Patchwire

Z.ai · Released Aug 18, 2026

GLM 5.3

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...

ReasoningOpen weights
  • Top 11%SciCode
  • Top 14%LMCA
  • Top 20%Vending-Bench 2
  • Top 20%WebDev Arena
Compare in showdown → OpenRouter ↗ All Z.ai models
Released
Aug 18 2026
Context window
1M 944K out
Input / 1M tokens
$0.079
Output / 1M tokens
$1.40

Where to run it

37 providers compared

Cheapest: Wafer at $0.079 / $1.40 per 1M input / output tokens — 90% less than the priciest option.

ProviderInputOutputCache readContextMax outputUptimevs. best
Waferus · FP4 $0.079 $1.40 $0.0781M944K100%24h Cheapest
WaferFP4 $0.18 $1.40 $0.181M944K100%24h +18%
Sail Researchus · FP8 $0.50 $1.50 $0.121M944K100%24h +84%
Sail ResearchFP8 $0.50 $1.50 $0.121M944K100%24h +84%
InceptronFP4 $0.55 $1.40 $0.181M944K99.3%24h +86%
DekaLLM $0.18 $2.95 $0.151M944K97.8%24h +113%
NovitaFP8 $0.63 $1.98 $0.121M131K99.7%24h +136%
DeepInfraFP4 $0.56 $2.50 $0.131M131K99.5%24h +156%
SiliconFlowFP8 $0.70 $2.20 $0.131M262K100%24h +163%
TenstorrentFP8 $0.60 $2.50 $0.101.04M131K99.9%24h +163%
GMICloudFP8 $0.70 $2.20 $0.131M944K99%24h +163%
Reka $0.14 $4.20 $0.10262K236K98.2%24h +182%
InferenceNetFP4 $0.08 $4.38 $0.0761M944K100%24h +182%
Relace $0.75 $2.40 $0.0751M131K100%24h +184%
Io NetFP8 $0.49 $3.20 $0.19262K131K96.9%24h +185%
MakoraFP4 $0.14 $4.40 $0.101M128K89.5%24h +194%
MorphFP8 $0.19 $4.40 $0.0471M944K99.3%24h +203%
AkashMLFP8 $0.19 $4.40 $0.191M131K99.9%24h +204%
Phala $0.84 $2.64 $0.161M944K100%24h +215%
DecartFP4 $0.84 $2.68 $0.191M944K99.7%24h +218%
DigitalOcean $0.91 $2.86 $0.171M128K99.9%24h +241%
Alibaba $1.19 $3.74 $0.241M131K100%24h +347%
CoreWeaveFP8 $1.20 $4.00 $0.191M944K97%24h +364%
Friendli $1.26 $3.96 $0.231M944K99.6%24h +373%
Mistralzdr · NVFP4 $1.40 $4.40 $0.141M131K100%24h +425%
PrimeIntellect $1.40 $4.40 $0.261M131K100%24h +425%
Cloudflare $1.40 $4.40 $0.261M944K100%24h +425%
Z.AIFP8 $1.40 $4.40 $0.261M131K100%24h +425%
Mistralnvfp4 · NVFP4 $1.40 $4.40 $0.141M131K99.9%24h +425%
Modal $1.40 $4.40 $0.261M944K99.9%24h +425%
BaiduFP8 $1.40 $4.40 $0.261M131K99.6%24h +425%
CrusoeFP4 $1.40 $4.40 $0.261M944K99.6%24h +425%
BaseTenus · FP4 $1.40 $4.40 $0.141M262K99.1%24h +425%
AtlasCloudFP8 $1.40 $4.40 $0.261M131K98.1%24h +425%
BaseTenFP4 $1.40 $4.40 $0.141M262K98%24h +425%
Fireworks $1.40 $4.40 $0.261M944K97.6%24h +425%
ParasailFP8 $1.40 $4.40 $0.261M944K97.4%24h +425%
Together $1.40 $4.40 $0.261.05M944K96.2%24h +425%
Venice $1.40 $4.40 $0.261M131K93.2%24h +425%
NebiusFP4 $1.40 $4.40 —1.02M922K85.7%24h +425%
Mistralnvfp4/eu · NVFP4 $1.54 $4.84 $0.151M131K100%24h +478%
BaseTenus/fast · FP8 $2.10 $6.60 $0.211M262K100%24h +688%
BaseTenfast · FP8 $2.10 $6.60 $0.211M262K100%24h +688%
Fireworksfast $2.10 $6.60 $0.391M944K99.6%24h +688%
ModelRunFP4 $2.10 $6.60 $0.401M524K97.7%24h +688%
Alibabaprime $2.80 $8.80 $0.561M131K100%24h +951%

Value

Price vs. performance

On the value frontierNo cheaper model beats GLM 5.3 on GPQA Diamond.
25.3%49.0%72.7%96.4% $0.01$0.10$1.00$10.00$100.00 DeepSeek V4.1 Flash 1017 (DeepSeek) — 89.8% · $0.30/1M in Gemini 4 Argon (Google) — 96.4% · $2.00/1M in Claude Haiku 5.5 (Anthropic) — 89.6% · $0.10/1M in Mistral Large 4 (Mistral) — 88.1% · $0.68/1M in GPT-6.1 Sol (OpenAI) — 95.4% · $2.00/1M in Claude Sonnet 5.5 (Anthropic) — 95.6% · $2.00/1M in GPT-6 Luna (OpenAI) — 90.5% · $0.10/1M in GPT-6 Sol (OpenAI) — 94.3% · $2.00/1M in Claude Opus 5.5 (Anthropic) — 90.6% · $4.00/1M in Grok 4.7 (xAI) — 92.7% · $2.00/1M in DeepSeek V4.1 Flash (DeepSeek) — 89.8% · $0.056/1M in GPT-6 Astra (OpenAI) — 95.8% · $10.00/1M in Qwen3.8 Max (0902) (Qwen) — 92.7% · $2.00/1M in Gemini 3.8 Flash (Google) — 95.4% · $0.82/1M in Gemini 3.7 Flash (Google) — 94.8% · $0.75/1M in DeepSeek V4 Pro 0813 (DeepSeek) — 91.7% · $0.66/1M in Grok 4.6 (xAI) — 94.0% · $2.00/1M in DeepSeek V4 Flash 0731 (DeepSeek) — 91.0% · $0.44/1M in Qwen3.7 Flash (Qwen) — 82.3% · $0.03/1M in Claude Opus 5 (Anthropic) — 93.9% · $5.00/1M in Gemini 3.6 Flash (Google) — 94.1% · $0.75/1M in Gemini 3.5 Flash Lite (Google) — 83.3% · $0.30/1M in Kimi K3 (Moonshot AI) — 93.1% · $0.24/1M in GPT-5.6 Luna (OpenAI) — 91.6% · $0.20/1M in GPT-5.6 Terra (OpenAI) — 93.3% · $2.00/1M in GPT-5.6 Sol (OpenAI) — 93.5% · $4.00/1M in Grok 4.5 (xAI) — 93.4% · $2.00/1M in Claude Sonnet 5 (Anthropic) — 90.5% · $2.00/1M in Kimi K2.7 Code (Moonshot AI) — 87.9% · $0.67/1M in Claude Fable 5 (Anthropic) — 85.9% · $10.00/1M in Qwen3.7 Plus (Qwen) — 87.9% · $0.32/1M in MiniMax M3 (MiniMax) — 90.9% · $0.30/1M in Claude Opus 4.8 (Anthropic) — 91.0% · $5.00/1M in Qwen3.7 Max (Qwen) — 90.9% · $1.48/1M in Gemini 3.5 Flash (Google) — 92.8% · $1.50/1M in Gemini 3.1 Flash Lite (Google) — 81.8% · $0.25/1M in Grok 4.3 (xAI) — 88.8% · $1.25/1M in Qwen3.5 Plus 2026-04-20 (Qwen) — 84.9% · $0.30/1M in Qwen3.6 Flash (Qwen) — 83.3% · $0.19/1M in Qwen3.6 35B A3B (Qwen) — 84.9% · $0.10/1M in Qwen3.6 27B (Qwen) — 85.9% · $0.25/1M in GPT-5.5 (OpenAI) — 90.7% · $5.00/1M in DeepSeek V4 Pro 0423 (DeepSeek) — 91.7% · $0.95/1M in DeepSeek V4 Flash 0423 (DeepSeek) — 91.0% · $0.091/1M in Kimi K2.6 (Moonshot AI) — 90.8% · $0.65/1M in Claude Opus 4.7 (Anthropic) — 90.1% · $5.00/1M in Gemma 4 26B A4B (Google) — 73.2% · $0.09/1M in Gemma 4 31B (Google) — 75.8% · $0.20/1M in Qwen3.6 Plus (Qwen) — 88.4% · $0.33/1M in GPT-5.4 Nano (OpenAI) — 78.5% · $0.20/1M in GPT-5.4 Mini (OpenAI) — 86.9% · $0.75/1M in Mistral Small 4 (Mistral) — 47.5% · $0.15/1M in Qwen3.5-9B (Qwen) — 79.0% · $0.10/1M in GPT-5.4 Pro (OpenAI) — 94.6% · $30.00/1M in GPT-5.4 (OpenAI) — 93.3% · $2.50/1M in Gemini 3.1 Flash Lite Preview (Google) — 81.8% · $0.25/1M in Qwen3.5-35B-A3B (Qwen) — 83.5% · $0.15/1M in Gemini 3.1 Pro Preview (Google) — 94.4% · $2.00/1M in Claude Sonnet 4.6 (Anthropic) — 87.4% · $3.00/1M in Qwen3.5 397B A17B (Qwen) — 86.4% · $0.39/1M in Claude Opus 4.6 (Anthropic) — 90.5% · $5.00/1M in Gemini 3 Flash Preview (Google) — 89.4% · $0.50/1M in GPT-5.2 (OpenAI) — 91.4% · $1.75/1M in Ministral 3 8B 2512 (Mistral) — 27.2% · $0.15/1M in Ministral 3 3B 2512 (Mistral) — 25.3% · $0.10/1M in Mistral Large 3 2512 (Mistral) — 51.3% · $0.50/1M in Claude Opus 4.5 (Anthropic) — 86.1% · $5.00/1M in GPT-5.1 (OpenAI) — 87.6% · $1.25/1M in Claude Haiku 4.5 (Anthropic) — 71.2% · $1.00/1M in Claude Sonnet 4.5 (Anthropic) — 82.3% · $3.00/1M in GPT-5 (OpenAI) — 86.2% · $1.25/1M in GPT-5 Mini (OpenAI) — 75.0% · $0.25/1M in GPT-5 Nano (OpenAI) — 69.4% · $0.05/1M in gpt-oss-120b (OpenAI) — 75.8% · $0.15/1M in gpt-oss-20b (OpenAI) — 60.8% · $0.018/1M in Claude Opus 4.1 (Anthropic) — 77.3% · $15.00/1M in Qwen3 30B A3B Instruct 2507 (Qwen) — 55.6% · $0.09/1M in Qwen3 235B A22B Thinking 2507 (Qwen) — 80.0% · $0.45/1M in Qwen3 235B A22B Instruct 2507 (Qwen) — 70.7% · $0.09/1M in Gemini 2.5 Pro (Google) — 85.3% · $1.25/1M in Gemini 2.5 Pro Preview 06-05 (Google) — 85.3% · $1.25/1M in R1 0528 (DeepSeek) — 76.3% · $0.50/1M in Qwen3 30B A3B (Qwen) — 61.7% · $0.12/1M in Qwen3 14B (Qwen) — 63.8% · $0.12/1M in Qwen3 32B (Qwen) — 65.7% · $0.08/1M in GLM 5.3 Flash (Z.ai) — 90.1% · $0.047/1M in GLM 5.2 (Z.ai) — 91.9% · $0.62/1M in GLM 5.1 (Z.ai) — 89.9% · $0.97/1M in GLM 5 (Z.ai) — 87.8% · $0.60/1M in GLM 4.7 Flash (Z.ai) — 60.5% · $0.061/1M in GLM 4.7 (Z.ai) — 83.3% · $0.54/1M in GLM 5.3 (Z.ai) — 90.9% · $0.079/1M in GLM 5.3

GLM 5.3 Other Z.ai Other labs Value frontier · GPQA Diamond vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.

Benchmarks

17 benchmark scores

BenchmarkScoreRankLeader
FrontierSWESoftware engineering · Ultra-long-horizon engineering tasks with a 20-hour budget each 30.2% #10of 19 GPT-6 Astra65.5%
DeepSWESoftware engineering · Original long-horizon tasks across active open-source repos 69.0% #7of 26 GPT-6 Astra74.1%
CursorBenchSoftware engineering · Ambiguous multi-file tasks drawn from real Cursor sessions 42.6% #8of 16 Claude Opus 5.557.8%
FrontierCodeSoftware engineering · Mergeable fixes for hard open-source issues 40.1% #25of 41 Claude Opus 5.554.6%
SciCodeSoftware engineering · Research-coding problems from the natural sciences 59.0% #10of 93 Claude Opus 5.566.9%
APEX-AgentsAgents & computer use · Long professional tasks in banking, consulting and law 56.6% #15of 51 Gemini 4 Argon82.4%
Vending-Bench 2Agents & computer use · Run a simulated vending business for a year (final balance) $8,164 #12of 61 GPT-6 Astra$15,515
SimpleQA VerifiedWriting & content · Factual accuracy on 1,000 short questions 41.0% #41of 66 Gemini 4 Argon76.0%
WebDev ArenaDesign & visual · People vote on which model builds the better website (Elo) 1614 #17of 88 Claude Opus 5.51820
GPQA DiamondReasoning & knowledge · PhD-level biology, chemistry and physics questions 90.9% #29of 92 Gemini 4 Argon96.4%
CritPtReasoning & knowledge · Open-ended, research-level physics problems 19.1% #27of 96 GPT-5.6 Sol32.3%
Chess PuzzlesReasoning & knowledge · Find the single best move in 100 new puzzles 37.0% #38of 70 GPT-6 Astra76.0%
LMCAReasoning & knowledge · Judge the quality of conceptual arguments like experts 55.5% #13of 96 Claude Sonnet 5.568.3%
FrontierMathMaths · Expert-written problems, undergrad to early research (tiers 1–3) 68.8% #26of 72 GPT-6.1 Sol93.7%
FrontierMath Tier 4Maths · Exceptionally hard research-level problems 29.3% #29of 62 GPT-6.1 Sol100.0%
ProofBenchMaths · Graduate maths proofs verified in Lean 4 49.0% #35of 70 Claude Sonnet 5.5100.0%
OTIS Mock AIMEMaths · Competition-style problems harder than MATH Level 5 91.1% #49of 90 Gemini 4 Argon100.0%

Specs

Details

Model ID
z-ai/glm-5.3
Developer
Z.ai
Release date
Aug 18, 2026 ·
Context window
1,048,576 tokens
Max output
943,718 tokens
API price
$0.079 / $1.40 per 1M input / output tokens
Providers
37
Input types
text
Reasoning
Yes
Tool calling
Yes
Open weights
Yes
Free tier
No

Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. Uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.