1---
2title: AI Models and Pricing - Zed
3description: AI models available via Zed Pro including Claude, GPT-5, Gemini, and Grok. Pricing, context windows, and tool call support.
4---
5
6# Models
7
8Zed's plans offer hosted versions of major LLMs with higher rate limits than direct API access. Model availability is updated regularly. To use your own API keys instead, see [LLM Providers](./llm-providers.md). For general setup, see [Configuration](./configuration.md).
9
10| Model | Provider | Token Type | Provider Price per 1M tokens | Zed Price per 1M tokens |
11| ---------------------- | --------- | ------------------- | ---------------------------- | ----------------------- |
12| Claude Opus 4.5 | Anthropic | Input | $5.00 | $5.50 |
13| | Anthropic | Output | $25.00 | $27.50 |
14| | Anthropic | Input - Cache Write | $6.25 | $6.875 |
15| | Anthropic | Input - Cache Read | $0.50 | $0.55 |
16| Claude Opus 4.1 | Anthropic | Input | $15.00 | $16.50 |
17| | Anthropic | Output | $75.00 | $82.50 |
18| | Anthropic | Input - Cache Write | $18.75 | $20.625 |
19| | Anthropic | Input - Cache Read | $1.50 | $1.65 |
20| Claude Sonnet 4.5 | Anthropic | Input | $3.00 | $3.30 |
21| | Anthropic | Output | $15.00 | $16.50 |
22| | Anthropic | Input - Cache Write | $3.75 | $4.125 |
23| | Anthropic | Input - Cache Read | $0.30 | $0.33 |
24| Claude Sonnet 4 | Anthropic | Input | $3.00 | $3.30 |
25| | Anthropic | Output | $15.00 | $16.50 |
26| | Anthropic | Input - Cache Write | $3.75 | $4.125 |
27| | Anthropic | Input - Cache Read | $0.30 | $0.33 |
28| Claude Sonnet 3.7 | Anthropic | Input | $3.00 | $3.30 |
29| | Anthropic | Output | $15.00 | $16.50 |
30| | Anthropic | Input - Cache Write | $3.75 | $4.125 |
31| | Anthropic | Input - Cache Read | $0.30 | $0.33 |
32| Claude Haiku 4.5 | Anthropic | Input | $1.00 | $1.10 |
33| | Anthropic | Output | $5.00 | $5.50 |
34| | Anthropic | Input - Cache Write | $1.25 | $1.375 |
35| | Anthropic | Input - Cache Read | $0.10 | $0.11 |
36| GPT-5 | OpenAI | Input | $1.25 | $1.375 |
37| | OpenAI | Output | $10.00 | $11.00 |
38| | OpenAI | Cached Input | $0.125 | $0.1375 |
39| GPT-5 mini | OpenAI | Input | $0.25 | $0.275 |
40| | OpenAI | Output | $2.00 | $2.20 |
41| | OpenAI | Cached Input | $0.025 | $0.0275 |
42| GPT-5 nano | OpenAI | Input | $0.05 | $0.055 |
43| | OpenAI | Output | $0.40 | $0.44 |
44| | OpenAI | Cached Input | $0.005 | $0.0055 |
45| Gemini 3.0 Pro | Google | Input | $2.00 | $2.20 |
46| | Google | Output | $12.00 | $13.20 |
47| Gemini 2.5 Pro | Google | Input | $1.25 | $1.375 |
48| | Google | Output | $10.00 | $11.00 |
49| Gemini 2.5 Flash | Google | Input | $0.30 | $0.33 |
50| | Google | Output | $2.50 | $2.75 |
51| Grok 4 | X.ai | Input | $3.00 | $3.30 |
52| | X.ai | Output | $15.00 | $16.5 |
53| | X.ai | Cached Input | $0.75 | $0.825 |
54| Grok 4 Fast | X.ai | Input | $0.20 | $0.22 |
55| | X.ai | Output | $0.50 | $0.55 |
56| | X.ai | Cached Input | $0.05 | $0.055 |
57| Grok 4 (Non-Reasoning) | X.ai | Input | $0.20 | $0.22 |
58| | X.ai | Output | $0.50 | $0.55 |
59| | X.ai | Cached Input | $0.05 | $0.055 |
60| Grok Code Fast 1 | X.ai | Input | $0.20 | $0.22 |
61| | X.ai | Output | $1.50 | $1.65 |
62| | X.ai | Cached Input | $0.02 | $0.022 |
63
64## Usage {#usage}
65
66Any usage of a Zed-hosted model will be billed at the Zed Price (rightmost column above). See [Plans and Usage](./plans-and-usage.md) for details on Zed's plans and limits for use of hosted models.
67
68> LLMs can enter unproductive loops that require user intervention. Monitor longer-running tasks and interrupt if needed.
69
70## Context Windows {#context-windows}
71
72A context window is the maximum span of text and code an LLM can consider at once, including both the input prompt and output generated by the model.
73
74| Model | Provider | Zed-Hosted Context Window |
75| ----------------- | --------- | ------------------------- |
76| Claude Opus 4.5 | Anthropic | 200k |
77| Claude Opus 4.1 | Anthropic | 200k |
78| Claude Sonnet 4 | Anthropic | 200k |
79| Claude Sonnet 3.7 | Anthropic | 200k |
80| Claude Haiku 4.5 | Anthropic | 200k |
81| GPT-5 | OpenAI | 400k |
82| GPT-5 mini | OpenAI | 400k |
83| GPT-5 nano | OpenAI | 400k |
84| Gemini 2.5 Pro | Google | 200k |
85| Gemini 2.5 Flash | Google | 200k |
86| Gemini 3.0 Pro | Google | 200k |
87
88> Context window limits for hosted Sonnet 4 and Gemini 2.5 Pro/Flash may increase in future releases.
89
90Each Agent thread and text thread in Zed maintains its own context window.
91The more prompts, attached files, and responses included in a session, the larger the context window grows.
92
93Start a new thread for each distinct task to keep context focused.
94
95## Tool Calls {#tool-calls}
96
97Models can use [tools](./tools.md) to interface with your code, search the web, and perform other useful functions.