Grok Code Fast 1
Aug 2025
Retired 2026-05-15Replace withGrok Build 0.1Newer version
MiMo v2.6 ProCheaper, as good
GPT-6 LunaBetter
Grok Build 0.1Newer versionMiMo v2.6 ProCheaper, as goodGPT-6 LunaBetterGrok Code Fast 1Compare inon
Benchmarks of Grok Code Fast 121
BenchmarkByScoreRank
Overall1
Knowledge4
Science2
Coding3
Documents1
Legacy · saturated or no longer reported10
No benchmark matches
Rankingin thinking mode?
Retired models are left out of the current rankings.
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperMiMo v2.6 ProthinkingOpen×3.3-57%$0.13Pass back reasoning_content+3BetterGPT-6 Lunalow+53%-84%$0.005Function calling only with none · Chat Completions+3
CheaperDeepSeek V4.1 Flash 1017maxOpen×3.2-58%$0.26Pass back reasoning_content · Chat Completions+4
CheaperClaude Haiku 5.5max×3.1-84%$0.21Remove sampling parameters+5
CheaperMiniMax M3.1 Flashthinking×3-79%$0.22Complete model response must be appendedModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen×3.3-57%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen×3.2-58%$0.26Pass back reasoning_content · Chat Completions+4Claude Haiku 5.5max×3.1-84%$0.21Remove sampling parameters+5MiniMax M3.1 Flashthinking×3-79%$0.22Complete model response must be appended
GLM 5.3 FlashmaxOpen×3-81%$0.28Defaults to max · Self-hosted+4ModelScoreCostPer taskWhat changes
GPT-6 Lunalow+53%-84%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow+49%-64%$0.01MiMo v2.5thinkingOpen+55%-86%$0.019Claude Haiku 5.5low×2.1-84%$0.024Remove sampling parameters+5GPT-5 Minihigh+19%-45%$0.053ModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen×3.3-57%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen×3.2-58%$0.26Pass back reasoning_content · Chat Completions+4GLM 5.3maxOpen×3.2+72%$2.01No image input+4
Step 5 PreviewthinkingOpen×3.1+14%$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen×3.1+380%$2.00Sampling parameters are fixed+3ModelScoreCostPer taskWhat changes
Grok 4.6medium×3—$1.14Grok 4.7low×3—$1.25Reasoning cannot be disabled+4Grok 4.5high×2.8—$0.88Grok Build 0.1thinking+93%—$1 / $2Grok 4.3medium+76%—$1.25 / $2.50Grok 4.20 Multi-Agentn/a—$1.25 / $2.50Grok 4.20 Non-Reasoningn/a—$1.25 / $2.50Context: not verifiedGrok 4.20 Reasoningn/a—$1.25 / $2.50Context: not verifiedAll xAI models →Benchmarks
all categoriesChat & Knowledge
AA Omniscience Index-37.1
GPQA Diamond72.7
Coding
Agents & Tool Use
τ²-bench · AA75.7
Writing & Language
FAQ
How much does Grok Code Fast 1 cost?›
$1 per 1M input tokens and $2 per 1M output tokens; cached input $0.20 per 1M.
Is Grok Code Fast 1 free to use?›
There is no free API; the cheapest paid price is $1 per 1M input tokens.
How can I use Grok Code Fast 1?›
Through the API of SpaceXAI.
What is the context window of Grok Code Fast 1?›
256K tokens, with up to 256K output tokens.
When was Grok Code Fast 1 released? Is there a newer version?›
Released 2025-08-28. It has been superseded by Grok Build 0.1.
Is Grok Code Fast 1 open source?›
No, Grok Code Fast 1 is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can Grok Code Fast 1 read images?›
It accepts text and images as input.
What is Grok Code Fast 1?›
Grok Code Fast 1 is a closed language model from xAI, released Aug 2025.
What are the best alternatives to Grok Code Fast 1?›
MiMo v2.6 Pro (cheaper), GPT-6 Luna (better).