models.md

  1---
  2title: AI Models and Pricing - Zed
  3description: AI models available via Zed Pro including Claude, GPT-5.4, Gemini 3.1 Pro, 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> **Note:** Claude Opus models and GPT-5.4 pro are not available on the [Student plan](./plans-and-usage.md#student).
 11
 12| Model                  | Provider  | Token Type          | Provider Price per 1M tokens | Zed Price per 1M tokens |
 13| ---------------------- | --------- | ------------------- | ---------------------------- | ----------------------- |
 14| Claude Opus 4.5        | Anthropic | Input               | $5.00                        | $5.50                   |
 15|                        | Anthropic | Output              | $25.00                       | $27.50                  |
 16|                        | Anthropic | Input - Cache Write | $6.25                        | $6.875                  |
 17|                        | Anthropic | Input - Cache Read  | $0.50                        | $0.55                   |
 18| Claude Opus 4.6        | Anthropic | Input               | $5.00                        | $5.50                   |
 19|                        | Anthropic | Output              | $25.00                       | $27.50                  |
 20|                        | Anthropic | Input - Cache Write | $6.25                        | $6.875                  |
 21|                        | Anthropic | Input - Cache Read  | $0.50                        | $0.55                   |
 22| Claude Sonnet 4.5      | Anthropic | Input               | $3.00                        | $3.30                   |
 23|                        | Anthropic | Output              | $15.00                       | $16.50                  |
 24|                        | Anthropic | Input - Cache Write | $3.75                        | $4.125                  |
 25|                        | Anthropic | Input - Cache Read  | $0.30                        | $0.33                   |
 26| Claude Sonnet 4.6      | Anthropic | Input               | $3.00                        | $3.30                   |
 27|                        | Anthropic | Output              | $15.00                       | $16.50                  |
 28|                        | Anthropic | Input - Cache Write | $3.75                        | $4.125                  |
 29|                        | Anthropic | Input - Cache Read  | $0.30                        | $0.33                   |
 30| Claude Haiku 4.5       | Anthropic | Input               | $1.00                        | $1.10                   |
 31|                        | Anthropic | Output              | $5.00                        | $5.50                   |
 32|                        | Anthropic | Input - Cache Write | $1.25                        | $1.375                  |
 33|                        | Anthropic | Input - Cache Read  | $0.10                        | $0.11                   |
 34| GPT-5.4 pro            | OpenAI    | Input               | $30.00                       | $33.00                  |
 35|                        | OpenAI    | Output              | $180.00                      | $198.00                 |
 36| GPT-5.4                | OpenAI    | Input               | $2.50                        | $2.75                   |
 37|                        | OpenAI    | Output              | $15.00                       | $16.50                  |
 38|                        | OpenAI    | Cached Input        | $0.025                       | $0.0275                 |
 39| GPT-5.3-Codex          | OpenAI    | Input               | $1.75                        | $1.925                  |
 40|                        | OpenAI    | Output              | $14.00                       | $15.40                  |
 41|                        | OpenAI    | Cached Input        | $0.175                       | $0.1925                 |
 42| GPT-5.2                | OpenAI    | Input               | $1.75                        | $1.925                  |
 43|                        | OpenAI    | Output              | $14.00                       | $15.40                  |
 44|                        | OpenAI    | Cached Input        | $0.175                       | $0.1925                 |
 45| GPT-5.2-Codex          | OpenAI    | Input               | $1.75                        | $1.925                  |
 46|                        | OpenAI    | Output              | $14.00                       | $15.40                  |
 47|                        | OpenAI    | Cached Input        | $0.175                       | $0.1925                 |
 48| GPT-5 mini             | OpenAI    | Input               | $0.25                        | $0.275                  |
 49|                        | OpenAI    | Output              | $2.00                        | $2.20                   |
 50|                        | OpenAI    | Cached Input        | $0.025                       | $0.0275                 |
 51| GPT-5 nano             | OpenAI    | Input               | $0.05                        | $0.055                  |
 52|                        | OpenAI    | Output              | $0.40                        | $0.44                   |
 53|                        | OpenAI    | Cached Input        | $0.005                       | $0.0055                 |
 54| Gemini 3.1 Pro         | Google    | Input               | $2.00                        | $2.20                   |
 55|                        | Google    | Output              | $12.00                       | $13.20                  |
 56| Gemini 3 Flash         | Google    | Input               | $0.50                        | $0.55                   |
 57|                        | Google    | Output              | $3.00                        | $3.30                   |
 58| Grok 4                 | X.ai      | Input               | $3.00                        | $3.30                   |
 59|                        | X.ai      | Output              | $15.00                       | $16.5                   |
 60|                        | X.ai      | Cached Input        | $0.75                        | $0.825                  |
 61| Grok 4 Fast            | X.ai      | Input               | $0.20                        | $0.22                   |
 62|                        | X.ai      | Output              | $0.50                        | $0.55                   |
 63|                        | X.ai      | Cached Input        | $0.05                        | $0.055                  |
 64| Grok 4 (Non-Reasoning) | X.ai      | Input               | $0.20                        | $0.22                   |
 65|                        | X.ai      | Output              | $0.50                        | $0.55                   |
 66|                        | X.ai      | Cached Input        | $0.05                        | $0.055                  |
 67| Grok Code Fast 1       | X.ai      | Input               | $0.20                        | $0.22                   |
 68|                        | X.ai      | Output              | $1.50                        | $1.65                   |
 69|                        | X.ai      | Cached Input        | $0.02                        | $0.022                  |
 70
 71## Recent Model Retirements
 72
 73As of February 19, 2026, Zed Pro serves newer model versions in place of the retired models below:
 74
 75- Claude Opus 4.1 → Claude Opus 4.5 or Claude Opus 4.6
 76- Claude Sonnet 4 → Claude Sonnet 4.5 or Claude Sonnet 4.6
 77- Claude Sonnet 3.7 (retired Feb 19) → Claude Sonnet 4.5 or Claude Sonnet 4.6
 78- GPT-5.1 and GPT-5 → GPT-5.2 or GPT-5.2-Codex
 79- Gemini 2.5 Pro → Gemini 3.1 Pro
 80- Gemini 3 Pro → Gemini 3.1 Pro
 81- Gemini 2.5 Flash → Gemini 3 Flash
 82
 83## Usage {#usage}
 84
 85Any 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.
 86
 87> LLMs can enter unproductive loops that require user intervention. Monitor longer-running tasks and interrupt if needed.
 88
 89## Context Windows {#context-windows}
 90
 91A 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.
 92
 93| Model                       | Provider  | Zed-Hosted Context Window |
 94| --------------------------- | --------- | ------------------------- |
 95| Claude Opus 4.5             | Anthropic | 200k                      |
 96| Claude Opus 4.6             | Anthropic | 1M                        |
 97| Claude Sonnet 4.5           | Anthropic | 200k                      |
 98| Claude Sonnet 4.6           | Anthropic | 1M                        |
 99| Claude Haiku 4.5            | Anthropic | 200k                      |
100| GPT-5.4 pro                 | OpenAI    | 400k                      |
101| GPT-5.4                     | OpenAI    | 400k                      |
102| GPT-5.3-Codex               | OpenAI    | 400k                      |
103| GPT-5.2                     | OpenAI    | 400k                      |
104| GPT-5.2-Codex               | OpenAI    | 400k                      |
105| GPT-5 mini                  | OpenAI    | 400k                      |
106| GPT-5 nano                  | OpenAI    | 400k                      |
107| Gemini 3.1 Pro              | Google    | 200k                      |
108| Gemini 3 Flash              | Google    | 200k                      |
109| Grok 4                      | X.ai      | 128k                      |
110| Grok 4 Fast                 | X.ai      | 128k                      |
111| Grok 4 Fast (Non-Reasoning) | X.ai      | 128k                      |
112| Grok Code Fast 1            | X.ai      | 256k                      |
113
114> Context window limits for hosted Gemini 3.1 Pro/3 Flash may increase in future releases.
115
116Each Agent thread in Zed maintains its own context window.
117The more prompts, attached files, and responses included in a session, the larger the context window grows.
118
119Start a new thread for each distinct task to keep context focused.
120
121## Tool Calls {#tool-calls}
122
123Models can use [tools](./tools.md) to interface with your code, search the web, and perform other useful functions.