Ranking · AI models

Best AI models for coding by price

How many LLM Stats coding-index points each dollar buys: useful for agents that make many calls per task.

Criteria the LLM Stats coding index divided by the blended 3:1 (input:output) price, only for models with a coding index of 35 or higher.

Data reviewed on Nov 4, 2026 · 21 of 36 models publish this figure.

  1. 01
    196.5Coding points per USD
  2. 02
    147.8Coding points per USD
  3. 03
    76.8Coding points per USD
#ModelCoding points per USDBlended priceContext
01Claude Haiku 5.5Anthropic196.5$0.201.00M
02MiniMax M3.1 FlashMiniMax147.8$0.2625—
03DeepSeek V4.1 FlashDeepSeek76.8$0.5251.00M
04Mistral Large 4Mistral AI35.3$1.051.00M
05Muse Spark 1.3Meta19.6$2.00—
06DeepSeek V4 ProDeepSeek19.5$1.981.00M
07GPT-6.1 TerraOpenAI18.6$2.001.05M
08GLM-5.3Z.ai (Zhipu AI)18.6$2.15—
09Qwen3.8 MaxAlibaba Cloud12.6$3.00—
10Claude Sonnet 5.5Anthropic12.2$4.001.00M
11Grok 4.7xAI11.9$3.00500K
12Gemini 4 ArgonGoogle10.8$4.001.05M
13Kimi K3.1 ProMoonshot AI10.7$4.001.05M
14GPT-6.1 SolOpenAI9.9$4.001.05M
15GPT-5.6 TerraOpenAI8.7$4.501.05M
16Kimi K3Moonshot AI6.8$6.001.05M
17Claude Opus 5.5Anthropic6.4$8.001.00M
18GPT-5.6 SolOpenAI5.3$8.001.05M
19Claude Opus 5Anthropic4.0$10.001.00M
20GPT-6 AstraOpenAI2.3$20.001.05M
21Claude Fable 5.1Anthropic1.8$20.001.00M

How it is calculated

  • The indexes (overall, reasoning, coding) are the ones LLM Stats publishes; Codifly does not run these tests.
  • Prices are each provider's official standard API prices, without caching or batching.
  • The blended price weighs 3 input tokens per output token; cost-benefit divides the overall index by that price.
Methodology and sources

Which one fits your case?

The top of a ranking is not always the most cost-effective at your volume. Estimate your cost or ask us for a written recommendation.

Compare Claude Haiku 5.5 vs MiniMax M3.1 FlashEstimate my monthly costGet a recommendation

Frequently asked questions

Which is the best AI model for coding per dollar?+

Claude Haiku 5.5 (196.5 pts/USD) leads this ranking, followed by MiniMax M3.1 Flash (147.8 pts/USD) · DeepSeek V4.1 Flash (76.8 pts/USD). Data reviewed on Nov 4, 2026.

Which model in this ranking has the best price-performance?+

Claude Haiku 5.5: 247.0 LLM Stats index points per dollar, at a blended price of $0.20 per million tokens.

How is this ranking calculated?+

the LLM Stats coding index divided by the blended 3:1 (input:output) price, only for models with a coding index of 35 or higher. The indexes (overall, reasoning, coding) are the ones LLM Stats publishes; Codifly does not run these tests. Prices are each provider's official standard API prices, without caching or batching. The blended price weighs 3 input tokens per output token; cost-benefit divides the overall index by that price.

A clearer perspective. In your inbox.

Analysis, guides and new technology comparisons.

Link a form to receive subscriptions.