Capability
Unranked
field median 58
Not eligible for a public rank
Celeris-1 diffusion language model
Released Jul 22, 2026 — see all recent releases
Decision reading
Celeris-1 is Celeris Labs’ first diffusion language model. It accepts text and images, has a 131,072-token context window, costs $0.20 per million input tokens and $0.70 per million output tokens, and has four source-verified benchmark rows. It remains unranked until broader public benchmark coverage is available.
Data as of August 22, 2026 · How the score is built
Strongest published evidence
Instruction Following ranks #30. A well-rounded choice across a range of tasks.
Validate before choosing
4 published rows leave some tracked benchmark slots empty.
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Price
$0.20input / $0.70 output
input median $1
blended $0.45
Speed
1932tok/s
field median 91.5 tok/s
First token 0.61 s
Context
131,072 tokenstokens
field median 200,000
Maximum output length is tracked separately
How much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- AgenticNot measured
- CodingNot measured
- Reasoning1/1 verified
- Knowledge1/1 verified
- Math1/1 verified
- MultilingualNot measured
- MultimodalNot measured
- Inst. Following1/1 verified
Verified sourceProvisionalNot measured
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- celeris-1Celeris-1 model guide
- Context window
- 131,072 tokensCeleris-1 model guide
- Maximum output
- Any positive integer within the 131,072-token shared limit (defaults to 2,048)Celeris-1 model guide
- Knowledge cutoff
- Not sourced yet
- Input modalities
- text, imageCeleris-1 model guide
- Output modalities
- textCeleris-1 model guide
- Parameters
- Not disclosed by the provider
- Availability
- Celeris OpenAI-compatible API (United States)Celeris availability
- Cloud regions
- Global endpoint · US East (us-east-1)Celeris-1 model guide
- Lifecycle
- activeCeleris-1 model guide
- API capabilities
- OpenAI-compatible chat completions · complete JSON responses · SSE streamingCeleris-1 model guide
- Prompt caching
- Not documented in the pricing recordCeleris API pricing
- Self-host
- Weights are not published
- Rate limits
- Workspace-wide sustained request rate; numeric limit not publishedCeleris API rate limits
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticWeight 22%0 benchmarksNot measured | Not measured | Not ranked | Not available | 22% | 0 benchmarks | Not measured |
| CodingWeight 20%0 benchmarksNot measured | Not measured | Not ranked | Not available | 20% | 0 benchmarks | Not measured |
| ReasoningWeight 17%1 benchmarkVerified | Score pending | Not ranked | Not available | 17% | 1 benchmark | Verified |
| KnowledgeRank Not rankedWeight 12%1 benchmarkVerified | 71.3 | Not ranked | Not available | 12% | 1 benchmark | Verified |
| MathWeight 5%1 benchmarkVerified | Score pending | Not ranked | Not available | 5% | 1 benchmark | Verified |
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | Not ranked | Not available | 7% | 0 benchmarks | Not measured |
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | Not ranked | Not available | 12% | 0 benchmarks | Not measured |
| Inst. FollowingRank #30 of 41Percentile 28thWeight 5%1 benchmarkVerified | 52.8 | #30 of 41 | 28th | 5% | 1 benchmark | Verified |
Benchmark ledger
Reasoning opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Reasoning1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| DROPDiscrete Reasoning Over Paragraphs | Score81.4% | Versus best verified row Best verified: Celeris-1 · 81.4% | GapBest verified | WeightDisplay only | Provider exact |
Knowledge1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMLU-ProMassive Multitask Language Understanding Professional | Score75.9% | Versus best verified row Best verified: Qwen3.7 Max · 89.6% | Gap13.7 behind | WeightWeighted 30% | Provider exact |
Math1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| GSM8KGrade School Math 8K | Score93.7% | Versus best verified row Best verified: Celeris-1 · 93.7% | GapBest verified | WeightDisplay only | Provider exact |
Inst. Following1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| IFEvalInstruction-Following Eval | Score80.8% | Versus best verified row Best verified: Qwen3.5-27B · 95% | Gap14.2 behind | WeightWeighted 35% | Provider exact |
Lineage
The sequence follows explicit supersedes links. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Jul 22, 2026 · you are here
Celeris-1Not publicly ranked · $0.2 / $0.7
Base entry
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Celeris-1, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
Celeris-1 is a proprietary model with a 131,072 tokens context window. No explicit reasoning mode is documented in this profile.
Available through Celeris's OpenAI-compatible API in the United States. The model accepts text and image input, returns text, and is intended for short, structured, latency-sensitive tasks; Celeris recommends another model for very long-form generation.
Official exact-value snapshot from Celeris's July 2026 benchmark report and model documentation. Celeris reports 75.9% on the full MMLU-Pro test set with five-shot chain-of-thought exemplars, strict answer-format scoring, and the reasoning budget set to zero. The provider also reports 158 ms p50 response time and 1,664 output tokens per second at p50 in separate first-party measurements; those speed figures remain outside BenchLM's runtime field because the runtime pipeline uses a single independent methodology.
4 of 402 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Instruction Following at #30. a well-rounded choice across a range of tasks.
Model research
What Celeris-1 is built for
Celeris-1 is a proprietary diffusion language model released on July 22, 2026. Celeris built it for short requests that sit inside an interactive path, including structured extraction, routing, classification, query rewriting, and repeated agent steps. The OpenAI-compatible API accepts text and images, returns text, and streams responses by default.
Diffusion is the architectural distinction. Autoregressive models normally commit to one token after another; Celeris says its system combines parallel decoding with sequential processing where language needs it. The model weights and full training specification are not public, so the profile records that description without implying an independent architecture audit.
How to read the speed claims
Celeris reports 1,664 output tokens per second at p50 on 49 successful timed requests from a 50-request workload. It also reports a 158 ms p50 response time alongside the 75.9% MMLU-Pro result. Both tests publish prompt shape, sample count, timing basis, and important limitations.
The cross-provider runtime snapshot supplies the independent speed card. It does not reproduce Celeris’s 1,664-token result because the prompts and timing methods differ. Each number belongs to its own workload.
Price, context, and the practical limit
Pay-as-you-go pricing is $0.20 per million input tokens and $0.70 per million output tokens. The context window is 131,072 tokens shared by the prompt and requested output, API access is currently limited to the United States, and Celeris recommends using another model for very long-form generation.
That makes Celeris-1 a focused candidate rather than a default model for every workload. Published evidence now covers knowledge, grade-school math, instruction following, and passage comprehension, but not coding, tool use, multilingual tasks, or long-context retrieval. A production decision still needs a replay set built from the requests the application will actually send.
Radar
Full release historyCeleris-1 release history
Celeris-1 released
Celeris · Model release
Source confirmed
Frequently asked questions
What is Celeris-1?
Celeris-1 is the first proprietary model from Celeris Labs, released July 22, 2026. It uses diffusion-based language generation, accepts text and images, and returns text. The hosted API exposes a 131,072-token context window shared by the prompt and requested output, with a focus on short, structured requests.
Is Celeris-1 a diffusion language model?
Yes. Celeris describes Celeris-1 as a diffusion language model that generates multiple tokens per model invocation. Its production system combines parallel decoding with sequential processing where needed. The weights and full architecture are not public, so the page records the provider’s description without treating it as independently reproduced.
How much does the Celeris-1 API cost?
Official pricing is $0.20 per million input tokens and $0.70 per million output tokens, metered separately. The pay-as-you-go plan uses the same Celeris-1 model and includes streaming through an OpenAI-compatible API. Enterprise pricing, dedicated clusters, and VPC deployment are quoted separately.
How fast is Celeris-1?
The model page carries an independent runtime snapshot. Celeris separately reports 1,664 output tokens per second at p50 and 158 ms p50 response time on provider-run workloads. Different prompts and timing methods mean the figures are not replications and should be compared only within their respective tests.
Does Celeris-1 support image input?
Yes. Celeris-1 accepts text and images in OpenAI-compatible chat-completion requests and returns text. Celeris documents image input for screenshot triage, document and receipt extraction, and image classification. Images count as prompt tokens at the standard input rate, and no public visual benchmark is attached to the model page yet.
What is the Celeris-1 MMLU-Pro score?
Celeris reports 75.9% on full MMLU-Pro using five-shot chain-of-thought exemplars, strict answer extraction, and a zero reasoning budget. The page also shows Celeris-published GSM8K, IFEval, and DROP rows, but four rows still do not provide enough coverage for a stable overall rank.
Last updated August 22, 2026. Runtime fields remain blank until a sourced snapshot exists.
Watch Celeris-1 in the weekly brief
Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.
Read a sample issueJoin 2,000+ readers.