ModelPriceWatch.com
Last scan 2026-08-09 Models tracked 198 Providers 30 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

Best LLM API for Coding

Compare LLM API pricing and capabilities for coding tasks. Independently benchmarked models for code generation, debugging, and software development — with verified per-token prices.

85 models qualify top 26 shown ranked by SWE-bench Verified
1Anthropic

Claude Opus 5

97% SWE-bench Verified

$10.00/1M blended · $5.00 in · $25.00 out

2OpenAI

GPT-5.6 Sol

96.2% SWE-bench Verified

$11.25/1M blended · $5.00 in · $30.00 out

3Anthropic

Claude Fable 5

95% SWE-bench Verified

$20.00/1M blended · $10.00 in · $50.00 out

MODELPRICEWATCH.COM · 2026-08-09

Cost calculator for this use casemonthly cost, top 3 models

1 Claude Opus 5
$—
2 GPT-5.6 Sol
$—
3 Claude Fable 5
$—

Full ranking — top 26 models

list prices, USD per 1M tokens
Top 26 models for Best LLM API for Coding, ranked by SWE-bench Verified
Model SWE-bench Verified Blended* Input Output Context Provider
1Claude Opus 5 97% $10.00 $5.00 $25.00 1M Anthropic
2GPT-5.6 Sol 96.2% $11.25 $5.00 $30.00 1M OpenAI
3Claude Fable 5 95% $20.00 $10.00 $50.00 1M Anthropic
4Kimi K3 93.4% $6.00 $3.00 $15.00 1M Moonshot
5GPT-5.6 Luna 93% $0.450 $0.200 $1.20 1M OpenAI
6Claude Opus 4.8 88.6% $10.00 $5.00 $25.00 1M Anthropic
7Claude Opus 4.7 87.6% $10.00 $5.00 $25.00 1M Anthropic
8Claude Sonnet 5 85.2% $4.00 $2.00 $10.00 1M Anthropic
9Claude Sonnet 4.5 82% $6.00 $3.00 $15.00 200K Anthropic
10GPT-5.4 75% $5.63 $2.50 $15.00 1M OpenAI
11Grok 4.3 65% $1.56 $1.25 $2.50 1M xAI
12GPT-4.1 49% $3.50 $2.00 $8.00 1M OpenAI
13MiniMax-M3 45% $0.525 $0.300 $1.20 1M MiniMax
14Mistral Large 3 35% $0.750 $0.500 $1.50 128K Mistral
15Llama 4 Scout 28% $0.168 $0.110 $0.340 10M Meta
16Llama 3.3 70B 22% $0.640 $0.590 $0.790 128K Meta
17Llama 3.1 8B 12% $0.058 $0.050 $0.080 128K Meta
18GPT-5.3 Codex 85% vendor $4.81 $1.75 $14.00 400K OpenAI
19DeepSeek V4 Pro 80.6% vendor $0.544 $0.435 $0.870 1M DeepSeek
20GPT-5.2 80% vendor $4.81 $1.75 $14.00 400K OpenAI
21Inkling Small $0.525 $0.300 $1.20 262K Thinking Machines
22Gemini 3.5 Flash-Lite $0.850 $0.300 $2.50 1M Google
23Inkling $1.76 $1.00 $4.05 262K Thinking Machines
24Muse Spark 1.2 $2.00 $1.25 $4.25 1M Meta
25Qwen3.8-Max $3.00 $2.00 $6.00 1M Alibaba
26Gemini 3.6 Flash $3.00 $1.50 $7.50 1M Google
Ranked by SWE-bench Verified — independent leaderboard data; benchmark citations are on each model page. Scores flagged “vendor” are the maker's own claim, shown for reference and ranked below independently-scored models; models with no published score rank last, cheapest first. * Blended = (3×input + 1×output) ÷ 4. Every price links to its source on the model page.

Recent price movement in this ranking

price-only deltas · logged by the daily scan

2 of the top 26 coding models have re-priced since we began tracking · last checked Aug 9, 2026.

Models in this Best LLM API for Coding ranking that have re-priced since tracking began, most recent move first
Model Changes Latest move Provider
GPT-5.6 Luna 1 price cut on Aug 1, 2026: $1/$6 → $0.2/$1.2 /Mtok OpenAI
MiniMax-M3 1 price cut on Jun 17, 2026: $0.6/$2.4 → $0.3/$1.2 /Mtok MiniMax
Changes = distinct price moves logged since tracking began; in/out prices are $ per 1M tokens. MODELPRICEWATCH.COM · 2026-08-09

Most recently, GPT-5.6 Luna cut its price on Aug 1, 2026 — a sign pricing in this category is still moving, so re-check before committing to a long-term choice. See all recent price moves →

How models are selected

Generally-available models with a SWE-bench Verified score (resolving real GitHub issues) or a code-specialized release, ranked by independently-evaluated SWE-bench Verified. One row per model — host duplicates are collapsed. Vendor-reported scores are shown flagged and ranked below independently-scored models, never against them; models with no published score rank last, cheapest first. Prices shown are verified against official provider pages.

Prices are per million tokens (Mtok), sourced directly from — and linked to — official provider pricing pages. "Blended cost" is (3×input + 1×output) ÷ 4 — weighted toward input because real workloads read far more tokens than they generate.

Other use case rankings