Skip to main content

GLM 5

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.

Input / output price
$0.95 / $2.55 per 1M
Context
205K tokens
Released
Feb 11, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "zai/glm-5".

Read docs

Providers

8 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
IO.netionet/glm-5
$0.94/M$3.008/M
Inference.netinference_net/glm-5
$0.95/M$2.55/M
Featherlessfeatherless/glm-5
$0.95/M$3.15/M
Bedrockbedrock/glm-5
$1.00/M$3.20/M
Concentrateconcentrate/glm-5
$1.00/M$3.20/M

Is a provider down? AWS Bedrock status, OpenRouter status

Pricing

Averaged across 8 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.98 per 1M
Average output
$3.09 per 1M
Average cache read
$0.35 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$1.00/MBedrock, Concentrate, Novita, Z.ai, and OpenRouterLowest$0.94/MIO.net

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

4.3tokens/sacross providers

Faster than 16% of the other 596 models on the gateway

Response latency

Lower is better

2.2sacross providers

Faster than 45% of the other 776 models on the gateway

Benchmarks

The Respan Index plus 17 published scores from 8 sources, each linked to where it was published.

27.8/ 100

Respan Index#99 of 176

176 ranked models. The shaded band is this model's 95% interval, 22.0 to 36.7. Hy3 preview and Seed1.8 fall inside it, so the gap is within the margin of error.
GLM 5 by category: Coding 10.3, Agents 34.5, Reasoning 26.0, Knowledge & language 22.6 (estimated), Human preference 52.0
  1. 99GLM-527.8
  2. 98Hy3 preview28.3
  3. 100Seed1.827.7

Published scores

BenchmarkScore
SWE-bench Verifieddocs.z.ai77.8%
SWE-bench VerifiedEpoch AI72.1%
Terminal-Bench 2.0docs.z.ai56.2%
WeirdMLHåvard Tveit Ihle48.2%

Compare GLM 5: GLM-5 vs GLM-4.7, GLM-5 vs GLM-5.1, GLM-5 vs Claude Sonnet 4.5, GLM-5 vs GLM-5.3, GLM-5 vs GLM-5.3-Flash, GLM-5 vs GLM-5.2

Apps

Use GLM 5 in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

GLM 5 FAQ

Short answers, built from the data on this page.

GLM 5 is a model from Z.ai, released on Feb 11, 2026. GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.

On the Respan gateway, input starts at $0.94 per 1M tokens on IO.net, and output starts at $2.55 per 1M tokens on Inference.net, after gateway discounts. Averaged across its 8 providers, it costs $0.98 per 1M input tokens and $3.09 per 1M output tokens.

GLM 5 is available through 8 providers: IO.net, Inference.net, Featherless, Bedrock, Concentrate, Novita, and 2 more.

GLM 5 accepts up to 205K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "zai/glm-5". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

GLM 5 scores 27.8 out of 100 on the Respan Index v1.1, ranking #99 of 176 models. By category: Coding 10.3, Agents 34.5, Reasoning 26.0, Knowledge & language 22.6 (estimated), and Human preference 52.0. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

GLM 5 has 17 published benchmark scores, including SWE-bench Verified 77.8%, tau2-bench Telecom 86.8%, and GPQA Diamond 87.8%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.