Kyma APIKyma API
Zhipu AI

Zhipu AI

GLM 5.1

#1 SWE-Bench

Zhipu's prior frontier-open flagship on Kyma — superseded by GLM 5.2 but still available by model ID — built for agentic coding and long-horizon work that runs for hours, not turns.

Modalities

Text → Text

Below release

fp4 · fp8

Weights

Published

zai-org/GLM-5.1

Where it sits in the catalogue Kyma measures

Every number against every text model Kyma prices per token — a stated rule, not a chosen line-up.

Price · input#51/71

$1.89

output $5.94 · cached $0.27675

median $1.013 · best $0.0494

Price · output#49/70

$5.94

per 1M tokens generated

median $3.531 · best $0.218

Availability · 30d#50/70

93.18%

44 observations since 2026-05-02

median 96.5% · best 100.0%

Throughput#48/66

28 tok/s

probe median, one fixed prompt

median 36.3 tok/s · best 377.8 tok/s

Response time#64/66

13.75 s

probe median, to a complete answer

median 2.73 s · best 0.84 s

Context

203K

max output 65,536

published by Zhipu AI, not measured here

Tick above each rail is this model, below it the other 70. Dashed rule is the field median, solid is its best. Better is left; the axis stops at the 90th percentile, so a few models sit past its right edge.

Usage

How much this model is actually called here.

Rank

#28

of 100 active models

Tokens served

15.0M

all-time

Platform share

0.3%

of all tokens

Pricing

Pay per token. Cached input bills at this model’s own cached rate, listed below.

$1.89 /1M input$5.94 /1M output
Hobby10 req/day · 2K in / 500 out
~$2.03/mo
Production1,000 req/day · 2K in / 500 out
~$203/mo
Scale20,000 req/day · 2K in / 500 out
~$4,050/mo
+ Estimate your workload
1,000
2,000
500
30%

Estimated monthly cost

$173

$5.78 / day on GLM 5.1

Same workload on:

GLM 5.2$122-29%
GLM 5.3$126-27%

Estimates use list pricing with cached input at this model's own cached rate. Actual bills depend on real token counts, and every response includes its exact cost.

When to use GLM 5.1

Updated 2026-06-10

Where this model earns its cost — and where it doesn't.

GLM 5.1 is the prior flagship of Zhipu's GLM line on Kyma and sits in the frontier-open quality tier. It is the #1 open-weight model on SWE-Bench Pro and built for long-horizon agentic runs that stretch to eight hours. If your workload is an agent that plans, edits, runs, and retries, this is the model that tier was made for. Its successor, GLM 5.2, is now the GLM flagship on Kyma.

On Kyma its top apps by token volume are coding agents — Cline and OpenClaw — which is the workload it was built for. Every call gets automatic failover if a serving path degrades, and prompt caching bills repeated prompt prefixes at this model's cached input rate — which matters for agents that resend the same long system prompt on every step.

The 203K-token context window holds a serious slice of a codebase plus the agent's working history, and the 64K max output leaves room for large diffs and long reasoning chains. Function calling, structured outputs, and extended reasoning are all supported, so it slots into existing agent frameworks without workarounds.

Autonomous coding agents

Its core design target — multi-step SWE tasks where the agent reads, edits, tests, and iterates across a repository for hours.

Long-horizon workflows

Eight-hour agentic runs are the headline capability; use it for jobs that need sustained planning rather than one-shot answers.

Complex reasoning

Extended reasoning mode works through debugging, architecture decisions, and multi-constraint planning before committing to an answer.

Tool-calling pipelines

Function calling plus structured outputs keep multi-step agent loops parseable and on schema, step after step.

Not ideal for: Image inputs (it's text-only) or latency-sensitive chat UX — it's a medium-speed, premium-priced model that earns its cost on deep agentic work, not quick interactive replies.

How it compares

Against the peers people actually weigh it against.

SpecGLM 5.1GLM 5.2GLM 5.3
Input /1M$1.89$1.101$1.178
Output /1M$5.94$3.76$3.702
Context203K1M1M
ToolsYesYesYes
ReasoningYesYesYes
Throughput28 tok/s73 tok/s28 tok/s

Quick start

Up and running in under two minutes.

  1. 1

    Create an API key

    Sign up and grab a key from the dashboard. GLM 5.1 needs a top-up — the signup credit covers the free tier.

    Get API key →
  2. 2

    Make your first request

    Drop in your key and send a chat completion — fully OpenAI-compatible.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.1",
    "messages": [
      {"role": "user", "content": "Explain prompt caching in one paragraph."}
    ]
  }'
  3. 3

    Stream responses

    Add "stream": true to receive tokens as they arrive.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.1",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

FAQ

Common questions about this model.

What is the context window of GLM 5.1?

GLM 5.1 has a 203K-token context window — roughly 299 pages of text in a single request.

How much does the GLM 5.1 API cost?

$1.89 per 1M input tokens and $5.94 per 1M output tokens, with cached input at $0.27675/1M — 85% off the input rate on repeated prompt prefixes. No subscription; you pay only for what you use.

Does GLM 5.1 support function calling?

Yes — GLM 5.1 supports tool/function calling and structured outputs (JSON mode), so it works with agent frameworks out of the box.

Are the weights for GLM 5.1 publicly available?

Yes. Zhipu AI publishes GLM 5.1's weights as zai-org/GLM-5.1, so you can download and run the model yourself (https://huggingface.co/zai-org/GLM-5.1, read 2026-08-14). Kyma serves it because it is convenient and has failover behind it, not because it is the only way to reach it.

Is GLM 5.1 ever served below the precision its creator released it at?

Sometimes. GLM 5.1 was released by Zhipu AI at bf16 (https://huggingface.co/zai-org/GLM-5.1/blob/main/config.json, read 2026-08-14), and at least one route serving it here reports fp4 or fp8 — narrower than that. Weights compressed below the release usually answer close to it, but it is not the identical artefact, and nothing in the response tells you which one answered. Kyma checked the routes on 2026-09-21, so it is your call rather than a silent one.

How do I use GLM 5.1?

Kyma is OpenAI-compatible: point your SDK's base URL at https://kymaapi.com/v1, use your Kyma API key, and set the model to glm-5.1. Signing up is free, but this model needs a top-up: the $0.50 signup credit covers the free tier only.

Is GLM 5.1 good for agentic coding?

That's exactly what it's built for — SWE-style coding tasks and long-horizon agentic runs — and on Kyma its top apps are coding agents like Cline and OpenClaw. The 203K context plus 64K output means an agent can carry a large working state and still emit full diffs without truncation.

Should I use GLM 5.1 or GLM 5.2?

GLM 5.2 is the newer flagship — it has a larger context window and tops the open-weight Intelligence Index, and glm-flagship resolves to it. Reach for GLM 5.1 only when you want to pin this exact version; send its model ID directly. The X-Kyma-Model header on every response tells you exactly which model ran.

Why run GLM 5.1 through Kyma?

One API key and one OpenAI-compatible endpoint cover this and every other model on the platform. You get automatic failover when a serving path degrades, prompt caching on repeated prefixes — a big deal for agents resending long system prompts — and exact per-request cost in usage.cost.

Needs a top-up — the signup credit covers the free tier.Create account →

More models by Zhipu AI

ModelContextInputOutput
Zhipu AIGLM 5.3 Flash1M$0.1791$0.5972
Zhipu AIGLM 5.31M$1.178$3.702
Zhipu AIGLM 5.21M$1.101$3.76
Zhipu AIGLM 4.7 Flash203K$0.081$0.54
Zhipu AIGLM 4.5 Air131K$0.1945$1.272