As of August 30, 2026, Gemma 3 1B is 95% cheaper per million tokens than Codestral-22B. Codestral-22B is $0.30 / $0.90 per million input/output tokens versus Gemma 3 1B at $0.02 / $0.04. Sources: https://mistral.ai/technology/pricing and https://ai.google.dev/gemini-api/docs/pricing
Sources: Mistral AI pricing (https://mistral.ai/technology/pricing); Gemini API pricing (https://ai.google.dev/gemini-api/docs/pricing)
Codestral-22B
Mistral
Input
$0.30
Output
$0.90
Gemma 3 1B
Input
$0.02
Output
$0.04
Token pricing, specs, and benchmarks side by side
Each bar is share of the current leader on that eval. Click a row to open the board.
HumanEval. Left is cheaper. Up is a higher score. The line is the best score you can buy at each price.
Codestral-22BGemma 3 1BVerdict
Gemma 3 1B offers significantly lower pricing, while Codestral-22B leads on benchmark performance. Your choice depends on whether cost efficiency or raw capability matters more for your use case.
As of August 30, 2026, Gemma 3 1B is 95% cheaper on blended LLM API pricing. Gemma 3 1B costs $0.02 per million input tokens and $0.04 per million output tokens ($0.06 blended 1M-in + 1M-out). Codestral-22B costs $0.30 / $0.90 per million tokens ($1.20 blended). Sources: https://mistral.ai/technology/pricing and https://ai.google.dev/gemini-api/docs/pricing. The cheapest LLM for your app still depends on how many output tokens you generate.
Codestral-22B Mistral API pricing is $0.30 input and $0.90 output per million tokens via Mistral AI. Gemma 3 1B Gemini API pricing is $0.02 input and $0.04 output per million tokens via Google. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.
Gemma 3 1B has a published LiveCodeBench score of 1.9%. Codestral-22B does not have that eval on this page yet.
Codestral-22B supports a 33K token context window, while Gemma 3 1B supports 33K tokens. Both models have the same context window size. Filling a larger window bills more input tokens, so the cheaper-per-million model can still cost more on long documents.
Codestral-22B leads on 2 of 2 shared benchmarks versus Gemma 3 1B'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.
Both Codestral-22B and Gemma 3 1B are production API models. For cost-sensitive production traffic, Gemma 3 1B 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.
Yes. Call Codestral-22B through Mistral AI and Gemma 3 1B through Google 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.
List rates are the latest published Mistral API pricing and Gemini API pricing, quoted per million tokens. Official rate sheets: https://mistral.ai/technology/pricing and https://ai.google.dev/gemini-api/docs/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.
Codestral-22B supports up to an unspecified number of output tokens per request, while Gemma 3 1B supports up to an unspecified number of output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.
Neither Codestral-22B nor Gemma 3 1B has published throughput data on this page yet. 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.
Use the model pickers at the top of this LLM comparison. Search any model in the index and the URL updates. Open Codestral-22B or Gemma 3 1B from the sidebar for the single-model API pricing page, or go back to the LLM pricing table to sort by cheapest blended cost.
This comparison covers API pricing, context window, throughput, and benchmark scores. Codestral-22B costs $0.30/M input and $0.90/M output via Mistral AI. Gemma 3 1B costs $0.02/M input and $0.04/M output.
Rank both on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.
The index
343 models across 36 providers. Search or jump to a lab — every model page stays linked here.
Next step
Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.
