Model comparison
Grok Build 0.1 vs Claude Sonnet 5: price, window, and status
Grok Build 0.1 costs $1.00 per cached coding session against $2.40 on Claude Sonnet 5, but it is in early access, with a 256K window and a price step at 200K.
· Prices as of September 28, 2026
Grok Build 0.1
xAI · Released May 2026 · Preview
xAI's dedicated agentic coding model, which also answers to the older grok-code-fast ids.
Grok Build 0.1 facts and comparisonsClaude Sonnet 5
Anthropic · Released June 30, 2026
Anthropic's balance of speed and intelligence, and a drop-in upgrade for Claude Sonnet 4.6. Anthropic pitches it as close to Claude Opus 4.8 at a lower price.
Claude Sonnet 5 facts and comparisons
The short answer
Grok Build 0.1 costs less than Claude Sonnet 5 on every example workload: $1.00 against $2.40 for the agentic coding session, and $0.19 against $0.86 for output-heavy work, since its output rate is $2 per million against $10. Sonnet 5 is a current model with a 1M context window that runs in Claude Code, Cursor, and GitHub Copilot, while Grok Build 0.1 is in early access with a 256K window and runs through OpenRouter and OpenCode. Grok Build 0.1 fits cost-driven agentic coding with prompts under 200K tokens, and Sonnet 5 fits large contexts and teams that work in Anthropic's tools.
Choose Grok Build 0.1 if
- You want the lower rates of this pair: $1 input and $2 output per million tokens.
- Your work is output-heavy, where the gap reaches 4.5x: $0.19 against $0.86 for the example generation.
- Your prompts stay under 200K tokens, below the line where every Grok Build 0.1 rate doubles.
- You still call the older grok-code-fast ids, which now answer to Grok Build 0.1.
Choose Claude Sonnet 5 if
- You want a model in general release rather than early access.
- You work in Claude Code, or in Cursor or GitHub Copilot, neither of which lists Grok Build 0.1.
- You need more than 256K tokens of context, or up to 128K of output per request.
- You want Anthropic's pitch: performance close to Claude Opus 4.8 at lower prices, and a drop-in upgrade from Claude Sonnet 4.6.
Side by side
Specs and prices
| Fact | Grok Build 0.1 | Claude Sonnet 5 |
|---|---|---|
| Maker | xAI | Anthropic |
| API model id | grok-build-0.1 | claude-sonnet-5 |
| Released | May 2026 | June 30, 2026 |
| Status | Preview | Current |
| Context window | 256K tokens | 1M tokens |
| Max output | Not published | 128K tokens |
| Open weights | No | No |
| Input, per 1M tokens | $1 | $2 |
| Cache hit, per 1M | $0.20 | $0.20 |
| Cache write, per 1M | $1 (same as input) | $2.50 (5-minute), $4 (1-hour) |
| Output, per 1M tokens | $2 | $10 |
| Runs in | OpenCode and OpenRouter | Claude Code, Cursor, OpenCode, OpenRouter, and GitHub Copilot |
Standard API rates in US dollars, as published by each maker (Grok Build 0.1: September 28, 2026; Claude Sonnet 5: September 26, 2026). Batch and priority tiers, taxes, and subscription plans are not included. Grok Build 0.1: Once a prompt reaches 200K tokens, every token in the request costs $2 input, $0.40 cached, and $4 output per million. Claude Sonnet 5: The full 1M context window is billed at standard rates. The launch price became the standard price on August 10, 2026, and a planned increase was cancelled.
Cost
What the same work costs
The same token counts, priced at each model’s published rates. Cached tokens are billed at each maker’s cache prices, so the session shows what caching is worth on each model.
Real sessions differ: the two models count the same code as different numbers of tokens, and reasoning settings change how much each one writes. Your own history is the real test.
| Workload | Grok Build 0.1 | Claude Sonnet 5 |
|---|---|---|
| Agentic coding session, 100K input, 400K written to cache, 2M read from cache, 50K output | $1.00 | $2.40 |
| Large one-off review, 150K input with no cache hits, 10K output | $0.17 | $0.40 |
| Output-heavy generation, 30K input, 80K output | $0.19 | $0.86 |
| A month of sessions, 110 sessions: 5 a day, 22 working days | $110.00 | $264.00 |
| Where the session’s cost goes | ||
| Cache writes | $0.40 | $1.30 |
| Cache reads | $0.40 | $0.40 |
| Uncached input | $0.10 | $0.20 |
| Output | $0.10 | $0.50 |
- caching saves on the session with Grok Build 0.1 (62%)
- $1.60
- caching saves on the session with Claude Sonnet 5 (56%)
- $3.10
What early access means for Grok Build 0.1
xAI announced Grok Build 0.1 as early access in May 2026 and describes it as "xAI's coding model, trained specifically for agentic coding workflows." It also answers to the older grok-code-fast ids. GitHub Copilot retired Grok Code Fast 1 on May 15, 2026, and neither Copilot nor Cursor lists Grok Build 0.1. It runs through OpenRouter and OpenCode.
Claude Sonnet 5 is a current model, released on June 30, 2026, and Anthropic calls it a drop-in upgrade for Claude Sonnet 4.6. It runs in Claude Code, Anthropic's own coding agent, where the sonnet alias resolves to it on the Anthropic API, and in Cursor, OpenCode, OpenRouter, and GitHub Copilot. Its launch price became the standard price on August 10, 2026, and a planned increase was cancelled.
Early access is a label about status, not price. The Grok Build 0.1 rates in the tables are xAI's published rates as of September 28, 2026, and the 0.1 version number is a reminder to recheck them, along with the model's availability, before building a team's workflow around it.
Where Grok Build 0.1's lower cost comes from
Input costs $1 per million on Grok Build 0.1 and $2 on Sonnet 5. Output is where the rate cards part most: $2 against $10, a 5x gap. That is why the output-heavy generation costs $0.19 on Grok Build 0.1 and $0.86 on Sonnet 5, while the large one-off review, which is mostly input, shows a smaller 2.4x gap at $0.17 against $0.40.
Cache hits cost the same on both, $0.20 per million. On Grok Build 0.1 that is 20% of input, and on Sonnet 5 it is 10%. The session's 2M cached tokens therefore cost $0.40 on either model, and reads add nothing to the difference.
Writes are the largest single gap. xAI lists no fee for writing the cache, so Grok Build 0.1 bills the 400K written tokens at its $1 input rate, $0.40. Anthropic bills 5-minute writes at 1.25x input and 1-hour writes at 2x, which comes to $1.30 on Sonnet 5. That $0.90 is most of the $1.40 session gap, and over 110 sessions a month the totals are $110.00 against $264.00.
The 256K window and the 200K price step
Grok Build 0.1 accepts 256K tokens of context, against 1M on Sonnet 5, and xAI does not publish its maximum output. Sonnet 5 writes up to 128K tokens per request.
Its long-context rule sits near the top of that window. Once a prompt reaches 200K tokens, every token in the request costs $2 input, $0.40 cached, and $4 output per million. In that band Grok Build 0.1's input matches Sonnet 5's $2, its cached reads cost twice Sonnet 5's $0.20, and its output, at $4 against $10, still costs less.
The example session keeps each request under 200K, so the cost table shows standard rates only. For repository-wide work that needs more than 256K in a single request, only Sonnet 5's 1M window can hold it.
How xAI and Anthropic describe these models
xAI names agentic software engineering and workflow tasks, with function calling, structured outputs, and reasoning, as what Grok Build 0.1 is for. Anthropic says Sonnet 5 is "built to be the most agentic Sonnet model yet" and lists planning and using tools like browsers and terminals on its own among its strengths. Both makers aim these models at agentic coding, and this page compares their prices and specs, not those claims.
Adaptive thinking is on by default on Sonnet 5, at high effort, and its tokenizer counts about 1.0 to 1.35x as many tokens as Claude Sonnet 4.6 for the same text. Token counts from two makers' tokenizers don't line up, so the same file can come to a different number of tokens on each.
EveryToken prices Sonnet 5 at Anthropic's rates from Claude Code, Cursor, and OpenCode history, and prices Grok Build 0.1 when you use it through OpenRouter, from OpenRouter's catalog.
Prompt caching
How each maker bills cached tokens
xAI
The xAI API caches repeated prompt prefixes automatically. Sending the same conversation id with each request raises the hit rate.
xAI lists no fee for writing the cache. A cache hit costs $0.50 per million tokens on Grok 4.7 and $0.20 on Grok Build 0.1.
Source: xAI docs: Prompt caching
Anthropic
Claude caches a prompt prefix up to a breakpoint. One top-level cache_control field places the breakpoint automatically and moves it as the conversation grows, or you can mark up to 4 blocks yourself. Claude Code manages caching for you.
A 5-minute cache write costs 1.25x the input price and a 1-hour write costs 2x. A cache hit costs 0.1x input on most models, 0.05x on Claude Opus 5.5, and 0.025x on Claude Fable 5.1 and Claude Mythos 5.1. Every hit restarts the cache lifetime at no charge.
Anthropic's rule of thumb: a 5-minute write pays for itself after one cache read, and a 1-hour write after two.
In Claude Code, the main conversation uses the 1-hour cache on a Claude subscription and the 5-minute cache with an API key. Each model has its own cache, so switching models starts over.
Source: Anthropic: Prompt caching
Your own numbers
See what Grok Build 0.1 and Claude Sonnet 5 really cost you.
everyaitoken reads your OpenRouter, Claude Code, Cursor, and OpenCode history on your Mac and prices every request at API rates, with what caching saved or cost. $9 once.
FAQ
Questions
Is Grok Build 0.1 cheaper than Claude Sonnet 5?
Yes, on every example workload. The agentic coding session costs $1.00 against $2.40, and 110 sessions a month cost $110.00 against $264.00. Cache hits cost $0.20 per million on both, so the gap comes from input, output, and Anthropic's cache-write premiums.
Is Grok Build 0.1 still in early access?
xAI announced it as early access in May 2026, and it carries preview status here. Claude Sonnet 5 is a current model.
Can I use Grok Build 0.1 in GitHub Copilot or Cursor?
Neither lists it. GitHub Copilot retired Grok Code Fast 1 on May 15, 2026. Grok Build 0.1 runs through OpenRouter and OpenCode, while Sonnet 5 is in both of those and in Cursor, GitHub Copilot, and Claude Code.
What does Grok Build 0.1 charge for long prompts?
Once a prompt reaches 200K tokens, every token in the request costs $2 input, $0.40 cached, and $4 output per million. Its window ends at 256K, so the higher rates cover the top of its range.
Sources
- xAI docs: Grok Build 0.1
- xAI docs: Release notes
- OpenRouter: Grok Build 0.1
- OpenCode docs: Zen
- GitHub Docs: Supported AI models in Copilot
- Anthropic: Pricing
- Anthropic docs: Claude Sonnet 5
- Anthropic: Introducing Claude Sonnet 5
- Claude Code docs: Model configuration
- Cursor docs: Claude Sonnet 5
- OpenRouter: Claude Sonnet 5
- OpenCode docs: Zen
- xAI docs: Prompt caching
- Anthropic: Prompt caching