All systems operational

Live status and speed of the Umans Code gateway and its models, refreshed every 30 seconds. For each model we show its output speed and median time to first token.

6 / 6production models operational

98.89%gateway uptime · 90 days

0models in testing

0active issues

Production

Models in production

6 listed

tok/s = output tokens per second · TTFT = time to first token · p50 = median over the last 5 minutes. On each gauge the midpoint is that model's target; the marker sits further right when it's beating target (faster TTFT, higher throughput).

Umans DeepSeek V4 Flash Recommended

umans-deepseek-v4-flash-0731 · DeepSeek-V4-Flash · DeepSeek

Operational

107.6tok/s

throughput · p50 · last 5 min

876ms

TTFT · p50 · last 5 min

100.00%

uptime · 24h

DeepSeek V4 Flash: DeepSeek's fast agentic coding MoE (284B total, 13B active), served from the official 0731 release on a 1M-token context. The cheapest production model in the lineup for real agentic work. Reasoning has four modes: non-think (none), think low (low, the default), think high (high) and think max (max). Served on our own GPU infrastructure with high availability.

90-day speed trends & events →

90 days agoin production since Aug 3, 2026today

Context

1049K

Max output

393K

Recommended

393K

Vision

Tools

Yes

Reasoning

Toggle · none/low/high/max

Weights

Full weights ↗

Umans Kimi K3

umans-kimi-k3 · Kimi K3 · Moonshot

Operational

61.4tok/s

throughput · p50 · last 5 min

2.10s

TTFT · p50 · last 5 min

100.00%

uptime · 24h

Kimi K3: Moonshot's most capable model and the first open 3T-class release - 2.8T parameters, a 1M-token context window, and native vision, built for repository-scale understanding and long agentic runs at closed-frontier quality (92.4% vs Claude Fable 5's 92.6% across ~1,030 agentic tasks in Fireworks' independent study). It thinks by default at maximum reasoning effort; select none, low, high, or max to trade depth for speed.

90-day speed trends & events →

90 days agoin production since Jul 31, 2026today

Context

1049K

Max output

131K

Recommended

131K

Vision

Yes

Tools

Yes

Reasoning

Toggle · none/low/high/max

Weights

Full weights ↗

Umans DeepSeek V4 Pro

umans-deepseek-v4-pro-0813 · DeepSeek-V4-Pro-0813 · DeepSeek

Operational

67.9tok/s

throughput · p50 · last 5 min

2.10s

TTFT · p50 · last 5 min

99.90%

uptime · 24h

DeepSeek V4 Pro, served from the official 0813 release: DeepSeek's flagship coding and reasoning MoE, built for long-horizon agentic coding and demanding tool-heavy workloads on a 1M-token context window. The 0813 release supersedes the April preview with substantially stronger agentic performance. Reasoning has three modes: non-think (none), think high (high, the default) and think max (max). Billed per token ($1.32 / $3.96 / $0.044 per 1M; input / output / cache read). Served on our own GPU infrastructure with high availability.

90-day speed trends & events →

90 days agoin production since Aug 15, 2026today

Context

1049K

Max output

393K

Recommended

393K

Vision

Tools

Yes

Reasoning

Toggle · none/high/max

Weights

Full weights ↗

Umans Flash Fastest

umans-flash · Qwen3.6-35B-A3B · Qwen

also served as umans-qwen3.6-35b-a3b

Operational

398.5tok/s

throughput · p50 · last 5 min

330ms

TTFT · p50 · last 5 min

99.34%

uptime · 24h

Our fastest model: a light workflow complement, not a standalone coder. Think Haiku next to Opus: not everything needs a frontier model, and Flash's speed (200+ tokens per second) compounds on the roles around umans-coder: gathering context, scout subagents, research, summaries, documentation, and quick edits.

90-day speed trends & events →

90 days agoin production since May 3, 2026today

Context

262K

Max output

262K

Recommended

33K

Vision

Yes

Tools

Yes

Reasoning

Toggle · none/low/medium/high

Weights

FP8 ↗

Umans GLM 5.2 Deprecated

umans-glm-5.2 · GLM

deprecated · serving until Aug 23, 2026 · successor umans-deepseek-v4-pro-0813

Operational

104.7tok/s

throughput · p50 · last 5 min

3.94s

TTFT · p50 · last 5 min

100.00%

uptime · 24h

GLM 5.2 is our best model for coding right now, with a 400K context window for large codebases. Vision is available on the Anthropic Messages API (`/v1/messages`) only, through a server-side handoff (GLM 5.2 generates the text, Kimi preprocesses the image); that handoff will be retired soon in favour of more efficient client-side image handling. Deprecated: use `umans-deepseek-v4-pro-0813` instead (sunset 2026-08-23).

90-day speed trends & events →

90 days agoin production since Jun 21, 2026today

Context

406K

Max output

131K

Recommended

131K

Vision

Via handoff

Tools

Yes

Reasoning

Toggle · none/high/max

Weights

FP8 ↗

Umans Kimi K2.7 Code Deprecated

umans-kimi-k2.7 · Kimi K2.7-Code · Moonshot

deprecated · serving until Aug 10, 2026 · successor umans-kimi-k3

successor to Kimi K2.6

also served as umans-coder

Operational

167.2tok/s

throughput · p50 · last 5 min

244ms

TTFT · p50 · last 5 min

100.00%

uptime · 24h

Kimi K2.7-Code via Umans Code - Moonshot's strongest coding model and the successor to Kimi K2.6. Built for complex, tool-heavy agentic coding; it reasons more efficiently than K2.6, so agent sessions run faster at the same depth. Deprecated: use `umans-kimi-k3` instead (sunset 2026-08-10).

90-day speed trends & events →

90 days agoin production since Jun 12, 2026today

Context

262K

Max output

262K

Recommended

33K

Vision

Yes

Tools

Yes

Reasoning

Always on

Weights

Full weights ↗

History

Gateway uptime

90-day window · daily worst status

90 days ago98.89% operationaltoday

Changelog

Recent events & model lifecycle

releases, retirements, and playground changes

Aug 182026

New Labs experiment: Umans Qwen3.8 27B Testing

A new lab opened on umans-qwen3.8-27b-lab: Qwen3.8 27B served from Qwen's official FP8 checkpoint, a compact dense model with native image and video understanding and a 256K context window, thinking at xhigh effort by default (dial to low or medium, or turn thinking off). Free and seat-gated while the experiment runs, served at limited capacity and low availability: it is a lab, so expect it to be flaky and to go down under load. Crash it, give it a moment, and try again. The window closes August 19, 2026.

Aug 152026

Released pay-per-token: Umans DeepSeek V4 Pro Released

umans-deepseek-v4-pro-0813 joins the lineup as the long-context coding flagship: DeepSeek's official 0813 release of V4 Pro, the checkpoint that served here as the seat-gated pre-release lab since August 13, with a 1M context window and thinking at high effort by default (dial to max when a task deserves more). Billed per token: $1.32 / $3.96 / $0.044 per 1M (input / output / cache read). It succeeds GLM 5.2, which is deprecated and sunsets on August 23, 2026. The pre-release window's metrics stay on the model's status page as its pre-release period (before Aug 15). Served on our own GPU infrastructure with high availability.

Aug 152026

Playground closed: Umans DeepSeek V4 Pro 0813 (pre-release) Testing

The V4 Pro 0813 pre-release window closed at the pay-per-token release: the production id now bills per token, so the seat-gated experiment on umans-deepseek-v4-pro-0813-lab ended rather than charge anyone by surprise. Thanks to everyone who pushed it, including through the August 14 outage, and shared findings; both the fixes and the metrics carried straight into the release. The model keeps serving as umans-deepseek-v4-pro-0813: the model stays.

Aug 132026

New Labs experiment: Umans DeepSeek V4 Pro 0813 Testing

A new lab opened on umans-deepseek-v4-pro-0813-lab: DeepSeek V4 Pro served from DeepSeek's own pre-release 0813 checkpoint - the flagship coding and reasoning MoE, ahead of its official release. Free and seat-gated while the experiment runs, served at limited capacity and low availability: it is a lab, so expect it to be flaky and to go down under load - crash it, give it a moment, and try again.

Aug 132026

Playground closed: Umans DeepSeek V4 Flash Vision Testing

The vision V4 Flash test window closed after two days. Thanks to everyone who pushed images through it and shared findings. The umans-deepseek-v4-flash-0731-vision-lab id is unlisted and stops serving; the text V4 Flash keeps serving as the pay-per-token umans-deepseek-v4-flash-0731 regardless: the model stays.

Aug 112026

New Labs experiment: Umans DeepSeek V4 Flash Vision Testing

The text V4 Flash lab window ended and a new vision lab opened on umans-deepseek-v4-flash-0731-vision-lab: our own V4 Flash with vision added, the same performance and speed as the text V4 Flash plus the ability to read images. Free and seat-gated while the experiment runs, served at limited capacity and low availability: it is a lab, so expect it to be flaky and to go down under load - crash it, give it a moment, and try again. (The vision lab closed on 2026-08-13 - see the entry above.)

Aug 32026

Released pay-per-token: Umans DeepSeek V4 Flash Released

umans-deepseek-v4-flash-0731 joins the lineup as the cheapest way we serve real agentic work: $0.14 / $0.28 / $0.028 per 1M (input / output / cache read), a 1M context window, thinking at low effort by default (dial up high or max when a task deserves more). It is the new default for new chats and CLI setups. Founding users pay the 10x cheaper cache rate until Monday, August 10, 2026 (see /pricing). Served on our own GPU infrastructure with high availability.

Aug 32026

The V4 Flash lab continues as umans-deepseek-v4-flash-0731-lab Testing

The V4 Flash pilot closed at the pay-per-token release: the production id now bills per token, so the seat-gated pilot on it ended rather than charge anyone by surprise. The lab reopened on the new umans-deepseek-v4-flash-0731-lab id with a smaller cohort - free, seat-gated, same experimental capacity as before. The model keeps serving as umans-deepseek-v4-flash-0731 regardless: the model stays. (The text lab closed on 2026-08-11 when the vision lab opened - see the next entry.)

Aug 12026

Generally available: Umans Kimi K3 Released

The Kimi K3 Labs pilot closed and umans-kimi-k3 is generally available: no Labs seat required anymore - plan and pay-per-token keys alike get the 1M context window, native vision, and max-effort reasoning at $3.00 / $15.00 / $0.30 per 1M (input / output / cache read).

Jul 312026

Released pay-per-token: Umans Kimi K3 Released

umans-kimi-k3 opened to pay-per-token (wallet and service-account keys): Moonshot's largest open model, a 1M context window, native vision, and max reasoning effort by default, billed at $3.00 / $15.00 / $0.30 per 1M (input / output / cache read).

Older events 10

Jul 162026

Playground closed: Umans DeepSeek V4 Pro DSpark Testing

The DSpark test window closed after two days. What we took from it: DSpark speculative decoding lets us serve more users at once while keeping each session fast enough, the DeepSeek V4 architecture is now mature enough to serve at scale, and the model itself is solid. V4 Pro is not joining the lineup though: it is still a preview build, and the issues testers hit (DSML leaks, language bleed, long-context artifacts) are model-side. DeepSeek confirmed a better version is coming this month, so we would rather roll the learnings into that. Thanks to everyone who tested.

Jul 142026

Playground opened: Umans DeepSeek V4 Pro DSpark Testing

umans-deepseek-v4-pro-dspark entered the playground for a short, seat-gated test window: DeepSeek V4 Pro served from the original weights with DSpark speculative decoding. Experimental and temporary; not for production.

Jul 22026

Playground closed: Umans GLM 5.2 NVFP4 Testing

The short NVFP4 test window ended after four days. Thanks to everyone who pushed it and shared findings.

Jun 292026

Playground opened: Umans GLM 5.2 NVFP4 Testing

umans-glm-5.2-nvfp4 entered the playground for a short, low-capacity test window. Experimental and temporary; not for production.

Jun 242026

Retired: Umans GLM 5.1 Retired

umans-glm-5.1 was retired in favour of GLM 5.2. Requests to the old id now return a clear deprecation error pointing to umans-glm-5.2.

Jun 212026

Released to production: Umans GLM 5.2 Released

umans-glm-5.2 was released as the long-context model, with a 405K context window, after a pre-release period that started Jun 16.