Home / Models / IBM / Granite 4.0 Micro
IBM logoIBMopen weights

Granite 4.0 Micro pricing

$0.017 per 1M input tokens and $0.11 per 1M output tokens. In real work that is 0.02¢ per chat answer and 0.05¢ to summarize a 20-page PDF.

Input / 1M$0.017
Output / 1M$0.11
Cached input / 1Mn/a
Chat answer0.02¢
Context131K
Quality-

What Granite 4.0 Micro costs per task

Token counts estimated from a measured model of the same lab (Qwen3.8 Flash), rescaled by tokenizer. Reasoning tokens are billed as output.

TaskCostTokens usedPrice rankBasis
Answer a chat question
0.02¢$0.18 / 1,000
87 in · 683 out · 909 reasoning12 of 336estimated
Reply to a customer email
<0.01¢$0.08 / 1,000
323 in · 97 out · 587 reasoning17 of 336estimated
Write a 1,500-word blog post
≥0.18¢$1.79 / 1,000
103 in · 0 out · 16,000 reasoning48 of 336estimated
Write 10 product descriptions
≥0.18¢$1.80 / 1,000
342 in · 0 out · 16,000 reasoning61 of 336estimated
Translate 1,000 words
0.02¢$0.17 / 1,000
1,375 in · 1,156 out · 136 reasoning6 of 336estimated
Proofread one page (500 words)
0.02¢$0.22 / 1,000
770 in · 665 out · 1,159 reasoning11 of 336estimated
Summarize a 20-page PDF
0.05¢$0.52 / 1,000
13,015 in · 497 out · 2,141 reasoning4 of 336estimated
Extract data from an invoice
0.03¢$0.25 / 1,000
497 in · 556 out · 1,617 reasoning17 of 336estimated
Analyze a 200-row spreadsheet
≥0.19¢$1.90 / 1,000
6,306 in · 0 out · 16,000 reasoning16 of 336estimated
Answer from 5 retrieved documents (RAG)
0.04¢$0.39 / 1,000
3,721 in · 966 out · 1,912 reasoning8 of 336estimated
Classify 100 support tickets
0.10¢$0.97 / 1,000
1,451 in · 529 out · 7,879 reasoning27 of 336estimated
Review 500 lines of code
≥0.19¢$1.87 / 1,000
4,835 in · 0 out · 16,000 reasoning19 of 336estimated
Write a SQL query
0.03¢$0.30 / 1,000
175 in · 401 out · 2,225 reasoning16 of 336estimated
Run a 50-step coding agent
4.9¢$48.85 / 1,000
2,241,975 in · 15,030 out · 80,850 reasoning19 of 336modeled

Price at every provider

List prices per 1M tokens (input / output) at each host serving Granite 4.0 Micro through OpenRouter today. Hosts can differ in quantization, context and speed.

ProviderInput / outputCached inputContextUptime
C
Cloudflareunknown
$0.017 / $0.11-131K100%

Price history

First seen in our price history on Oct 31, 2025 at $0.017 input / $0.11 output. Since then the output price moved from $0.11 to $0.11 per 1M tokens (1 change).

$0$0.032$0.064$0.097$0.13Oct 2025Jan 2026Apr 2026Jul 2026Oct 2026
Output per 1MInput per 1M

FAQ

How much does Granite 4.0 Micro cost?

Granite 4.0 Micro costs $0.017 per 1 million input tokens and $0.11 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.02¢ and summarizing a 20-page PDF about 0.05¢.

Where is Granite 4.0 Micro cheapest?

Among 1 providers we track, the lowest list price today is at Cloudflare: $0.017 input and $0.11 output per 1M tokens.

Is the Granite 4.0 Micro cost per task measured or estimated?

Estimated: Granite 4.0 Micro was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of IBM. Real usage can differ.