Skip to main content

Ultramarine 1 Flash

Ultramarine 1 Flash is a multimodal model built for knowledge work in enterprise operations, finance, law, and consulting. It’s based on GLM-5.3 Flash, with 320B total parameters (18B active) and a 1M-token context window. This model is hosted in the global region. If you require region restrictions, please contact your account team. Serverless may run the model at a different numerical precision than was used in training, so outputs can differ slightly from the dedicated deployments and published evaluation results.

Model card on Hugging Face
Input / output price
$0.15 / $0.50 per 1M
Context
1M tokens
Released
Oct 14, 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 "ultramarine-1-flash".

Read docs

Providers

2 providers, cheapest first, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Concentrateconcentrate/ultramarine-1-flash
$0.15/M$0.50/M
Fireworksfireworks/ultramarine-1-flash-us
$0.15/M$0.50/M

Is a provider down? Fireworks AI status

Pricing

Averaged across 2 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.15 per 1M
Average output
$0.50 per 1M
Average cache read
$0.03 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.15/MConcentrate and Fireworks

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

1.7tokens/sacross providers

Faster than 1% of the other 599 models on the gateway

Response latency

Lower is better

0.6sacross providers

Faster than 81% of the other 780 models on the gateway

Benchmarks

7 published scores from 1 source, each linked to where it was published.

Published scores

BenchmarkScore
Terminal-Bench 2.1paperinstruments.com83.2%
DeepSWE v1.1paperinstruments.com61.5%

Apps

Use Ultramarine 1 Flash 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.

Ultramarine 1 Flash FAQ

Short answers, built from the data on this page.

Ultramarine 1 Flash is a model from Other, released on Oct 14, 2026. Ultramarine 1 Flash is a multimodal model built for knowledge work in enterprise operations, finance, law, and consulting. It’s based on GLM-5.3 Flash, with 320B total parameters (18B active) and a 1M-token context window. This model is hosted in the global region. If you require region restrictions, please contact your account team. Serverless may run the model at a different numerical precision than was used in training, so outputs can differ slightly from the dedicated deployments and published evaluation results.

On the Respan gateway, Ultramarine 1 Flash costs $0.15 per 1M input tokens and $0.50 per 1M output tokens on every provider, after gateway discounts.

Ultramarine 1 Flash is available through 2 providers: Concentrate and Fireworks.

Ultramarine 1 Flash accepts up to 1M 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 "ultramarine-1-flash". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Ultramarine 1 Flash has 7 published benchmark scores, including Terminal-Bench 2.1 83.2%, JobBench 62.9%, and FrontierFinance 53.3. 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.