As of August 25, 2026, GLM-4.5-Air is 75% cheaper per million tokens than GLM-5-Turbo. GLM-4.5-Air is $0.20 / $1.10 per million input/output tokens versus GLM-5-Turbo at $1.20 / $4.00. Source: https://docs.z.ai/guides/overview/pricing
Source: Z AI pricing (https://docs.z.ai/guides/overview/pricing)
GLM-4.5-Air
Z AI
Input
$0.20
Output
$1.10
GLM-5-Turbo
Z AI
Input
$1.20
Output
$4.00
Token pricing, specs, and benchmarks side by side
GLM-4.5-AirGLM-5-TurboVerdict
Both models are closely matched on benchmarks. GLM-4.5-Air has the pricing advantage, making it the better value unless GLM-5-Turbo's specific capabilities are critical to your workflow.
As of August 25, 2026, GLM-4.5-Air is 75% cheaper on blended LLM API pricing. GLM-4.5-Air costs $0.20 per million input tokens and $1.10 per million output tokens ($1.30 blended 1M-in + 1M-out). GLM-5-Turbo costs $1.20 / $4.00 per million tokens ($5.20 blended). Sources: https://docs.z.ai/guides/overview/pricing and https://docs.z.ai/guides/overview/pricing. The cheapest LLM for your app still depends on how many output tokens you generate.
GLM-4.5-Air Z AI API pricing is $0.20 input and $1.10 output per million tokens via Z AI. GLM-5-Turbo Z AI API pricing is $1.20 input and $4.00 output per million tokens via Z AI. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.
GLM-4.5-Air has a published SWE-bench Verified score of 57.6%. GLM-5-Turbo does not have that eval on this page yet.
GLM-4.5-Air supports a 131K token context window, while GLM-5-Turbo supports 262K tokens. GLM-5-Turbo 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.
Shared benchmark scores for GLM-4.5-Air and GLM-5-Turbo are still limited. Check the comparison table for the evals each model has published. 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 GLM-4.5-Air and GLM-5-Turbo are production API models. For cost-sensitive production traffic, GLM-4.5-Air 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 GLM-4.5-Air through Z AI and GLM-5-Turbo through Z 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.
List rates are the latest published Z AI API pricing and Z AI API pricing, quoted per million tokens. Official rate sheets: https://docs.z.ai/guides/overview/pricing and https://docs.z.ai/guides/overview/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.
GLM-4.5-Air supports up to an unspecified number of output tokens per request, while GLM-5-Turbo 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 GLM-4.5-Air nor GLM-5-Turbo 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 GLM-4.5-Air or GLM-5-Turbo 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. GLM-4.5-Air costs $0.20/M input and $1.10/M output. GLM-5-Turbo costs $1.20/M input and $4.00/M output.
Rank both on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.
The index
280 models across 33 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.
