Google: Gemma 4 26B A4B comes out ahead on the data we track: 3 advantages and none for Mistral: Mistral Small 4 (batch).
| Spec | Google: Gemma 4 26B A4B | Mistral: Mistral Small 4 (batch) |
|---|---|---|
| Provider | Mistral AI | |
| Input price (per 1M tokens) | $0.07 | $0.07 |
| Output price (per 1M tokens) | $0.23 | $0.30 |
| Blended price (3:1 input/output) | $0.11 | $0.13 |
| Cheaper than … of all models we track | 80% | 76% |
| Context window | 262K tokens (~393 pages) | 262K tokens (~393 pages) |
| Larger context than … of all models | 48% | 48% |
| Max output per response | 236K tokens (~176,900 words) | 210K tokens (~157,300 words) |
| Input types | image, text, video | text, image |
| Output types | text | text |
| Free variant | Yes | No |
| Listed since | 2026-04-03 | 2026-03-16 |
Monthly cost at list price for five common workloads. Token counts per unit are stated so you can scale them to your own traffic. A workload that does not fit a model's context window is marked rather than priced.
| Workload (per month) | Google: Gemma 4 26B A4B | Mistral: Mistral Small 4 (batch) | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $9.56 | $11.63 | Google: Gemma 4 26B A4B saves $2.06 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $10.35 | $12.00 | Google: Gemma 4 26B A4B saves $1.65 |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context (60,000 in / 6,000 out tokens) | $10.80 | $12.60 | Google: Gemma 4 26B A4B saves $1.80 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $6.75 | $7.80 | Google: Gemma 4 26B A4B saves $1.05 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $3.60 | $4.05 | Google: Gemma 4 26B A4B saves $0.45 |
| Capability | Google: Gemma 4 26B A4B | Mistral: Mistral Small 4 (batch) | What it lets you do |
|---|---|---|---|
| Tool / function calling | ✓ Yes | ✓ Yes | call your APIs and run agent loops |
| Structured output (JSON schema) | ✓ Yes | ✓ Yes | return JSON that validates against your schema |
| Reasoning / thinking mode | ✓ Yes | ✓ Yes | spend extra tokens thinking before answering hard problems |
| Image input | ✓ Yes | ✓ Yes | read screenshots, charts and scanned pages |
| Audio input | — | — | take speech or audio directly |
| File / PDF input | — | — | accept documents without your own parsing step |
| Image output | — | — | generate images, not just text |
| Built-in web search | — | — | answer from live web results |
| Seed (reproducible sampling) | ✓ Yes | ✓ Yes | repeat a generation for tests and evals |
| Log-probabilities | ✓ Yes | — | read token confidence for classification and scoring |
From each model's published parameters and input/output types. “—” means not advertised, not proven absent.
| Date | Model | Input / 1M | Output / 1M |
|---|---|---|---|
| 2026-10-17 | Google: Gemma 4 26B A4B | $0.07 | $0.23 |
| 2026-10-13 | Google: Gemma 4 26B A4B | $0.08 | $0.26 |
| 2026-10-10 | Google: Gemma 4 26B A4B | $0.07 | $0.23 |
| 2026-10-06 | Google: Gemma 4 26B A4B | $0.08 | $0.26 |
| 2026-10-03 | Google: Gemma 4 26B A4B | $0.07 | $0.23 |
| 2026-09-29 | Google: Gemma 4 26B A4B | $0.08 | $0.26 |
| 2026-09-26 | Google: Gemma 4 26B A4B | $0.07 | $0.23 |
| 2026-09-13 | Google: Gemma 4 26B A4B | $0.09 | $0.30 |
No advantage on the data we track — pick it for provider preference or output quality on your own prompts.
Google: Gemma 4 26B A4B comes out ahead on the data we track: 3 advantages and none for Mistral: Mistral Small 4 (batch).
Google: Gemma 4 26B A4B is cheaper: $0.11 vs $0.13 per 1M tokens at a typical 3:1 input/output mix, 19% less. For 50,000 support conversations a month that is $9.56 against $11.63.
Google: Gemma 4 26B A4B costs $0.07 per 1M input tokens and $0.23 per 1M output tokens; Mistral: Mistral Small 4 (batch) costs $0.07 input and $0.30 output. Output tokens are billed separately, so long answers shift the gap.
Both take 262K tokens per request — roughly 393 pages of text.
Tool calling — Google: Gemma 4 26B A4B: yes, Mistral: Mistral Small 4 (batch): yes. JSON-schema structured output — Google: Gemma 4 26B A4B: yes, Mistral: Mistral Small 4 (batch): yes.
Yes, both accept image input.
Google: Gemma 4 26B A4B has a free variant (google/gemma-4-26b-a4b-it:free). Free variants usually carry tighter rate limits.
Google: Gemma 4 26B A4B can write up to 236K tokens (about 176,900 words) per response; Mistral: Mistral Small 4 (batch) up to 210K (about 157,300 words).
Google: Gemma 4 26B A4B was listed on 2026-04-03; Mistral: Mistral Small 4 (batch) on 2026-03-16.
Google: Gemma 4 26B A4B: input price cut 12% ($0.08 → $0.07/1M), output price cut 12% ($0.26 → $0.23/1M) on 2026-10-17 (11 price changes since 2026-08-06). Mistral: Mistral Small 4 (batch): input price cut 50% ($0.15 → $0.07/1M), output price cut 50% ($0.60 → $0.30/1M) on 2026-09-10.
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Full Google: Gemma 4 26B A4B specs →Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
Full Mistral: Mistral Small 4 (batch) specs →