262K | $1.50 | $7.50 | tool-use, implicit-caching |
| `alibaba/qwen3-coder-30b-a3b` | Qwen 3 Coder 30B A3B Instruct | 262K | $0.15 | $0.60 | tool-use |
| `alibaba/qwen3-coder-next` | Qwen3 Coder Next | 256K | $0.50 | $1.20 | tool-use |
| `alibaba/qwen3-coder-plus` | Qwen3 Coder Plus | 1M | $1.00 | $5.00 | implicit-caching, tool-use |
| `alibaba/qwen3-max` | Qwen3 Max | 262K | $1.20 | $6.00 | tool-use, implicit-caching |
| `alibaba/qwen3-max-preview` | Qwen3 Max Preview | 262K | $1.20 | $6.00 | tool-use, implicit-caching |
| `alibaba/qwen3-max-thinking` | Qwen 3 Max Thinking | 256K | $1.20 | $6.00 | reasoning, tool-use |
| `alibaba/qwen3-next-80b-a3b-instruct` | Qwen3 Next 80B A3B Instruct | 131K | $0.15 | $1.20 | tool-use |
| `alibaba/qwen3-next-80b-a3b-thinking` | Qwen3 Next 80B A3B Thinking | 131K | $0.15 | $1.20 | reasoning, tool-use |
| `alibaba/qwen3-vl-235b-a22b-instruct` | Qwen3 VL 235B A22B Instruct | 131K | $0.40 | $1.60 | tool-use, vision, implicit-caching |
| `alibaba/qwen3-vl-instruct` | Qwen3 VL 235B A22B Instruct | 131K | $0.40 | $1.60 | tool-use, vision, implicit-caching |
| `alibaba/qwen3-vl-thinking` | Qwen3 VL 235B A22B Thinking | 131K | $0.40 | $4.00 | vision, reasoning, tool-use, file-input |
| `alibaba/qwen3.5-flash` | Qwen 3.5 Flash | 1M | $0.10 | $0.40 | vision, file-input, reasoning, tool-use |
| `alibaba/qwen3.5-plus` | Qwen 3.5 Plus | 1M | $0.40 | $2.40 | vision, file-input, reasoning, tool-use |
| `alibaba/qwen3.6-27b` | Qwen 3.6 27B | 256K | $0.60 | $3.60 | reasoning, tool-use, file-input, vision |
| `alibaba/qwen3.6-plus` | Qwen 3.6 Plus | 1M | $0.50 | $3.00 | reasoning, tool-use, vision, file-input |
| `alibaba/qwen3.7-max` | Qwen 3.7 Max | 991K | $1.25 | $3.75 | implicit-caching, reasoning, tool-use |
| `alibaba/qwen3.7-plus` | Qwen 3.7 Plus | 1M | $0.40 | $1.60 | reasoning, tool-use, implicit-caching, file-input, vision |

### amazon

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `amazon/nova-2-lite` | Nova 2 Lite | 1M | $0.30 | $2.50 | file-input, reasoning, tool-use, vision |
| `amazon/nova-lite` | Nova Lite | 300K | $0.06 | $0.24 | file-input, tool-use, vision |
| `amazon/nova-micro` | Nova Micro | 128K | $0.04 | $0.14 | tool-use |
| `amazon/nova-pro` | Nova Pro | 300K | $0.80 | $3.20 | file-input, tool-use, vision |

### anthropic

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `anthropic/claude-3-haiku` | Claude 3 Haiku | 200K | $0.25 | $1.25 | tool-use, vision, explicit-caching |
| `anthropic/claude-3.5-haiku` | Claude 3.5 Haiku | 200K | $0.80 | $4.00 | file-input, tool-use, vision, explicit-caching |
| `anthropic/claude-fable-5` | Claude Fable 5 | 1M | $10.00 | $50.00 | reasoning, tool-use, explicit-caching, file-input, vision |
| `anthropic/claude-haiku-4.5` | Claude Haiku 4.5 | 200K | $1.00 | $5.00 | explicit-caching, file-input, reasoning, tool-use, vision, web-search |
| `anthropic/claude-opus-4` | Claude Opus 4 | 200K | $15.00 | $75.00 | file-input, reasoning, tool-use, vision, explicit-caching |
| `anthropic/claude-opus-4.1` | Claude Opus 4.1 | 200K | $15.00 | $75.00 | file-input, reasoning, tool-use, vision, explicit-caching |
| `anthropic/claude-opus-4.5` | Claude Opus 4.5 | 200K | $5.00 | $25.00 | explicit-caching, file-input, reasoning, tool-use, vision, web-search |
| `anthropic/claude-opus-4.6` | Claude Opus 4.6 | 1M | $5.00 | $25.00 | tool-use, reasoning, vision, file-input, explicit-caching, web-search |
| `anthropic/claude-opus-4.7` | Claude Opus 4.7 | 1M | $5.00 | $25.00 | tool-use, reasoning, vision, file-input, explicit-caching, web-search |
| `anthropic/claude-opus-4.8` | Claude Opus 4.8 | 1M | $5.00 | $25.00 | tool-use, reasoning, vision, file-input, explicit-caching, web-search |
| `anthropic/claude-sonnet-4` | Claude Sonnet 4 | 1M | $3.00 | $15.00 | file-input, reasoning, tool-use, vision, explicit-caching |
| `anthropic/claude-sonnet-4.5` | Claude Sonnet 4.5 | 1M | $3.00 | $15.00 | explicit-caching, file-input, reasoning, tool-use, vision, web-search |
| `anthropic/claude-sonnet-4.6` | Claude Sonnet 4.6 | 1M | $3.00 | $15.00 | file-input, reasoning, tool-use, vision, explicit-caching, web-search |
| `anthropic/claude-sonnet-5` | Claude Sonnet 5 | 1M | $2.00 | $10.00 | reasoning, tool-use, explicit-caching, file-input, vision, web-search |

### arcee-ai

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `arcee-ai/trinity-large-preview` | Trinity Large Preview | 131K | $0.25 | $1.00 | tool-use |
| `arcee-ai/trinity-large-thinking` | Trinity Large Thinking | 262K | $0.25 | $0.90 | reasoning, tool-use |
| `arcee-ai/trinity-mini` | Trinity Mini | 131K | $0.04 | $0.15 | tool-use |

### bytedance

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `bytedance/seed-1.6` | Seed 1.6 | 256K | $0.25 | $2.00 | reasoning, tool-use, vision |
| `bytedance/seed-1.8` | Bytedance Seed 1.8 | 256K | $0.25 | $2.00 | reasoning, tool-use, vision |

### cohere

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `cohere/command-a` | Command A | 256K | $2.50 | $10.00 | tool-use |

### deepseek

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `deepseek/deepseek-r1` | DeepSeek-R1 | 128K | $1.35 | $5.40 | reasoning, tool-use, implicit-caching |
| `deepseek/deepseek-v3` | DeepSeek V3 0324 | 164K | $0.27 | $1.12 | tool-use |
| `deepseek/deepseek-v3.1` | DeepSeek V3.1 | 128K | $0.60 | $1.70 | implicit-caching, reasoning, tool-use |
| `deepseek/deepseek-v3.1-terminus` | DeepSeek V3.1 Terminus | 131K | $0.27 | $1.00 | implicit-caching, reasoning, tool-use |
| `deepseek/deepseek-v3.2` | DeepSeek V3.2 | 128K | $0.28 | $0.42 | tool-use, implicit-caching |
| `deepseek/deepseek-v3.2-thinking` | DeepSeek V3.2 Thinking | 128K | $0.62 | $1.85 | tool-use, implicit-caching, reasoning |
| `deepseek/deepseek-v4-flash` | DeepSeek V4 Flash | 1M | $0.14 | $0.28 | reasoning, tool-use, implicit-caching |
| `deepseek/deepseek-v4-pro` | DeepSeek V4 Pro | 1M | $0.43 | $0.87 | reasoning, tool-use, implicit-caching |

### google

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `google/gemini-2.5-flash` | Gemini 2.5 Flash | 1M | $0.30 | $2.50 | file-input, reasoning, tool-use, vision, web-search, implicit-caching |
| `google/gemini-2.5-flash-image` | Nano Banana (Gemini 2.5 Flash Image) | 33K | $0.30 | $2.50 | image-generation, web-search |
| `google/gemini-2.5-flash-lite` | Gemini 2.5 Flash Lite | 1.0M | $0.10 | $0.40 | file-input, reasoning, tool-use, vision, web-search, implicit-caching |
| `google/gemini-2.5-pro` | Gemini 2.5 Pro | 1.0M | $1.25 | $10.00 | file-input, reasoning, tool-use, vision, web-search, implicit-caching |
| `google/gemini-3-flash` | Gemini 3 Flash | 1M | $0.50 | $3.00 | reasoning, file-input, vision, tool-use, web-search, implicit-caching |
| `google/gemini-3-pro-image` | Nano Banana Pro (Gemini 3 Pro Image) | 66K | $2.00 | $12.00 | image-generation, web-search, implicit-caching |
| `google/gemini-3-pro-preview` | Gemini 3 Pro Preview | 1M | $2.00 | $12.00 | file-input, tool-use, reasoning, vision, web-search, implicit-caching |
| `google/gemini-3.1-flash-image` | Gemini 3.1 Flash Image (Nano Banana 2) | 131K | $0.50 | $3.00 | image-generation, implicit-caching, reasoning, vision, web-search |
| `google/gemini-3.1-flash-image-preview` | Gemini 3.1 Flash Image Preview (Nano Banana 2) | 131K | $0.50 | $3.00 | image-generation, implicit-caching, reasoning, vision, web-search |
| `google/gemini-3.1-flash-lite` | Gemini 3.1 Flash Lite | 1M | $0.25 | $1.50 | reasoning, tool-use, implicit-caching, file-input, vision, web-search |
| `google/gemini-3.1-flash-lite-image` | Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) | 66K | $0.25 | $1.50 | image-generation, implicit-caching, reasoning, vision, web-search |
| `google/gemini-3.1-flash-lite-preview` | Gemini 3.1 Flash Lite Preview | 1M | $0.25 | $1.50 | reasoning, tool-use, implicit-caching, file-input, vision, web-search |
| `google/gemini-3.1-pro-preview` | Gemini 3.1 Pro Preview | 1M | $2.00 | $12.00 | file-input, tool-use, reasoning, vision, web-search, implicit-caching |
| `google/gemini-3.5-flash` | Gemini 3.5 Flash | 1M | $1.50 | $9.00 | reasoning, file-input, vision, tool-use, web-search, implicit-caching |
| `google/gemini-omni-flash-preview` | Gemini Omni Flash Preview | 1M | $1.50 | $9.00 | file-input, reasoning, vision, video-generation |
| `google/gemma-4-26b-a4b-it` | Gemma 4 26B A4B IT | 262K | $0.15 | $0.60 | file-input, reasoning, tool-use, vision, implicit-caching |
| `google/gemma-4-31b-it` | Gemma 4 31B IT | 262K | $0.14 | $0.40 | file-input, reasoning, tool-use, vision |

### inception

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `inception/mercury-2` | Mercury 2 | 128K | $0.25 | $0.75 | reasoning, tool-use |
| `inception/mercury-coder-small` | Mercury Coder Small Beta | 32K | $0.25 | $1.00 | tool-use |

### interfaze

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `interfaze/interfaze-beta` | Interfaze Beta | 1M | $1.50 | $3.50 | file-input, reasoning, tool-use, vision |

### kwaipilot

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `kwaipilot/kat-coder-air-v2.5` | Kat Coder Air V2.5 | 256K | $0.15 | $0.60 | reasoning, tool-use, implicit-caching |
| `kwaipilot/kat-coder-pro-v1` | KAT-Coder-Pro V1 | 256K | $0.30 | $1.20 | tool-use |
| `kwaipilot/kat-coder-pro-v2` | Kat Coder Pro V2 | 256K | $0.30 | $1.20 | tool-use, reasoning, implicit-caching |
| `kwaipilot/kat-coder-pro-v2.5` | Kat Coder Pro V2.5 | 256K | $0.74 | $2.96 | reasoning, tool-use, implicit-caching |

### meituan

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `meituan/longcat-flash-chat` | LongCat Flash Chat | 128K | - | - | tool-use |
| `meituan/longcat-flash-thinking-2601` | LongCat Flash Thinking 2601 | 33K | - | - | reasoning, tool-use |

### meta

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `meta/llama-3.1-70b` | Llama 3.1 70B Instruct | 128K | $0.72 | $0.72 | tool-use |
| `meta/llama-3.1-8b` | Llama 3.1 8B Instruct | 128K | $0.22 | $0.22 | tool-use, implicit-caching |
| `meta/llama-3.2-11b` | Llama 3.2 11B Vision Instruct | 128K | $0.16 | $0.16 | tool-use, vision |
| `meta/llama-3.2-1b` | Llama 3.2 1B Instruct | 128K | $0.10 | $0.10 | - |
| `meta/llama-3.2-3b` | Llama 3.2 3B Instruct | 128K | $0.15 | $0.15 | - |
| `meta/llama-3.2-90b` | Llama 3.2 90B Vision Instruct | 128K | $0.72 | $0.72 | tool-use, vision |
| `meta/llama-3.3-70b` | Llama 3.3 70B Instruct | 128K | $0.72 | $0.72 | tool-use |
| `meta/llama-4-maverick` | Llama 4 Maverick 17B Instruct | 128K | $0.24 | $0.97 | tool-use, vision |
| `meta/llama-4-scout` | Llama 4 Scout 17B Instruct | 128K | $0.17 | $0.66 | tool-use, vision |
| `meta/muse-spark-1.1` | Muse Spark 1.1 | 1.0M | $1.25 | $4.25 | reasoning, tool-use, implicit-caching, file-input, vision |

### minimax

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `minimax/minimax-m2` | MiniMax M2 | 205K | $0.30 | $1.20 | reasoning, tool-use |
| `minimax/minimax-m2.1` | MiniMax M2.1 | 205K | $0.30 | $1.20 | reasoning, tool-use, implicit-caching |
| `minimax/minimax-m2.1-lightning` | MiniMax M2.1 Lightning | 205K | $0.30 | $2.40 | reasoning, tool-use, implicit-caching |
| `minimax/minimax-m2.5` | MiniMax M2.5 | 205K | $0.30 | $1.20 | reasoning, tool-use, implicit-caching |
| `minimax/minimax-m2.5-highspeed` | MiniMax M2.5 High Speed | 205K | $0.60 | $2.40 | reasoning, tool-use, implicit-caching |
| `minimax/minimax-m2.7` | MiniMax M2.7 | 205K | $0.30 | $1.20 | reasoning, tool-use, implicit-caching |
| `minimax/minimax-m2.7-highspeed` | MiniMax M2.7 High Speed | 205K | $0.60 | $2.40 | reasoning, tool-use, implicit-caching |
| `minimax/minimax-m3` | MiniMax M3 | 1M | $0.30 | $1.20 | reasoning, tool-use, vision, file-input, implicit-caching |

### mistral

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `mistral/codestral` | Mistral Codestral | 128K | $0.30 | $0.90 | tool-use |
| `mistral/devstral-2` | Devstral 2 | 256K | $0.40 | $2.00 | tool-use |
| `mistral/devstral-small` | Devstral Small 1.1 | 128K | $0.10 | $0.30 | tool-use |
| `mistral/devstral-small-2` | Devstral Small 2 | 256K | $0.10 | $0.30 | tool-use, vision |
| `mistral/magistral-medium` | Magistral Medium 2509 | 128K | $2.00 | $5.00 | reasoning, tool-use, vision |
| `mistral/magistral-small` | Magistral Small 2509 | 128K | $0.50 | $1.50 | reasoning, tool-use, vision |
| `mistral/ministral-14b` | Ministral 14B | 256K | $0.20 | $0.20 | file-input, tool-use, vision |
| `mistral/ministral-3b` | Ministral 3B | 128K | $0.10 | $0.10 | tool-use |
| `mistral/ministral-8b` | Ministral 8B | 128K | $0.15 | $0.15 | tool-use |
| `mistral/mistral-large-3` | Mistral Large 3 | 256K | $0.50 | $1.50 | tool-use, vision |
| `mistral/mistral-medium` | Mistral Medium 3.1 | 128K | $0.40 | $2.00 | tool-use, vision |
| `mistral/mistral-medium-3.5` | Mistral Medium Latest | 256K | $1.50 | $7.50 | reasoning, tool-use, vision |
| `mistral/mistral-nemo` | Mistral Nemo 12B | 128K | $0.15 | $0.15 | tool-use |
| `mistral/mistral-small` | Mistral Small | 32K | $0.10 | $0.30 | tool-use, vision |
| `mistral/pixtral-12b` | Pixtral 12B 2409 | 128K | $0.15 | $0.15 | tool-use, vision |
| `mistral/pixtral-large` | Pixtral Large | 128K | $2.00 | $6.00 | tool-use, vision |

### moonshotai

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `moonshotai/kimi-k2` | Kimi K2 Instruct | 131K | $0.57 | $2.30 | tool-use |
| `moonshotai/kimi-k2-thinking` | Kimi K2 Thinking | 216K | $0.47 | $2.00 | reasoning, tool-use, implicit-caching |
| `moonshotai/kimi-k2.5` | Kimi K2.5 | 262K | $0.60 | $3.00 | reasoning, vision, tool-use, implicit-caching |
| `moonshotai/kimi-k2.6` | Kimi K2.6 | 262K | $0.95 | $4.00 | implicit-caching, reasoning, tool-use, vision |
| `moonshotai/kimi-k2.7-code` | Kimi K2.7 Code | 256K | $0.95 | $4.00 | reasoning, tool-use, implicit-caching, file-input, vision |
| `moonshotai/kimi-k2.7-code-highspeed` | Kimi K2.7 Code High Speed | 262K | $1.90 | $8.00 | reasoning, tool-use, implicit-caching, file-input, vision |

### morph

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `morph/morph-v3-fast` | Morph V3 Fast | 82K | $0.80 | $1.20 | - |
| `morph/morph-v3-large` | Morph V3 Large | 82K | $0.90 | $1.90 | - |

### nvidia

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `nvidia/nemotron-3-nano-30b-a3b` | Nemotron 3 Nano 30B A3B | 262K | $0.05 | $0.24 | reasoning, tool-use |
| `nvidia/nemotron-3-super-120b-a12b` | NVIDIA Nemotron 3 Super 120B A12B | 256K | $0.15 | $0.65 | reasoning, tool-use |
| `nvidia/nemotron-3-ultra-550b-a55b` | Nemotron 3 Ultra | 1M | $0.60 | $2.40 | reasoning, tool-use, implicit-caching |
| `nvidia/nemotron-nano-12b-v2-vl` | Nvidia Nemotron Nano 12B V2 VL | 131K | $0.20 | $0.60 | vision, reasoning, tool-use |
| `nvidia/nemotron-nano-9b-v2` | Nvidia Nemotron Nano 9B V2 | 131K | $0.06 | $0.23 | reasoning, tool-use |

### openai

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `openai/gpt-3.5-turbo` | GPT-3.5 Turbo | 16K | $0.50 | $1.50 | tool-use |
| `openai/gpt-3.5-turbo-instruct` | GPT-3.5 Turbo Instruct | 8K | $1.50 | $2.00 | - |
| `openai/gpt-4-turbo` | GPT-4 Turbo | 128K | $10.00 | $30.00 | tool-use, vision |
| `openai/gpt-4.1` | GPT-4.1 | 1.0M | $2.00 | $8.00 | file-input, implicit-caching, tool-use, vision, web-search |
| `openai/gpt-4.1-mini` | GPT-4.1 mini | 1.0M | $0.40 | $1.60 | file-input, implicit-caching, tool-use, vision, web-search |
| `openai/gpt-4.1-nano` | GPT-4.1 nano | 1.0M | $0.10 | $0.40 | file-input, implicit-caching, tool-use, vision, web-search |
| `openai/gpt-4o` | GPT-4o | 128K | $2.50 | $10.00 | file-input, implicit-caching, tool-use, vision, web-search |
| `openai/gpt-4o-mini` | GPT-4o mini | 128K | $0.15 | $0.60 | file-input, implicit-caching, tool-use, vision, web-search |
| `openai/gpt-4o-mini-search-preview` | GPT 4o Mini Search Preview | 128K | $0.15 | $0.60 | web-search |
| `openai/gpt-5` | GPT-5 | 400K | $1.25 | $10.00 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/gpt-5-chat` | GPT 5 Chat | 128K | $1.25 | $10.00 | file-input, implicit-caching, tool-use, vision, web-search |
| `openai/gpt-5-codex` | GPT-5-Codex | 400K | $1.25 | $10.00 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/gpt-5-mini` | GPT-5 mini | 400K | $0.25 | $2.00 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/gpt-5-nano` | GPT-5 nano | 400K | $0.05 | $0.40 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/gpt-5-pro` | GPT-5 pro | 400K | $15.00 | $120.00 | file-input, reasoning, tool-use, vision, web-search |
| `openai/gpt-5.1-codex` | GPT-5.1-Codex | 400K | $1.25 | $10.00 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/gpt-5.1-codex-max` | GPT 5.1 Codex Max | 400K | $1.25 | $10.00 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/gpt-5.1-codex-mini` | GPT 5.1 Codex Mini | 400K | $0.25 | $2.00 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/gpt-5.1-instant` | GPT-5.1 Instant | 128K | $1.25 | $10.00 | file-input, implicit-caching, tool-use, vision, web-search |
| `openai/gpt-5.1-thinking` | GPT 5.1 Thinking | 400K | $1.25 | $10.00 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/gpt-5.2` | GPT 5.2 | 400K | $1.75 | $14.00 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/gpt-5.2-chat` | GPT 5.2 Chat | 128K | $1.75 | $14.00 | file-input, implicit-caching, tool-use, vision, web-search |
| `openai/gpt-5.2-codex` | GPT 5.2 Codex | 400K | $1.75 | $14.00 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/gpt-5.2-pro` | GPT 5.2 | 400K | $21.00 | $168.00 | tool-use, vision, reasoning, file-input, web-search |
| `openai/gpt-5.3-chat` | GPT-5.3 Chat | 128K | $1.75 | $14.00 | file-input, implicit-caching, tool-use, vision, web-search |
| `openai/gpt-5.3-codex` | GPT 5.3 Codex | 400K | $1.75 | $14.00 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/gpt-5.4` | GPT 5.4 | 1.1M | $2.50 | $15.00 | file-input, implicit-caching, reasoning, tool-use, vision, web-search, websocket-realtime |
| `openai/gpt-5.4-mini` | GPT 5.4 Mini | 400K | $0.75 | $4.50 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/gpt-5.4-nano` | GPT 5.4 Nano | 400K | $0.20 | $1.25 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/gpt-5.4-pro` | GPT 5.4 Pro | 1.1M | $30.00 | $180.00 | file-input, reasoning, tool-use, vision, web-search |
| `openai/gpt-5.5` | GPT 5.5 | 1M | $5.00 | $30.00 | file-input, implicit-caching, reasoning, tool-use, vision, web-search, websocket-realtime |
| `openai/gpt-5.5-pro` | GPT 5.5 Pro | 1M | $30.00 | $180.00 | reasoning, tool-use, file-input, web-search, vision |
| `openai/gpt-5.6-luna` | GPT 5.6 Luna | 1.1M | $1.00 | $6.00 | reasoning, file-input, tool-use, vision, implicit-caching, web-search |
| `openai/gpt-5.6-sol` | GPT 5.6 Sol | 1.1M | $5.00 | $30.00 | reasoning, tool-use, implicit-caching, file-input, vision, web-search |
| `openai/gpt-5.6-terra` | GPT 5.6 Terra | 1.1M | $2.50 | $15.00 | reasoning, web-search, file-input, tool-use, vision, implicit-caching |
| `openai/gpt-oss-120b` | GPT OSS 120B | 131K | $0.10 | $0.50 | reasoning, tool-use, implicit-caching |
| `openai/gpt-oss-20b` | GPT OSS 20B | 131K | $0.05 | $0.20 | reasoning, tool-use, implicit-caching |
| `openai/gpt-oss-safeguard-20b` | GPT OSS Safeguard 20B | 131K | $0.07 | $0.30 | implicit-caching, reasoning, tool-use |
| `openai/o1` | o1 | 200K | $15.00 | $60.00 | file-input, reasoning, tool-use, vision, implicit-caching |
| `openai/o3` | o3 | 200K | $2.00 | $8.00 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/o3-deep-research` | o3-deep-research | 200K | $10.00 | $40.00 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |
| `openai/o3-mini` | o3-mini | 200K | $1.10 | $4.40 | implicit-caching, reasoning, tool-use |
| `openai/o3-pro` | o3 Pro | 200K | $20.00 | $80.00 | reasoning, vision, file-input, tool-use, web-search |
| `openai/o4-mini` | o4-mini | 200K | $1.10 | $4.40 | file-input, implicit-caching, reasoning, tool-use, vision, web-search |

### perplexity

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `perplexity/sonar` | Sonar | 127K | - | - | vision, web-search |
| `perplexity/sonar-pro` | Sonar Pro | 200K | - | - | vision, web-search |
| `perplexity/sonar-reasoning-pro` | Sonar Reasoning Pro | 127K | - | - | reasoning, web-search |

### sakana

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `sakana/fugu-ultra` | Fugu Ultra | 1M | $5.00 | $30.00 | vision, tool-use, reasoning |

### stepfun

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `stepfun/step-3.5-flash` | StepFun 3.5 Flash | 262K | $0.09 | $0.30 | reasoning, tool-use, implicit-caching |
| `stepfun/step-3.7-flash` | Step 3.7 Flash | 256K | $0.20 | $1.15 | implicit-caching, reasoning, tool-use, vision |

### xai

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `xai/grok-4.1-fast-non-reasoning` | Grok 4.1 Fast Non-Reasoning | 1M | $0.20 | $0.50 | tool-use, file-input, vision, implicit-caching |
| `xai/grok-4.1-fast-reasoning` | Grok 4.1 Fast Reasoning | 1M | $0.20 | $0.50 | reasoning, file-input, vision, tool-use, implicit-caching |
| `xai/grok-4.20-multi-agent` | Grok 4.20 Multi-Agent | 2M | $1.25 | $2.50 | reasoning, tool-use, implicit-caching, vision, file-input, web-search |
| `xai/grok-4.20-multi-agent-beta` | Grok 4.20 Multi Agent Beta | 2M | $1.25 | $2.50 | reasoning, tool-use, implicit-caching, vision, file-input, web-search |
| `xai/grok-4.20-non-reasoning` | Grok 4.20 Non-Reasoning | 2M | $1.25 | $2.50 | tool-use, implicit-caching, file-input, vision, web-search |
| `xai/grok-4.20-non-reasoning-beta` | Grok 4.20 Beta Non-Reasoning | 2M | $1.25 | $2.50 | tool-use, implicit-caching, vision, file-input, web-search |
| `xai/grok-4.20-reasoning` | Grok 4.20 Reasoning | 2M | $1.25 | $2.50 | reasoning, tool-use, implicit-caching, vision, file-input, web-search |
| `xai/grok-4.20-reasoning-beta` | Grok 4.20 Beta Reasoning | 2M | $1.25 | $2.50 | reasoning, tool-use, vision, file-input, implicit-caching, web-search |
| `xai/grok-4.3` | Grok 4.3 | 1M | $1.25 | $2.50 | reasoning, tool-use, implicit-caching, file-input, vision, web-search |
| `xai/grok-4.5` | Grok 4.5 | 500K | $2.00 | $6.00 | reasoning, tool-use, implicit-caching, file-input, vision, web-search |
| `xai/grok-build-0.1` | Grok Build 0.1 | 256K | $1.00 | $2.00 | reasoning, implicit-caching, vision, tool-use, web-search |

### xiaomi

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `xiaomi/mimo-v2-flash` | MiMo V2 Flash | 262K | $0.10 | $0.30 | implicit-caching, reasoning, tool-use |
| `xiaomi/mimo-v2-pro` | MiMo V2 Pro | 1M | $1.00 | $3.00 | implicit-caching, reasoning, tool-use |
| `xiaomi/mimo-v2.5` | MiMo M2.5 | 1.1M | $0.14 | $0.28 | reasoning, tool-use, implicit-caching, file-input, vision |
| `xiaomi/mimo-v2.5-pro` | MiMo V2.5 Pro | 1.1M | $0.43 | $0.87 | reasoning, tool-use, file-input, implicit-caching |

### zai

| Model ID | Name | Context | Input ($/1M) | Output ($/1M) | Capabilities |
| --- | --- | --- | --- | --- | --- |
| `zai/glm-4.5` | GLM 4.5 | 128K | $0.60 | $2.20 | reasoning, tool-use, implicit-caching |
| `zai/glm-4.5-air` | GLM 4.5 Air | 128K | $0.20 | $1.10 | reasoning, tool-use, implicit-caching |
| `zai/glm-4.5v` | GLM 4.5V | 66K | $0.60 | $1.80 | implicit-caching, reasoning, tool-use, vision |
| `zai/glm-4.6` | GLM 4.6 | 200K | $0.60 | $2.20 | implicit-caching, reasoning, tool-use |
| `zai/glm-4.6v` | GLM-4.6V | 128K | $0.30 | $0.90 | vision, file-input, reasoning, tool-use, implicit-caching |
| `zai/glm-4.6v-flash` | GLM-4.6V-Flash | 128K | - | - | vision, reasoning, file-input, tool-use, implicit-caching |
| `zai/glm-4.7` | GLM 4.7 | 200K | $0.60 | $2.20 | reasoning, tool-use, implicit-caching |
| `zai/glm-4.7-flash` | GLM 4.7 Flash | 200K | $0.07 | $0.40 | reasoning, tool-use, implicit-caching |
| `zai/glm-4.7-flashx` | GLM 4.7 FlashX | 200K | $0.06 | $0.40 | reasoning, tool-use, implicit-caching |
| `zai/glm-5` | GLM 5 | 203K | $0.95 | $3.15 | reasoning, tool-use, implicit-caching |
| `zai/glm-5-turbo` | GLM 5 Turbo | 203K | $1.20 | $4.00 | reasoning, tool-use, implicit-caching |
| `zai/glm-5.1` | GLM 5.1 | 202K | $1.30 | $4.30 | implicit-caching, reasoning, tool-use |
| `zai/glm-5.2` | GLM 5.2 | 1.0M | $1.40 | $4.40 | reasoning, tool-use, implicit-caching |
| `zai/glm-5.2-fast` | GLM 5.2 Fast | 1M | $2.10 | $6.60 | reasoning, tool-use, implicit-caching |
| `zai/glm-5v-turbo` | GLM 5V Turbo | 200K | $1.20 | $4.00 | reasoning, tool-use, implicit-caching, vision, file-input |

## Image models

Image pricing is usage-based and is not listed here.

### bfl

| Model ID | Name | Capabilities |
| --- | --- | --- |
| `bfl/flux-2-flex` | FLUX.2 [flex] | image-generation |
| `bfl/flux-2-klein-4b` | FLUX.2 [klein] 4B | image-generation |
| `bfl/flux-2-klein-9b` | FLUX.2 [klein] 9B | image-generation |
| `bfl/flux-2-max` | FLUX.2 [max] | image-generation |
| `bfl/flux-2-pro` | FLUX.2 [pro] | image-generation |
| `bfl/flux-kontext-max` | FLUX.1 Kontext Max | image-generation |
| `bfl/flux-kontext-pro` | FLUX.1 Kontext Pro | image-generation |
| `bfl/flux-pro-1.0-fill` | FLUX.1 Fill [pro] | image-generation |
| `bfl/flux-pro-1.1` | FLUX1.1 [pro] | image-generation |
| `bfl/flux-pro-1.1-ultra` | FLUX1.1 [pro] Ultra | image-generation |

### bytedance

| Model ID | Name | Capabilities |
| --- | --- | --- |
| `bytedance/seedream-4.0` | Seedream 4.0 | image-generation |
| `bytedance/seedream-4.5` | Seedream 4.5 | image-generation |
| `bytedance/seedream-5.0-lite` | Seedream 5.0 Lite | image-generation |
| `bytedance/seedream-5.0-pro` | Seedream 5.0 Pro | image-generation |

### google

| Model ID | Name | Capabilities |
| --- | --- | --- |
| `google/imagen-4.0-fast-generate-001` | Imagen 4 Fast | image-generation |
| `google/imagen-4.0-generate-001` | Imagen 4 | image-generation |
| `google/imagen-4.0-ultra-generate-001` | Imagen 4 Ultra | image-generation |

### openai

| Model ID | Name | Capabilities |
| --- | --- | --- |
| `openai/gpt-image-1` | GPT Image 1 | image-generation, implicit-caching |
| `openai/gpt-image-1-mini` | GPT Image 1 Mini | image-generation, implicit-caching |
| `openai/gpt-image-1.5` | GPT Image 1.5 | image-generation, implicit-caching |
| `openai/gpt-image-2` | GPT Image 2 | image-generation, implicit-caching |

### prodia

| Model ID | Name | Capabilities |
| --- | --- | --- |
| `prodia/flux-fast-schnell` | Flux Schnell | image-generation |

### quiverai

| Model ID | Name | Capabilities |
| --- | --- | --- |
| `quiverai/arrow-1.1` | Arrow 1.1 | image-generation |

### recraft

| Model ID | Name | Capabilities |
| --- | --- | --- |
| `recraft/recraft-v2` | Recraft V2 | image-generation |
| `recraft/recraft-v3` | Recraft V3 | image-generation |
| `recraft/recraft-v4` | Recraft V4 | image-generation |
| `recraft/recraft-v4-pro` | Recraft V4 Pro | image-generation |
| `recraft/recraft-v4.1` | Recraft V4.1 | image-generation |
| `recraft/recraft-v4.1-pro` | Recraft V4.1 Pro | image-generation |
| `recraft/recraft-v4.1-utility` | Recraft V4.1 Utility | image-generation |
| `recraft/recraft-v4.1-utility-pro` | Recraft V4.1 Utility Pro | image-generation |

### xai

| Model ID | Name | Capabilities |
| --- | --- | --- |
| `xai/grok-imagine-image` | Grok Imagine Image | image-generation |