GLM-5.3 is Z.ai's current GLM flagship, priced at $1.40 per 1M input tokens and $4.40 per 1M output tokens with a 1M context window. It replaced GLM-5.2 at the same price.
GLM-5.3 costs $1.40 input / $4.40 output per 1M tokens, with cached input at $0.26 and cache storage currently free. If you're on GLM-5.2 or 5.1, switching costs nothing extra: Z.ai lists all three at identical rates.
| GLM-5.3 | |
|---|---|
| Provider | Z.ai |
| Tier | Mid-tier |
| Input / 1M tokens | $1.40 |
| Output / 1M tokens | $4.40 |
| Cache hit / 1M | $0.26 |
| Cache write / 1M | — |
| Context window | 1M |
| Notes | GLM flagship; replaced 5.2 at same price; strong coding value |
| Model | Support chatbot 10,000 conversations × (2,000 input + 400 output tokens) | Document Q&A 1,000 questions × (30,000 input + 800 output tokens) | Coding agent session 4M input tokens (90% cache hits) + 150,000 output tokens |
|---|---|---|---|
| GLM-5.3 | $45.60 | $45.52 | $2.16 |
| Mistral Large 3 | $16.00 | $16.20 | $2.23 |
| DeepSeek V4-Pro | $21.12 | $21.38 | $0.64 |
| Mistral Large 4 | $22.40 | $22.68 | $0.85 |
Standard rates per 1M tokens from data on this site. The coding-agent row assumes 90% of input is read from the prompt cache (full input price where a model has no cache rate). Cache-write fees, batch discounts and long-context surcharges listed in the notes are not included. Updated November 2, 2026.
| Model | Tier | Input / 1M | Output / 1M | Cache hit / 1M | Context | Notes |
|---|---|---|---|---|---|---|
| Mistral Large 3 | Mid-tier | $0.50 | $1.50 | — | 256K | Former Mistral flagship; deprecated Oct 31, 2026, retiring Apr 30, 2027 — replaced by Mistral Large 4 |
| DeepSeek V4-Pro | Mid-tier | $0.66 | $1.98 | $0.022 | 1M | A planned Sep 14, 2026 reroute to V4.1-Flash rates was reversed after user pushback; billing unchanged since the Aug 13, 2026 GA build. Off-peak rate shown; peak (01:00-04:00 & 06:00-10:00 UTC weekdays) is 2x: $1.32/$3.96 |
| Mistral Large 4 | Mid-tier | $0.70 | $2.10 | $0.07 | 1M | New Mistral flagship (Oct 6, 2026; public preview); open-weight 1.05T MoE (52B active), multimodal; replaces Large 3 and Medium 3.5 |
| Grok 4.3 | Mid-tier | $1.25 | $2.50 | $0.20 | 1M | Reasoning workhorse; replaced Grok 4; ≥200K tokens: $2.50/$5, cache $0.40 |
| Gemini 3.8 Flash | Mid-tier | $0.75 | $3.75 | $0.075 | 1M | On the Gemini API free and paid tiers; Gemini 3.7 Flash retired Oct 8, 2026 and now auto-routes here (requests still billed at this rate); intro price thru Dec 31, reverts to $1.50/$7.50 (cache $0.15) Jan 1 |
Cached input on GLM-5.3 is billed at $0.26 per 1M tokens, a fraction of the $1.40 standard input rate, and Z.ai lists cached-input storage as free for a limited time across the GLM-5.x line. For agents that resend a large codebase or tool schema on every step, that combination is where most of the savings come from; the coding-agent row in the cost table assumes 90% cache hits for that reason. Watch for the storage promotion ending, since it would add a cost the tables here don't include.
GLM-5.3 accepts text only, with a 1M-token context window and up to 128K output tokens. Reasoning can't be turned off: requests that set thinking.type to disabled fail. You choose an effort level instead (low, high or max, default max), and dropping to low is the simplest way to cut output spend on routine tasks. Z.ai exposes OpenAI Chat Completions-compatible, OpenAI Responses-compatible and Anthropic Messages-compatible endpoints, so most existing SDK code works with a base-URL change.
Z.ai also sells GLM-5.3-Flash and GLM-5.3-FlashX at much lower per-token rates for high-volume, latency-sensitive work, and keeps older GLM-4.x Flash models free. For interactive coding, the GLM Coding Plan includes GLM-5.3 on a points-based quota, with off-peak calls using half the points. GLM-5.3 is also available through Perplexity's Agent API at the same input, output and cache-read rates, and Mistral's platform lists it among its current models.
$1.40 for input, $4.40 for output and $0.26 for cached input. Cached-input storage is free for a limited time.
No. Z.ai lists GLM-5.3, GLM-5.2 and GLM-5.1 at the same input, cached-input and output prices.
No. Z.ai's GLM-5.3 docs say it currently supports text-only input.
No. Reasoning is always on; you can set the effort to low, high or max (the default) to control how many tokens it spends.
How we choose: prices come from each vendor's official pricing page and are re-checked every week. We take no affiliate fees, so rankings aren't for sale.