Which is cheaper, GPT-5 Codex or Mistral Small 4?
As of August 20, 2026, Mistral Small 4 is 93% cheaper on blended LLM API pricing. Mistral Small 4 costs $0.15 per million input tokens and $0.60 per million output tokens ($0.75 blended 1M-in + 1M-out). GPT-5 Codex costs $1.25 / $10.00 per million tokens ($11.25 blended). Sources: https://developers.openai.com/api/docs/pricing and https://docs.mistral.ai/platform/pricing/. The cheapest LLM for your app still depends on how many output tokens you generate.
How much does GPT-5 Codex vs Mistral Small 4 cost per million tokens?
GPT-5 Codex OpenAI API pricing is $1.25 input and $10.00 output per million tokens via OpenAI. Mistral Small 4 Mistral API pricing is $0.15 input and $0.60 output per million tokens via Mistral AI. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.
Which is better for coding, GPT-5 Codex or Mistral Small 4?
GPT-5 Codex has a published SWE-bench Verified score of 74.5%. Mistral Small 4 does not have that eval on this page yet.
What is the context window for GPT-5 Codex vs Mistral Small 4?
GPT-5 Codex supports a 400K token context window, while Mistral Small 4 supports 256K tokens. GPT-5 Codex offers a larger context window. Filling a larger window bills more input tokens, so the cheaper-per-million model can still cost more on long documents.
Which model performs better on benchmarks, GPT-5 Codex or Mistral Small 4?
GPT-5 Codex leads on 1 of 1 shared benchmarks versus Mistral Small 4's 0 wins. Check the comparison table for GPQA Diamond, SWE-bench, MMLU, HLE, and the other evals we track. Token price and benchmark score together are the usual LLM comparison, not either number alone.
Is GPT-5 Codex or Mistral Small 4 better for production use?
Both GPT-5 Codex and Mistral Small 4 are production API models. For cost-sensitive production traffic, Mistral Small 4 has better economics on the blended 1M-in + 1M-out scale. For maximum capability, weight the benchmark table for your domain. Many production stacks route cheap models for drafts and a frontier model for the hard turn, which is usually cheaper than sending everything to the expensive API.
Can I switch between GPT-5 Codex and Mistral Small 4 in my app?
Yes. Call GPT-5 Codex through OpenAI and Mistral Small 4 through Mistral AI with separate API keys, or through a gateway that already wraps both. Keep prompts in tokens, not characters, when you estimate the invoice. AnotherWrapper templates can swap providers without rewriting auth and billing.
How accurate is this GPT-5 Codex vs Mistral Small 4 pricing data?
List rates are the latest published OpenAI API pricing and Mistral API pricing, quoted per million tokens. Official rate sheets: https://developers.openai.com/api/docs/pricing and https://docs.mistral.ai/platform/pricing/. Prompt caching, batch APIs, and committed-use discounts can change the invoice. Benchmark scores are from official publications and independent evals, updated as new numbers land.
What is the output token limit for GPT-5 Codex and Mistral Small 4?
GPT-5 Codex supports up to an unspecified number of output tokens per request, while Mistral Small 4 supports up to 256K output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.
Which model has better throughput, GPT-5 Codex or Mistral Small 4?
Mistral Small 4 has a measured throughput of approximately 4.30138482451386 tokens/second. Throughput data for GPT-5 Codex is not yet available. Throughput (tokens per second) and time-to-first-token are why two models with the same per-million-token price can still feel different in chat and agents.
How do I switch the models in this GPT-5 Codex vs Mistral Small 4 comparison?
Use the model pickers at the top of this LLM comparison. Search any model in the index and the URL updates. Open GPT-5 Codex or Mistral Small 4 from the sidebar for the single-model API pricing page, or go back to the LLM pricing table to sort by cheapest blended cost.
