Mistral Small 4 alternatives
Same input types and capabilities, at least half the context window · USD per 1M tokens
We found 10 models that can replace Mistral Small 4 ($0.15 input / $0.60 output per million tokens). 5 of them are cheaper. The cheapest, Muse Spark 1.2 Contributor, costs 52.4% less on a blended 3:1 basis: $1.40 instead of $2.70 per month for a chatbot workload (10M input / 2M output tokens).
// 10 alternatives
| model | lab | in $/1M | out $/1M | ctx | vs Mistral Small 4 | chatbot / mo |
|---|---|---|---|---|---|---|
| Muse Spark 1.2 Contributor | Meta | $0.10 | $0.20 | 1.05M | −52.4% | $1.40 |
| Muse Spark 1.3 Contributor | Meta | $0.10 | $0.20 | 1.05M | −52.4% | $1.40 |
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | 1.05M | −33.3% | $1.80 | |
| Claude Haiku 5.5 · compare | Anthropic | $0.10 | $0.50 | 1M | −23.8% | $2.00 |
| GPT-6 Luna · compare | OpenAI | $0.10 | $0.50 | 1.05M | −23.8% | $2.00 |
| GPT-5.6 Luna · compare | OpenAI | $0.20 | $1.20 | 1.05M | +71.4% | $4.40 |
| Gemini 3.1 Flash Lite | $0.25 | $1.50 | 1.05M | +114.3% | $5.50 | |
| GLM-5.3-FlashX · compare | Z.AI (Zhipu) | $0.37 | $1.25 | 1M | +124.8% | $6.20 |
| Gemini 2.5 Flash | $0.30 | $2.50 | 1.05M | +223.8% | $8.00 | |
| Gemini 3.5 Flash Lite | $0.30 | $2.50 | 1.05M | +223.8% | $8.00 |
// how we pick alternatives
An alternative must accept every input type Mistral Small 4 accepts (text, image, pdf), offer the same tool-calling and reasoning support, and have at least half of its 262.1K-token context window. Models are sorted by blended price (3 × input + output) / 4, using base-tier list prices refreshed daily.