Long documents
Prompts that approach the documented context limit
Ember-1
Ember-1 has the larger documented context window.
Confidence: documented
Ember-1 vs Inkling
Updated September 28, 2026. We do not rank this pair: at least one has no public score. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
Share or export
Decision reading
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. 3 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 3
- Ember-1 only
- 2
- Inkling only
- 18
- Like-for-like categories
- 0 / 8
Supported: InklingHow the comparison works
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Chat turn cost
1K fresh input + 500 output tokens
Inkling
Inkling has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesCache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Inkling
Inkling has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Inkling
Inkling has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesCoding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Ember-1 is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limitedAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Ember-1 is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limited
Which one for a specific job
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
—Ember-136.5Inkling
Not comparable · BenchAlign v5.7
The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
2 Ember-1 only
3 Shared
18 Inkling only
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
SWE-bench VerifiedCoding
Normalized gap 14.6Ember-1:92.2%Inkling:77.6%
Bars run 0–100 on each benchmark’s normalized display scale
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign v5.7 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Agentic
Not comparable- Ember-1
- Not ranked
- Inkling
- 36.2
- Supported · #57/111
- Basis
- BenchAlign v5.7 lane · 2 vs 4 public rows
- Reading
- Not comparable
Coding
Not comparable- Ember-1
- Not ranked
- Inkling
- 36.5
- Supported · #67/136
- Basis
- BenchAlign v5.7 lane · 3 vs 6 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Ember-1
- Not ranked
- Inkling
- 75.5
- #12/27
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Ember-1
- Not ranked
- Inkling
- 49.7
- #41/50
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- Ember-1
- Not ranked
- Inkling
- 54.4
- Supported · #44/160
- Basis
- BenchAlign v5.7 lane · 0 vs 6 public rows
- Reading
- Not comparable
Multilingual
Not comparable- Ember-1
- Not ranked
- Inkling
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Ember-1
- Not ranked
- Inkling
- 83.9
- #44/124
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Math
Not comparable- Ember-1
- Not ranked
- Inkling
- 78.5
- Unranked · 1 rankable row
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
| Category | Ember-1 | Inkling | Basis | Reading |
|---|---|---|---|---|
| Agentic | Not ranked | 36.2Supported · #57/111 | Not comparableBenchAlign v5.7 lane · 2 vs 4 public rows | Not comparable |
| Coding | Not ranked | 36.5Supported · #67/136 | Not comparableBenchAlign v5.7 lane · 3 vs 6 public rows | Not comparable |
| Reasoning | Not ranked | 75.5#12/27 | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | 49.7#41/50 | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
| Knowledge | Not ranked | 54.4Supported · #44/160 | Not comparableBenchAlign v5.7 lane · 0 vs 6 public rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | 83.9#44/124 | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Math | Not ranked | 78.5Unranked · 1 rankable row | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.7) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Supported evidence per lane · bars run 0–100Methodology
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Ember-1
- $0.0105
- Fits in one request
- Inkling
- $0.00421
- Fits in one request
Inkling has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Ember-1
- $0.195
- Fits in one request
- Inkling
- $0.10754
- Fits in one request
Inkling has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Ember-1
- $0.27
- Fits in one request
- Inkling
- $0.159
- Fits in one request
Inkling has the lower modeled cost
Costs use the listed standard API rates.
Cached input falls back to the list input rate only where a cached rate is unpublished
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationEmber-1Inkling
Context window
Maximum documented context; output-token limits may be lower.
Ember-1
Inkling
1M
API model ID
Ember-1
accounts/fireworks/models/ember-1
Fireworks Ember-1 model pageInkling
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Ember-1
$0.3 per 1M cached input tokens
Fireworks Ember-1 model pageInkling
$0.374 per 1M cached input tokens
Documented inputs
Ember-1
Not sourced
Inkling
Not sourced
Documented outputs
Ember-1
Not sourced
Inkling
Not sourced
Provider availability
Ember-1
Not sourced
Inkling
Not sourced
Reasoning profile
Ember-1
Reasoning
Inkling
Hybrid
Weight access
Ember-1
Proprietary
Inkling
Open Weight
License
Ember-1
Proprietary
Inkling
Open Weight
Release date
Ember-1
2026-09-23
Inkling
2026-07-15
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
- Workload cost
- Repository review: $0.195 vs $0.10754. Cache-heavy agent loop: $0.27 vs $0.159.
- Context tradeoff
- Ember-1 has the larger documented window (1.04M).
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Ember-1 or Inkling?
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Ember-1 or Inkling?
Ember-1 is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, Ember-1 or Inkling?
Ember-1 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, Ember-1 or Inkling?
For the stated presets, chat costs $0.0105 on Ember-1 and $0.00421 on Inkling; repository review costs $0.195 and $0.10754; the cache-heavy agent loop costs $0.27 and $0.159. Costs use the listed standard API rates.
Which has the larger context window, Ember-1 or Inkling?
Ember-1 has the larger documented context window: 1.04M, compared with 1M.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence23 rows
Agentic
Terminal-Bench 2.1
Ember-182.0%SourceInkling63.8%SourceEmber-1 leads this result
τ²-bench Airline
Ember-166.0%SourceInkling—Not directly comparable
BrowseComp
Ember-1—Inkling77.1%SourceNot directly comparable
MCP Atlas
Ember-1—Inkling74.1%SourceNot directly comparable
Terminal-Bench 2.1 (Vals)
Ember-1—Inkling47.6%SourceNot directly comparable
Coding
Terminal-Bench 2.1
Ember-182.0%SourceInkling63.8%SourceEmber-1 leads this result
SWE-bench Verified
Ember-192.2%SourceInkling77.6%SourceEmber-1 leads this result
DeepSWE
Ember-175.2%SourceInkling—Not directly comparable
SWE-bench Pro
Ember-1—Inkling54.3%SourceNot directly comparable
FrontierSWE v2
Ember-1—Inkling4.1%SourceNot directly comparable
LiveCodeBench (Vals)
Ember-1—Inkling85.5%SourceNot directly comparable
SWE-bench (Vals)
Ember-1—Inkling77.6%SourceNot directly comparable
Multimodal
Knowledge
GPQA
Ember-1—Inkling87.9%SourceNot directly comparable
GPQA-D
Ember-1—Inkling87.9%SourceNot directly comparable
HLE
Ember-1—Inkling46%SourceNot directly comparable
HLE w/o tools
Ember-1—Inkling30%SourceNot directly comparable
GPQA Diamond (Vals)
Ember-1—Inkling87.1%SourceNot directly comparable
MMLU-Pro (Vals)
Ember-1—Inkling86.3%SourceNot directly comparable
Instruction following
IFBench
Ember-1—Inkling79.8%SourceNot directly comparable
Math
AIME26
Ember-1—Inkling97.1%SourceNot directly comparable
23 public results · 3 shared
Watch Ember-1 vs Inkling
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.
Last updated September 28, 2026